"CLI-Anything: Making ALL Software Agent-Native" -- CLI-Hub: https://clianything.cc/
Python
fix(joplin):timeout and node
27494539a-hub2cf307a05e2a
diff --git a/README.md b/README.mdindex 350bfcf53..2789c6597 100644--- a/README.md+++ b/README.md@@ -1,19 +1,19 @@-<h1 align="center"><img src="assets/icon.png" alt="" width="64" style="vertical-align: middle;"> CLI-Anything: Making ALL Software Agent-Native</h1>+<h1 align="center"><img src="assets/icon.png" alt="" width="64" style="vertical-align: middle;"> CLI-Anything: Making ALL Software Agent-Native</h1><div align="center"><a href="https://trendshift.io/repositories/22991" target="_blank"><img src="https://trendshift.io/api/badge/repositories/22991" alt="HKUDS%2FCLI-Anything | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a></div><p align="center">- <strong>Today's Software Serves Humans👨�? Tomorrow's Users will be Agents🤖.<br>+ <strong>Today's Software Serves Humans????? Tomorrow's Users will be Agents??.<br>CLI-Anything: Bridging the Gap Between AI Agents and the World's Software</strong><br></p>-**🌐 [CLI-Hub](https://hkuds.github.io/CLI-Anything/)**: `pip install cli-anything-hub` then `cli-hub install <name>` �?browse, install, and manage all community-built CLIs. Want to add your own? [Open a PR](https://github.com/HKUDS/CLI-Anything/blob/main/CONTRIBUTING.md) �?the hub updates instantly.+**?? [CLI-Hub](https://hkuds.github.io/CLI-Anything/)**: `pip install cli-anything-hub` then `cli-hub install <name>` ??browse, install, and manage all community-built CLIs. Want to add your own? [Open a PR](https://github.com/HKUDS/CLI-Anything/blob/main/CONTRIBUTING.md) ??the hub updates instantly.-**🎬 [See Demos](#-real-world-demos)**: Watch AI agents use generated CLIs plus preview, live preview, and trajectory loops to produce real artifacts �?CAD builds, 3D scenes, diagrams, gameplay, subtitles, and more.+**?? [See Demos](#-real-world-demos)**: Watch AI agents use generated CLIs plus preview, live preview, and trajectory loops to produce real artifacts ??CAD builds, 3D scenes, diagrams, gameplay, subtitles, and more.-**🙋 [Become a Contributor, or Request a CLI]**: [Join us](https://github.com/HKUDS/CLI-Anything/issues/new?template=contributor-signup.yml)! Sign up to build a new CLI harness �?once reviewed and merged, you'll gain access as one of our community contributors! Wish CLI-Anything supported a specific software or service? Submit a [wishlist request](https://github.com/HKUDS/CLI-Anything/issues/new?template=cli-wishlist.yml)!+**?? [Become a Contributor, or Request a CLI]**: [Join us](https://github.com/HKUDS/CLI-Anything/issues/new?template=contributor-signup.yml)! Sign up to build a new CLI harness ??once reviewed and merged, you'll gain access as one of our community contributors! Wish CLI-Anything supported a specific software or service? Submit a [wishlist request](https://github.com/HKUDS/CLI-Anything/issues/new?template=cli-wishlist.yml)!<p align="center"><a href="#-quick-start"><img src="https://img.shields.io/badge/Quick_Start-5_min-blue?style=for-the-badge" alt="Quick Start"></a>@@ -24,8 +24,8 @@ CLI-Anything: Bridging the Gap Between AI Agents and the World's Software</stron</p><p align="center">- <img src="https://img.shields.io/badge/python-�?.10-blue?logo=python&logoColor=white" alt="Python">- <img src="https://img.shields.io/badge/click-�?.0-green" alt="Click">+ <img src="https://img.shields.io/badge/python-??.10-blue?logo=python&logoColor=white" alt="Python">+ <img src="https://img.shields.io/badge/click-??.0-green" alt="Click"><img src="https://img.shields.io/badge/pytest-100%25_pass-brightgreen" alt="Pytest"><img src="https://img.shields.io/badge/coverage-unit_%2B_e2e-orange" alt="Coverage"><img src="https://img.shields.io/badge/output-JSON_%2B_Human-blueviolet" alt="Output">@@ -33,7 +33,7 @@ CLI-Anything: Bridging the Gap Between AI Agents and the World's Software</stron<a href="https://github.com/HKUDS/.github/blob/main/profile/README.md"><img src="https://img.shields.io/badge/WeChat-Group-C5EAB4?style=flat&logo=wechat&logoColor=white" alt="WeChat"></a></p>-**One Command Line**: Make any software agent-ready for Pi, OpenClaw, nanobot, Cursor, Claude Code, etc. [**中文文档**](README_CN.md) | [**日本語ドキュメン�?*](README_JA.md)+**One Command Line**: Make any software agent-ready for Pi, OpenClaw, nanobot, Cursor, Claude Code, etc. [**�����ĵ�**](README_CN.md) | [**�ձ��Z�ɥ�����??*](README_JA.md)<p align="center"><img src="assets/cli-typing.gif" alt="CLI-Anything typing demo" width="800">@@ -45,114 +45,114 @@ CLI-Anything: Bridging the Gap Between AI Agents and the World's Software</stron----## 📰 News+## ?? News> Thanks to all invaluable efforts from the community! More updates continuously on the way everyday..-- **2026-04-18** 🧩 **All SKILL.md files are now being unified under the top-level `skills/` directory** �?every CLI skill can be installed from one canonical source with `npx skills add HKUDS/CLI-Anything --skill <skill-name> -g -y`. We also added root-skill validation CI, synced contribution / PR docs and REPL skill-path hints to the new layout, and refreshed the **CLI-Hub** install-first frontend around the new `npx skills` flow.+- **2026-04-18** ?? **All SKILL.md files are now being unified under the top-level `skills/` directory** ??every CLI skill can be installed from one canonical source with `npx skills add HKUDS/CLI-Anything --skill <skill-name> -g -y`. We also added root-skill validation CI, synced contribution / PR docs and REPL skill-path hints to the new layout, and refreshed the **CLI-Hub** install-first frontend around the new `npx skills` flow.-- **2026-04-17** 🌐 **CLI-Hub** received another install UX pass �?public registry metadata and skill coverage were tightened, visit counting was corrected, and the web hub was further refined. 🧪 **Shotcut** render output duration was fixed (#92). 📝 **SKILL** contribution paths were corrected for the new docs flow (#224), and the skill generator now safely handles empty intros (#203).+- **2026-04-17** ?? **CLI-Hub** received another install UX pass ??public registry metadata and skill coverage were tightened, visit counting was corrected, and the web hub was further refined. ?? **Shotcut** render output duration was fixed (#92). ?? **SKILL** contribution paths were corrected for the new docs flow (#224), and the skill generator now safely handles empty intros (#203).-- **2026-04-16** 🗺�?**QGIS CLI** merged (#207) �?a full GIS / map authoring harness landed. 🧬 **UniMol Tools CLI** merged (#219) for molecular modeling workflows. 🌐 **CLI-Hub** also added more public CLIs, including **py4csr**, refreshed its generated meta-skill, corrected SKILL contribution docs, and fixed `apt-get` package extraction in skill generation (#204).+- **2026-04-16** ????**QGIS CLI** merged (#207) ??a full GIS / map authoring harness landed. ?? **UniMol Tools CLI** merged (#219) for molecular modeling workflows. ?? **CLI-Hub** also added more public CLIs, including **py4csr**, refreshed its generated meta-skill, corrected SKILL contribution docs, and fixed `apt-get` package extraction in skill generation (#204).-- **2026-04-16** 📈 **Unreal Insights CLI** expanded �?added background capture session control (`capture start/status/snapshot/stop`), engine-root-matched `UnrealInsights.exe` resolution/build flows, and refreshed docs/tests for the new orchestration workflow.+- **2026-04-16** ?? **Unreal Insights CLI** expanded ??added background capture session control (`capture start/status/snapshot/stop`), engine-root-matched `UnrealInsights.exe` resolution/build flows, and refreshed docs/tests for the new orchestration workflow.-- **2026-04-15** 🌐 **CLI-Hub** updated to **v0.2.0** �?the PyPI package now supports public CLIs from multiple install sources (`pip`, `npm`, `brew`, bundled/system tools), backed by a new `public_registry.json`. The Hub frontend was redesigned with separate **CLI-Anything CLIs** and **Public CLIs** decks, and live end-to-end checks now cover real install, update, and uninstall flows across both pip and npm packages.+- **2026-04-15** ?? **CLI-Hub** updated to **v0.2.0** ??the PyPI package now supports public CLIs from multiple install sources (`pip`, `npm`, `brew`, bundled/system tools), backed by a new `public_registry.json`. The Hub frontend was redesigned with separate **CLI-Anything CLIs** and **Public CLIs** decks, and live end-to-end checks now cover real install, update, and uninstall flows across both pip and npm packages.-- **2026-04-14** 🧭 **Safari CLI** merged (#212) and added to the Hub registry �?browser automation via `safari-mcp`. 🎬 **Kdenlive** also received compatibility fixes for Gen 5 project output and invalid project generation.+- **2026-04-14** ?? **Safari CLI** merged (#212) and added to the Hub registry ??browser automation via `safari-mcp`. ?? **Kdenlive** also received compatibility fixes for Gen 5 project output and invalid project generation.-- **2026-04-13** 📓 **Obsidian CLI** merged (#211) �?knowledge management harness via the Local REST API, with 48 unit tests and 7 E2E tests. ⛓️ **Eth2-Quickstart CLI** merged (#195) �?Ethereum staking node management harness. 📚 **Zotero CLI** updated to v0.4.1 (#201) �?now shipped from its standalone repo, and CLI-Hub gained support for remote `skill_md` URLs.+- **2026-04-13** ?? **Obsidian CLI** merged (#211) ??knowledge management harness via the Local REST API, with 48 unit tests and 7 E2E tests. ?? **Eth2-Quickstart CLI** merged (#195) ??Ethereum staking node management harness. ?? **Zotero CLI** updated to v0.4.1 (#201) ??now shipped from its standalone repo, and CLI-Hub gained support for remote `skill_md` URLs.-- **2026-04-11** 🔗 **n8n CLI** merged (#188) �?workflow automation harness for self-hosted automation flows. 🔧 **Exa CLI** fix (#205) added the `x-exa-integration` header for usage tracking. 📦 **CLI-Hub** also gained its PyPI auto-publish workflow and package refresh pipeline.+- **2026-04-11** ?? **n8n CLI** merged (#188) ??workflow automation harness for self-hosted automation flows. ?? **Exa CLI** fix (#205) added the `x-exa-integration` header for usage tracking. ?? **CLI-Hub** also gained its PyPI auto-publish workflow and package refresh pipeline.-- **2026-04-10** 📦 **CLI-Hub package manager** launched �?`pip install cli-anything-hub` to browse, search, install, update, and uninstall CLI-Anything harnesses from one command. The web Hub also shipped its first install-focused frontend refresh and "Empower yourself" toolkit card.+- **2026-04-10** ?? **CLI-Hub package manager** launched ??`pip install cli-anything-hub` to browse, search, install, update, and uninstall CLI-Anything harnesses from one command. The web Hub also shipped its first install-focused frontend refresh and "Empower yourself" toolkit card.<details>-<summary>Earlier news (Apr 1�?)</summary>+<summary>Earlier news (Apr 1??)</summary>-- **2026-04-09** 🧹 Cleanup and docs pass (#200) �?fixed Openscreen test subtotals, added Openscreen to the Chinese README and project structure, and clarified `/cli-anything` command syntax in the docs.+- **2026-04-09** ?? Cleanup and docs pass (#200) ??fixed Openscreen test subtotals, added Openscreen to the Chinese README and project structure, and clarified `/cli-anything` command syntax in the docs.-- **2026-04-08** 🎬 **Openscreen CLI** merged (#183) �?screen recording editor harness with 101 tests. ☁️ **CloudAnalyzer CLI** merged (#181) �?cloud cost analysis harness with 27 commands. 🌊 **SeaClip / PM2 / ChromaDB** harnesses merged (#129).+- **2026-04-08** ?? **Openscreen CLI** merged (#183) ??screen recording editor harness with 101 tests. ?? **CloudAnalyzer CLI** merged (#181) ??cloud cost analysis harness with 27 commands. ?? **SeaClip / PM2 / ChromaDB** harnesses merged (#129).-- **2026-04-07** 🔄 **Dify Workflow CLI** merged (#191) �?workflow automation wrapper. 🔧 **Inkscape** auto-save fix (#193, fixes #182). 🛡�?**DomShell security hardening** (#156) �?URL validation and DOM sanitization for the browser CLI. 🥧 **Pi Coding Agent extension** merged (#178).+- **2026-04-07** ?? **Dify Workflow CLI** merged (#191) ??workflow automation wrapper. ?? **Inkscape** auto-save fix (#193, fixes #182). ????**DomShell security hardening** (#156) ??URL validation and DOM sanitization for the browser CLI. ?? **Pi Coding Agent extension** merged (#178).-- **2026-04-06** 🔍 **Exa CLI** merged (#172) �?AI-powered web search and answers harness. 🎮 **Godot CLI** merged (#140) �?game engine harness with a full demo-game E2E pipeline. ☁️ **CloudAnalyzer** review fixes and frontend improvements also landed.+- **2026-04-06** ?? **Exa CLI** merged (#172) ??AI-powered web search and answers harness. ?? **Godot CLI** merged (#140) ??game engine harness with a full demo-game E2E pipeline. ?? **CloudAnalyzer** review fixes and frontend improvements also landed.-- **2026-04-03** 🧪 **WireMock CLI** merged (#170) �?HTTP mock server harness for API testing. 🥧 **Pi Coding Agent** extension support also landed, and CLI demo recordings were added to the docs.+- **2026-04-03** ?? **WireMock CLI** merged (#170) ??HTTP mock server harness for API testing. ?? **Pi Coding Agent** extension support also landed, and CLI demo recordings were added to the docs.-- **2026-04-01** ⚔️ **Slay the Spire II CLI** merged (#148) �?deck-building roguelike harness. 🎥 **VideoCaptioner CLI** merged (#166) �?AI-powered video captioning harness. 🛰�?**IntelWatch** was added to the registry for B2B OSINT workflows.+- **2026-04-01** ?? **Slay the Spire II CLI** merged (#148) ??deck-building roguelike harness. ?? **VideoCaptioner CLI** merged (#166) ??AI-powered video captioning harness. ????**IntelWatch** was added to the registry for B2B OSINT workflows.</details><details>-<summary>Earlier news (Mar 23�?0)</summary>+<summary>Earlier news (Mar 23??0)</summary>-- **2026-03-30** 🏗�?**CLI-Anything v0.2.0** �?HARNESS.md progressive disclosure redesign. Detailed guides extracted into `guides/` for on-demand loading. Phases 1�? now contiguous. Key Principles and Rules merged into a single authoritative section.+- **2026-03-30** ????**CLI-Anything v0.2.0** ??HARNESS.md progressive disclosure redesign. Detailed guides extracted into `guides/` for on-demand loading. Phases 1?? now contiguous. Key Principles and Rules merged into a single authoritative section.-- **2026-03-29** 📐 Blender skill docs updated �?enforce absolute render paths and correct prerequisites.+- **2026-03-29** ?? Blender skill docs updated ??enforce absolute render paths and correct prerequisites.-- **2026-03-28** 🌐 **CLIBrowser** added to CLI-Hub registry for agent-accessible browser automation.+- **2026-03-28** ?? **CLIBrowser** added to CLI-Hub registry for agent-accessible browser automation.-- **2026-03-27** 📚 Zotero SKILL.md enhanced with agent-facing constraints; REPL config and executable resolution fixes.+- **2026-03-27** ?? Zotero SKILL.md enhanced with agent-facing constraints; REPL config and executable resolution fixes.-- **2026-03-26** 📖 **Zotero CLI** harness landed for Zotero desktop (library management, collections, citations). Draw.io custom ID bugfix (#132) and registry.json syntax fix.+- **2026-03-26** ?? **Zotero CLI** harness landed for Zotero desktop (library management, collections, citations). Draw.io custom ID bugfix (#132) and registry.json syntax fix.-- **2026-03-25** 🎮 **RenderDoc CLI** merged for GPU frame capture analysis. FreeCAD updated for v1.1. Blender EEVEE engine name corrected. Zoom token permissions hardened.+- **2026-03-25** ?? **RenderDoc CLI** merged for GPU frame capture analysis. FreeCAD updated for v1.1. Blender EEVEE engine name corrected. Zoom token permissions hardened.-- **2026-03-24** 🏭 **FreeCAD CLI** added with 258 commands across 17 groups. **iTerm2** and **Teltonika RMS** harnesses added to registry.+- **2026-03-24** ?? **FreeCAD CLI** added with 258 commands across 17 groups. **iTerm2** and **Teltonika RMS** harnesses added to registry.-- **2026-03-23** 🤖 Launched **CLI-Hub meta-skill** �?agents can now discover and install CLIs autonomously. **Krita CLI** harness merged for digital painting.+- **2026-03-23** ?? Launched **CLI-Hub meta-skill** ??agents can now discover and install CLIs autonomously. **Krita CLI** harness merged for digital painting.</details><details>-<summary>Earlier news (Mar 11�?2)</summary>+<summary>Earlier news (Mar 11??2)</summary>-- **2026-03-22** 🎵 **MuseScore CLI** merged with transpose, export, and instrument management.+- **2026-03-22** ?? **MuseScore CLI** merged with transpose, export, and instrument management.-- **2026-03-21** 🔧 Infrastructure improvements �?refined test harnesses and documentation across multiple CLIs. Enhanced Windows compatibility for several backends.+- **2026-03-21** ?? Infrastructure improvements ??refined test harnesses and documentation across multiple CLIs. Enhanced Windows compatibility for several backends.-- **2026-03-20** 🌐 **Novita AI** CLI added for OpenAI-compatible API access. Registry metadata improvements for better hub discovery.+- **2026-03-20** ?? **Novita AI** CLI added for OpenAI-compatible API access. Registry metadata improvements for better hub discovery.-- **2026-03-19** 📦 Package structure refinements across harnesses. Improved SKILL.md generation with better command documentation.+- **2026-03-19** ?? Package structure refinements across harnesses. Improved SKILL.md generation with better command documentation.-- **2026-03-18** 🧪 Test coverage expansion �?additional E2E scenarios and edge case validation across multiple CLIs.+- **2026-03-18** ?? Test coverage expansion ??additional E2E scenarios and edge case validation across multiple CLIs.-- **2026-03-17** 🌐 Launched the **[CLI-Hub](https://hkuds.github.io/CLI-Anything/)** �?a central registry where you can browse, search, and install any CLI with a single `pip` command.+- **2026-03-17** ?? Launched the **[CLI-Hub](https://hkuds.github.io/CLI-Anything/)** ??a central registry where you can browse, search, and install any CLI with a single `pip` command.-- **2026-03-16** 🤖 Added **SKILL.md generation** (Phase 6.5) �?every generated CLI now ships with an AI-discoverable skill definition.+- **2026-03-16** ?? Added **SKILL.md generation** (Phase 6.5) ??every generated CLI now ships with an AI-discoverable skill definition.-- **2026-03-15** 🐾 Support for **OpenClaw** from the community! Merged Windows `cygpath` guard for cross-platform support.+- **2026-03-15** ?? Support for **OpenClaw** from the community! Merged Windows `cygpath` guard for cross-platform support.-- **2026-03-14** 🔒 Fixed a GIMP Script-Fu path injection vulnerability and added **Japanese README** translation.+- **2026-03-14** ?? Fixed a GIMP Script-Fu path injection vulnerability and added **Japanese README** translation.-- **2026-03-13** 🔌 **Qodercli** plugin officially merged as a community contribution with dedicated setup scripts.+- **2026-03-13** ?? **Qodercli** plugin officially merged as a community contribution with dedicated setup scripts.-- **2026-03-12** 📦 **Codex skill** integration landed, bringing CLI-Anything to yet another AI coding platform.+- **2026-03-12** ?? **Codex skill** integration landed, bringing CLI-Anything to yet another AI coding platform.-- **2026-03-11** 📞 **Zoom** video conferencing harness added as the 11th supported application.+- **2026-03-11** ?? **Zoom** video conferencing harness added as the 11th supported application.</details>----## 🤔 Why CLI?+## ?? Why CLI?CLI is the universal interface for both humans and AI agents:-�?**Structured & Composable** - Text commands match LLM format and chain for complex workflows+??**Structured & Composable** - Text commands match LLM format and chain for complex workflows-�?**Lightweight & Universal** - Minimal overhead, works across all systems without dependencies+??**Lightweight & Universal** - Minimal overhead, works across all systems without dependencies-�?**Self-Describing** - --help flags provide automatic documentation agents can discover+??**Self-Describing** - --help flags provide automatic documentation agents can discover-�?**Proven Success** - Claude Code runs thousands of real workflows through CLI daily+??**Proven Success** - Claude Code runs thousands of real workflows through CLI daily-�?**Agent-First Design** - Structured JSON output eliminates parsing complexity+??**Agent-First Design** - Structured JSON output eliminates parsing complexity-�?**Deterministic & Reliable** - Consistent results enable predictable agent behavior+??**Deterministic & Reliable** - Consistent results enable predictable agent behavior-## 🚀 Quick Start+## ?? Quick Start### Prerequisites@@ -163,7 +163,7 @@ CLI is the universal interface for both humans and AI agents:### Pick Your Platform<details open>-<summary><h4 id="-claude-code">�?Claude Code</h4></summary>+<summary><h4 id="-claude-code">??Claude Code</h4></summary>**Step 1: Add the Marketplace**@@ -210,27 +210,27 @@ If you see `Unknown skill: cli-anything`, focus on plugin install/load first (bo- Older builds only: `/cli-anything:cli-anything ./gimp`This runs the full pipeline:-1. 🔍 **Analyze** �?Scans source code, maps GUI actions to APIs-2. 📐 **Design** �?Architects command groups, state model, output formats-3. 🔨 **Implement** �?Builds Click CLI with REPL, JSON output, undo/redo-4. 📋 **Plan Tests** �?Creates TEST.md with unit + E2E test plans-5. 🧪 **Write Tests** �?Implements comprehensive test suite-6. 📝 **Document** �?Updates TEST.md with results-7. 📦 **Publish** �?Creates `setup.py`, installs to PATH+1. ?? **Analyze** ??Scans source code, maps GUI actions to APIs+2. ?? **Design** ??Architects command groups, state model, output formats+3. ?? **Implement** ??Builds Click CLI with REPL, JSON output, undo/redo+4. ?? **Plan Tests** ??Creates TEST.md with unit + E2E test plans+5. ?? **Write Tests** ??Implements comprehensive test suite+6. ?? **Document** ??Updates TEST.md with results+7. ?? **Publish** ??Creates `setup.py`, installs to PATH**Step 4 (Optional): Refine and Improve the CLI**After the initial build, you can iteratively refine the CLI to expand coverage and add missing capabilities:```bash-# Broad refinement �?agent analyzes gaps across all capabilities+# Broad refinement ??agent analyzes gaps across all capabilities/cli-anything:refine ./gimp-# Focused refinement �?target a specific functionality area+# Focused refinement ??target a specific functionality area/cli-anything:refine ./gimp "I want more CLIs on image batch processing and filters"```-The refine command performs gap analysis between the software's full capabilities and current CLI coverage, then implements new commands, tests, and documentation for the identified gaps. You can run it multiple times to steadily expand coverage �?each run is incremental and non-destructive.+The refine command performs gap analysis between the software's full capabilities and current CLI coverage, then implements new commands, tests, and documentation for the identified gaps. You can run it multiple times to steadily expand coverage ??each run is incremental and non-destructive.<details><summary><strong>Alternative: Manual Installation</strong></summary>@@ -253,7 +253,7 @@ cp -r CLI-Anything/cli-anything-plugin ~/.claude/plugins/cli-anything</details><details>-<summary><h4 id="-pi-coding-agent">�?Pi Coding Agent</h4></summary>+<summary><h4 id="-pi-coding-agent">??Pi Coding Agent</h4></summary>**Step 1: Install the Extension**@@ -291,10 +291,10 @@ Once the extension is loaded, the following commands are available:**Step 3 (Optional): Refine and Improve the CLI**```bash-# Broad refinement �?agent analyzes gaps across all capabilities+# Broad refinement ??agent analyzes gaps across all capabilities/cli-anything:refine ./gimp-# Focused refinement �?target a specific functionality area+# Focused refinement ??target a specific functionality area/cli-anything:refine ./gimp "batch processing and filters"```@@ -311,7 +311,7 @@ Once the extension is loaded, the following commands are available:</details><details>-<summary><h4 id="-opencode">�?OpenCode (Experimental)</h4></summary>+<summary><h4 id="-opencode">??OpenCode (Experimental)</h4></summary>**Step 1: Install the Commands**@@ -353,17 +353,17 @@ The command runs as a subtask and follows the same 7-phase methodology as Claude**Step 3 (Optional): Refine and Improve the CLI**```bash-# Broad refinement �?agent analyzes gaps across all capabilities+# Broad refinement ??agent analyzes gaps across all capabilities/cli-anything-refine ./gimp-# Focused refinement �?target a specific functionality area+# Focused refinement ??target a specific functionality area/cli-anything-refine ./gimp "batch processing and filters"```</details><details>-<summary><h4 id="-goose">�?Goose (Desktop / CLI) <sup><code>Experimental</code></sup> <sup><code>Community</code></sup></h4></summary>+<summary><h4 id="-goose">??Goose (Desktop / CLI) <sup><code>Experimental</code></sup> <sup><code>Community</code></sup></h4></summary>**Step 1: Install Goose**@@ -387,7 +387,7 @@ Once Goose is configured, start a session and use the same CLI-Anything commands<details>-<summary><h4 id="-qodercli">�?Qodercli <sup><code>Community</code></sup></h4></summary>+<summary><h4 id="-qodercli">??Qodercli <sup><code>Community</code></sup></h4></summary>**Step 1: Register the Plugin**@@ -409,7 +409,7 @@ This registers the cli-anything plugin in `~/.qoder.json`. Start a new Qodercli<details>-<summary><h4 id="-openclaw">�?OpenClaw <sup><code>Community</code></sup></h4></summary>+<summary><h4 id="-openclaw">??OpenClaw <sup><code>Community</code></sup></h4></summary>**Step 1: Install the Skill**@@ -436,7 +436,7 @@ The skill follows the same 7-phase methodology as Claude Code and OpenCode.<details>-<summary><h4 id="-codex">�?Codex <sup><code>Experimental</code></sup> <sup><code>Community</code></sup></h4></summary>+<summary><h4 id="-codex">??Codex <sup><code>Experimental</code></sup> <sup><code>Community</code></sup></h4></summary>**Step 1: Install the Skill**@@ -476,7 +476,7 @@ OpenCode commands, while keeping the generated Python harness format unchanged.<details>-<summary><h4 id="-github-copilot-cli">�?GitHub Copilot CLI <sup><code>Community</code></sup></h4></summary>+<summary><h4 id="-github-copilot-cli">??GitHub Copilot CLI <sup><code>Community</code></sup></h4></summary>**Step 1: Install the Plugin**@@ -499,14 +499,14 @@ This installs the CLI-Anything plugin to GitHub Copilot CLI. The plugin should n</details><details>-<summary><h4 id="-more-platforms-coming-soon">🔮 More Platforms (Coming Soon)</h4></summary>+<summary><h4 id="-more-platforms-coming-soon">?? More Platforms (Coming Soon)</h4></summary>CLI-Anything is designed to be platform-agnostic. Support for more AI coding agents is planned:-- **Codex** �?available via the bundled skill in `codex-skill/`-- **Cursor** �?coming soon-- **Windsurf** �?coming soon-- **Your favorite tool** �?contributions welcome! See the `opencode-commands/` directory for a reference implementation.+- **Codex** ??available via the bundled skill in `codex-skill/`+- **Cursor** ??coming soon+- **Windsurf** ??coming soon+- **Your favorite tool** ??contributions welcome! See the `opencode-commands/` directory for a reference implementation.</details>@@ -531,9 +531,9 @@ Each in-repo harness now has a canonical [`SKILL.md`](#-skillmd-generation) at `----## 🤖 Empower Your Agents with CLI-Hub+## ?? Empower Your Agents with CLI-Hub-CLI-Hub lets agents autonomously discover and install the CLIs they need �?zero human intervention required.+CLI-Hub lets agents autonomously discover and install the CLIs they need ??zero human intervention required.We published a **meta-skill** that lets any AI agent freely explore the full catalog of community CLIs and pick the right one for the task.@@ -553,7 +553,7 @@ nanobot skills install cli-anything-hubFind appropriate CLI software in CLI-Hub and complete the task: <your task here>```-The agent will browse the catalog, install whichever CLI fits the task, and use it �?all autonomously.+The agent will browse the catalog, install whichever CLI fits the task, and use it ??all autonomously.**How it works under the hood:**@@ -561,42 +561,42 @@ The agent will browse the catalog, install whichever CLI fits the task, and use2. The agent reads 20+ CLIs organized by category with one-line `pip install` commands3. The agent installs whichever CLI fits the task, then reads that CLI's own SKILL.md for detailed usage-The catalog auto-updates whenever `registry.json` changes �?new community CLIs show up automatically.+The catalog auto-updates whenever `registry.json` changes ??new community CLIs show up automatically.> **For Claude Code users:** Copy [`skills/cli-hub-meta-skill/SKILL.md`](skills/cli-hub-meta-skill/SKILL.md) into your project or skills directory for the same automatic CLI discovery.----## 💡 CLI-Anything's Vision: Building Agent-Native Software+## ?? CLI-Anything's Vision: Building Agent-Native Software-�?🌐 **Universal Access** - Every software becomes instantly agent-controllable through structured CLI.+???? **Universal Access** - Every software becomes instantly agent-controllable through structured CLI.-�?🔗 **Seamless Integration** - Agents control any application without APIs, GUI, rebuilding or complex wrappers.+???? **Seamless Integration** - Agents control any application without APIs, GUI, rebuilding or complex wrappers.-�?🚀 **Future-Ready Ecosystem** - Transform human-designed software into agent-native tools with one command.+???? **Future-Ready Ecosystem** - Transform human-designed software into agent-native tools with one command.----## 🔧 When to Use CLI-Anything+## ?? When to Use CLI-Anything| Category | How to be Agent-native | Notable Examples ||----------|----------------------|----------|-| **📂 GitHub Repositories** | Transform any open-source project into agent-controllable tools through automatic CLI generation | VSCodium, WordPress, Calibre, Zotero, Joplin, Logseq, Penpot, Super Productivity |-| **🤖 AI/ML Platforms** | Automate model training, inference pipelines, and hyperparameter tuning through structured commands | Stable Diffusion WebUI, ComfyUI, Ollama, InvokeAI, Text-generation-webui, Open WebUI, Fooocus, Kohya_ss, AnythingLLM, SillyTavern |-| **📊 Data & Analytics** | Enable programmatic data processing, visualization, and statistical analysis workflows | JupyterLab, Apache Superset, Metabase, Redash, DBeaver, KNIME, Orange, OpenSearch Dashboards, Lightdash |-| **💻 Development Tools** | Streamline code editing, building, testing, and deployment processes via command interfaces | Jenkins, Gitea, Hoppscotch, Portainer, pgAdmin, SonarQube, ArgoCD, OpenLens, Insomnia, Beekeeper Studio, **[iTerm2](https://iterm2.com)** |-| **🎨 Creative & Media** | Control content creation, editing, and rendering workflows programmatically | Blender, GIMP, OBS Studio, Audacity, Krita, Kdenlive, Shotcut, Inkscape, Darktable, LMMS, Ardour |-| **🎮 Game Development** | Manage game projects, scenes, exports, and scripting through headless engine interfaces | **[Godot Engine](https://godotengine.org)**, **[s&box](https://sbox.game)** |-| **🔬 Scientific Computing** | Automate research workflows, simulations, and complex calculations | ImageJ, FreeCAD, QGIS, ParaView, Gephi, LibreCAD, Stellarium, KiCad, JASP, Jamovi |-| **🏢 Enterprise & Office** | Convert business applications and productivity tools into agent-accessible systems | NextCloud, GitLab, Grafana, Mattermost, LibreOffice, AppFlowy, NocoDB, Odoo (Community), Plane, ERPNext |-| **📞 Communication & Collaboration** | Automate meeting scheduling, participant management, recording retrieval, and reporting through structured CLI | Zoom, Jitsi Meet, BigBlueButton, Mattermost |-| **📐 Diagramming & Visualization** | Create and manipulate diagrams, flowcharts, architecture diagrams, and visual documentation programmatically | Draw.io (diagrams.net), Mermaid, PlantUML, Excalidraw, yEd |-| **🌐 Network & Infrastructure** | Manage network services, DNS, ad-blocking, and infrastructure through structured CLI commands | AdGuardHome |-| **🧪 Testing & Mocking** | Control HTTP mock servers, manage test stubs, record and replay API traffic for integration testing | **[WireMock](https://wiremock.org)** |-| **🔬 Graphics & GPU Debugging** | Analyze GPU frame captures, inspect pipeline state, export shaders, and diff rendering state | RenderDoc |-| **🎬 Video & Subtitles** | Transcribe speech, translate subtitles, burn styled captions into video �?full captioning pipeline | VideoCaptioner |-| **🔍 AI-Native Search** | Neural and deep web search with structured content retrieval through embedding-based APIs | [Exa](https://exa.ai) |-| **�?AI Content Generation** | Generate professional deliverables (slides, docs, diagrams, websites, research reports) through AI-powered cloud APIs | [AnyGen](https://www.anygen.io), Gamma, Beautiful.ai, Tome |+| **?? GitHub Repositories** | Transform any open-source project into agent-controllable tools through automatic CLI generation | VSCodium, WordPress, Calibre, Zotero, Joplin, Logseq, Penpot, Super Productivity |+| **?? AI/ML Platforms** | Automate model training, inference pipelines, and hyperparameter tuning through structured commands | Stable Diffusion WebUI, ComfyUI, Ollama, InvokeAI, Text-generation-webui, Open WebUI, Fooocus, Kohya_ss, AnythingLLM, SillyTavern |+| **?? Data & Analytics** | Enable programmatic data processing, visualization, and statistical analysis workflows | JupyterLab, Apache Superset, Metabase, Redash, DBeaver, KNIME, Orange, OpenSearch Dashboards, Lightdash |+| **?? Development Tools** | Streamline code editing, building, testing, and deployment processes via command interfaces | Jenkins, Gitea, Hoppscotch, Portainer, pgAdmin, SonarQube, ArgoCD, OpenLens, Insomnia, Beekeeper Studio, **[iTerm2](https://iterm2.com)** |+| **?? Creative & Media** | Control content creation, editing, and rendering workflows programmatically | Blender, GIMP, OBS Studio, Audacity, Krita, Kdenlive, Shotcut, Inkscape, Darktable, LMMS, Ardour |+| **?? Game Development** | Manage game projects, scenes, exports, and scripting through headless engine interfaces | **[Godot Engine](https://godotengine.org)**, **[s&box](https://sbox.game)** |+| **?? Scientific Computing** | Automate research workflows, simulations, and complex calculations | ImageJ, FreeCAD, QGIS, ParaView, Gephi, LibreCAD, Stellarium, KiCad, JASP, Jamovi |+| **?? Enterprise & Office** | Convert business applications and productivity tools into agent-accessible systems | NextCloud, GitLab, Grafana, Mattermost, LibreOffice, AppFlowy, NocoDB, Odoo (Community), Plane, ERPNext |+| **?? Communication & Collaboration** | Automate meeting scheduling, participant management, recording retrieval, and reporting through structured CLI | Zoom, Jitsi Meet, BigBlueButton, Mattermost |+| **?? Diagramming & Visualization** | Create and manipulate diagrams, flowcharts, architecture diagrams, and visual documentation programmatically | Draw.io (diagrams.net), Mermaid, PlantUML, Excalidraw, yEd |+| **?? Network & Infrastructure** | Manage network services, DNS, ad-blocking, and infrastructure through structured CLI commands | AdGuardHome |+| **?? Testing & Mocking** | Control HTTP mock servers, manage test stubs, record and replay API traffic for integration testing | **[WireMock](https://wiremock.org)** |+| **?? Graphics & GPU Debugging** | Analyze GPU frame captures, inspect pipeline state, export shaders, and diff rendering state | RenderDoc |+| **?? Video & Subtitles** | Transcribe speech, translate subtitles, burn styled captions into video ??full captioning pipeline | VideoCaptioner |+| **?? AI-Native Search** | Neural and deep web search with structured content retrieval through embedding-based APIs | [Exa](https://exa.ai) |+| **??AI Content Generation** | Generate professional deliverables (slides, docs, diagrams, websites, research reports) through AI-powered cloud APIs | [AnyGen](https://www.anygen.io), Gamma, Beautiful.ai, Tome |---@@ -609,37 +609,37 @@ AI agents are great at reasoning but terrible at using real professional softwar| **Current Pain Point** | **CLI-Anything's Fix** ||----------|----------------------|-| 🤖 "AI can't use real tools" | Direct integration with actual software backends (Blender, LibreOffice, FFmpeg) �?full professional capabilities, zero compromises |-| 💸 "UI automation breaks constantly" | No screenshots, no clicking, no RPA fragility. Pure command-line reliability with structured interfaces |-| 📊 "Agents need structured data" | Built-in JSON output for seamless agent consumption + human-readable formats for debugging |-| 🔧 "Custom integrations are expensive" | One Claude plugin auto-generates CLIs for ANY codebase through proven 7-phase pipeline |-| �?"Prototype vs Production gap" | 2,392+ tests with real software validation. Battle-tested across 18 major applications |+| ?? "AI can't use real tools" | Direct integration with actual software backends (Blender, LibreOffice, FFmpeg) ??full professional capabilities, zero compromises |+| ?? "UI automation breaks constantly" | No screenshots, no clicking, no RPA fragility. Pure command-line reliability with structured interfaces |+| ?? "Agents need structured data" | Built-in JSON output for seamless agent consumption + human-readable formats for debugging |+| ?? "Custom integrations are expensive" | One Claude plugin auto-generates CLIs for ANY codebase through proven 7-phase pipeline |+| ??"Prototype vs Production gap" | 2,392+ tests with real software validation. Battle-tested across 18 major applications |----## 🎯 What Can You Do with CLI-Anything?+## ?? What Can You Do with CLI-Anything?<table><tr><td width="33%">-### 🛠�?Let Agents Take Your Workflows+### ????Let Agents Take Your Workflows-Professional or everyday �?just throw the codebase at `/cli-anything`. GIMP, Blender, Shotcut for creative work. LibreOffice, OBS Studio for daily tasks. Don't have the source? Find an open-source alternative and throw *that* in. You'll instantly get a full CLI your agents can use.+Professional or everyday ??just throw the codebase at `/cli-anything`. GIMP, Blender, Shotcut for creative work. LibreOffice, OBS Studio for daily tasks. Don't have the source? Find an open-source alternative and throw *that* in. You'll instantly get a full CLI your agents can use.</td><td width="33%">-### 🔗 Unify Scattered APIs into One CLI+### ?? Unify Scattered APIs into One CLI-Tired of juggling fragmented web service APIs? Feed the docs or SDK manuscripts to `/cli-anything` and your agents get a **powerful, stateful CLI** that wraps those individual endpoints into coherent command groups. One tool instead of dozens of raw API calls �?stronger capabilities while saving tokens.+Tired of juggling fragmented web service APIs? Feed the docs or SDK manuscripts to `/cli-anything` and your agents get a **powerful, stateful CLI** that wraps those individual endpoints into coherent command groups. One tool instead of dozens of raw API calls ??stronger capabilities while saving tokens.</td><td width="33%">-### 🚀 Replace or Supercharge GUI Agents+### ?? Replace or Supercharge GUI Agents-CLI-Anything can flat-out **replace GUI-based agent approaches** �?no more screenshots, no brittle pixel-clicking. But here's the fun part: once you `/cli-anything` a GUI software, you can **synthesize agent tasks, evaluators, and benchmarks** entirely via code and terminal �?fully automated, iteratively refinable, massively more efficient.+CLI-Anything can flat-out **replace GUI-based agent approaches** ??no more screenshots, no brittle pixel-clicking. But here's the fun part: once you `/cli-anything` a GUI software, you can **synthesize agent tasks, evaluators, and benchmarks** entirely via code and terminal ??fully automated, iteratively refinable, massively more efficient.</td></tr>@@ -647,19 +647,19 @@ CLI-Anything can flat-out **replace GUI-based agent approaches** �?no more scr----## �?⚙️ How CLI-Anything Works+## ???? How CLI-Anything Works<table><tr><td width="50%">-### 🏗�?Fully Automated 7-Phase Pipeline-From codebase analysis to PyPI publishing �?the plugin handles architecture design, implementation, test planning, test writing, and documentation completely automatically.+### ????Fully Automated 7-Phase Pipeline+From codebase analysis to PyPI publishing ??the plugin handles architecture design, implementation, test planning, test writing, and documentation completely automatically.</td><td width="50%">-### 🎯 Authentic Software Integration+### ?? Authentic Software IntegrationDirect calls to real applications for actual rendering. LibreOffice generates PDFs, Blender renders 3D scenes, Audacity processes audio via sox. **Zero compromises**, **Zero toy implementations**.</td>@@ -667,13 +667,13 @@ Direct calls to real applications for actual rendering. LibreOffice generates PD<tr><td width="50%">-### 🔁 Smart Session Management+### ?? Smart Session ManagementPersistent project state with undo/redo capabilities, plus unified REPL interface (ReplSkin) that delivers consistent interactive experience across all CLIs.</td><td width="50%">-### 📦 Zero-Config Installation+### ?? Zero-Config InstallationSimple pip install -e . puts cli-anything-<software> directly on PATH. Agents discover tools via standard which commands. No setup, no wrappers.</td>@@ -681,20 +681,20 @@ Simple pip install -e . puts cli-anything-<software> directly on PATH. Agents di<tr><td width="50%">-### 🧪 Production-Grade Testing+### ?? Production-Grade TestingMulti-layered validation: unit tests with synthetic data, end-to-end tests with real files and software, plus CLI subprocess verification of installed commands.</td><td width="50%">-### 🐍 Clean Package Architecture-All CLIs organized under cli_anything.* namespace �?conflict-free, pip-installable, with consistent naming: cli-anything-gimp, cli-anything-blender, etc.+### ?? Clean Package Architecture+All CLIs organized under cli_anything.* namespace ??conflict-free, pip-installable, with consistent naming: cli-anything-gimp, cli-anything-blender, etc.</td></tr></table>-### 🤖 SKILL.md Generation+### ?? SKILL.md GenerationEach generated CLI now has a canonical `SKILL.md` at `skills/cli-anything-<software>/SKILL.md`. This makes the current monorepo directly consumable by `npx skills`, while a packaged compatibility copy at `cli_anything/<software>/skills/SKILL.md` preserves installed-harness behavior.@@ -708,9 +708,9 @@ SKILL.md files are auto-generated during Phase 6.5 of the pipeline using `skill_----## 🎬 Real-World Demos+## ?? Real-World Demos-AI agents using generated CLIs to produce complete, useful artifacts �?no GUI needed.+AI agents using generated CLIs to produce complete, useful artifacts ??no GUI needed.### FreeCAD — Curiosity Rover via Preview, Live Preview, and Trajectory@@ -744,7 +744,7 @@ An agent uses the Blender harness to grow a hard-surface orbital relay drone und> **Harness:** `cli-anything-drawio` | **Time:** ~4 min | **Artifact:** `.drawio` + `.png`-An agent creates a full HTTPS connection lifecycle diagram from scratch �?TCP three-way handshake, TLS negotiation, encrypted data exchange, and TCP four-way termination �?entirely through CLI commands.+An agent creates a full HTTPS connection lifecycle diagram from scratch ??TCP three-way handshake, TLS negotiation, encrypted data exchange, and TCP four-way termination ??entirely through CLI commands.<p align="center"><img src="assets/demos/drawio-demo.gif" alt="Draw.io CLI demo: building an HTTPS handshake diagram" width="720" />@@ -763,7 +763,7 @@ An agent creates a full HTTPS connection lifecycle diagram from scratch �?TCP> **Harness:** `cli-anything-slay-the-spire-ii` | **Artifact:** Automated gameplay session-An agent plays through a Slay the Spire II run using the CLI harness �?reading game state, selecting cards, choosing paths, and making strategic decisions in real-time.+An agent plays through a Slay the Spire II run using the CLI harness ??reading game state, selecting cards, choosing paths, and making strategic decisions in real-time.<p align="center"><img src="assets/demos/slay-the-spire-ii-gameplay.gif" alt="Slay the Spire II CLI gameplay demo" width="720" />@@ -794,19 +794,19 @@ An agent uses the VideoCaptioner CLI to automatically generate and overlay style----## 🎬 Demonstrations+## ?? Demonstrations-### 🎯 General-Purpose-CLI-Anything works on any software with a codebase �?no domain restrictions or architectural limitations.+### ?? General-Purpose+CLI-Anything works on any software with a codebase ??no domain restrictions or architectural limitations.-### 🏭 Professional-Grade Testing+### ?? Professional-Grade TestingTested across 18 diverse, complex applications spanning creative, productivity, communication, diagramming, AI image generation, AI content generation, network ad blocking, local LLM inference, native debugging, and graphics profiling domains previously inaccessible to AI agents.-### 🎨 Diverse Domain Coverage+### ?? Diverse Domain CoverageFrom creative workflows (image editing, 3D modeling, vector graphics) to production tools (audio, office, live streaming, video editing).-### �?Full CLI Generation-Each application received complete, production-ready CLI interfaces �?not demos, but comprehensive tool access preserving full capabilities.+### ??Full CLI Generation+Each application received complete, production-ready CLI interfaces ??not demos, but comprehensive tool access preserving full capabilities.<table><tr>@@ -817,421 +817,421 @@ Each application received complete, production-ready CLI interfaces �?not demo<th align="center">Tests</th></tr><tr>-<td align="center"><strong>🎨 GIMP</strong></td>+<td align="center"><strong>?? GIMP</strong></td><td>Image Editing</td><td><code>cli-anything-gimp</code></td><td>Pillow + GEGL/Script-Fu</td>-<td align="center">�?107</td>+<td align="center">??107</td></tr><tr>-<td align="center"><strong>🧊 Blender</strong></td>+<td align="center"><strong>?? Blender</strong></td><td>3D Modeling & Rendering</td><td><code>cli-anything-blender</code></td><td>bpy (Python scripting)</td>-<td align="center">�?208</td>+<td align="center">??208</td></tr><tr>-<td align="center"><strong>✏️ Inkscape</strong></td>+<td align="center"><strong>?? Inkscape</strong></td><td>Vector Graphics</td><td><code>cli-anything-inkscape</code></td><td>Direct SVG/XML manipulation</td>-<td align="center">�?202</td>+<td align="center">??202</td></tr><tr>-<td align="center"><strong>🎵 Audacity</strong></td>+<td align="center"><strong>?? Audacity</strong></td><td>Audio Production</td><td><code>cli-anything-audacity</code></td><td>Python wave + sox</td>-<td align="center">�?161</td>+<td align="center">??161</td></tr><tr>-<td align="center"><strong>🌐 Browser</strong></td>+<td align="center"><strong>?? Browser</strong></td><td>Browser Automation</td><td><code>cli-anything-browser</code></td><td>DOMShell MCP + Accessibility Tree</td>-<td align="center">�?<a href="browser/agent-harness/">New</a></td>+<td align="center">??<a href="browser/agent-harness/">New</a></td></tr><tr>-<td align="center"><strong>📄 LibreOffice</strong></td>+<td align="center"><strong>?? LibreOffice</strong></td><td>Office Suite (Writer, Calc, Impress)</td><td><code>cli-anything-libreoffice</code></td><td>ODF generation + headless LO</td>-<td align="center">�?158</td>+<td align="center">??158</td></tr><tr>-<td align="center"><strong>�?<a href="n8n/agent-harness/">n8n</a></strong></td>+<td align="center"><strong>??<a href="n8n/agent-harness/">n8n</a></strong></td><td>Workflow Automation</td><td><code>cli-anything-n8n</code></td><td>n8n REST API v1.1.1</td>-<td align="center">�?<a href="n8n/agent-harness/">55+ cmds</a></td>+<td align="center">??<a href="n8n/agent-harness/">55+ cmds</a></td></tr><tr>-<td align="center"><strong>📧 <a href="mailchimp/agent-harness/">Mailchimp</a></strong></td>+<td align="center"><strong>?? <a href="mailchimp/agent-harness/">Mailchimp</a></strong></td><td>Email Marketing & Automation</td><td><code>cli-anything-mailchimp</code></td><td>Mailchimp Marketing API v3.0</td>-<td align="center">�?<a href="mailchimp/agent-harness/">303 cmds</a></td>+<td align="center">??<a href="mailchimp/agent-harness/">303 cmds</a></td></tr><tr>-<td align="center"><strong>📚 <a href="zotero/agent-harness/">Zotero</a></strong></td>+<td align="center"><strong>?? <a href="zotero/agent-harness/">Zotero</a></strong></td><td>Reference Management</td><td><code>cli-anything-zotero</code></td><td>Local SQLite + connector + Local API</td>-<td align="center">�?<a href="zotero/agent-harness/">New</a></td>+<td align="center">??<a href="zotero/agent-harness/">New</a></td></tr><tr>-<td align="center"><strong>📓 <a href="joplin/agent-harness/">Joplin</a></strong></td>+<td align="center"><strong>?? <a href="joplin/agent-harness/">Joplin</a></strong></td><td>Note-taking & To-dos</td><td><code>cli-anything-joplin</code></td><td>Joplin terminal CLI subprocess</td>-<td align="center">✅ 112</td>+<td align="center">? 112</td></tr><tr>-<td align="center"><strong>📝 <a href="mubu/agent-harness/">Mubu</a></strong></td>+<td align="center"><strong>?? <a href="mubu/agent-harness/">Mubu</a></strong></td><td>Knowledge Management & Outlining</td><td><code>cli-anything-mubu</code></td><td>Local Mubu data + sync logs</td>-<td align="center">�?96</td>+<td align="center">??96</td></tr><tr>-<td align="center"><strong>📹 OBS Studio</strong></td>+<td align="center"><strong>?? OBS Studio</strong></td><td>Live Streaming & Recording</td><td><code>cli-anything-obs-studio</code></td><td>JSON scene + obs-websocket</td>-<td align="center">�?153</td>+<td align="center">??153</td></tr><tr>-<td align="center"><strong>📱 <a href="nslogger/agent-harness/">NSLogger</a></strong></td>+<td align="center"><strong>?? <a href="nslogger/agent-harness/">NSLogger</a></strong></td><td>iOS/macOS Log Capture</td><td><code>cli-anything-nslogger</code></td><td>NSLogger wire protocol + native macOS Bonjour</td>-<td align="center">�?139</td>+<td align="center">??139</td></tr><tr>-<td align="center"><strong>🎞�?Kdenlive</strong></td>+<td align="center"><strong>????Kdenlive</strong></td><td>Video Editing</td><td><code>cli-anything-kdenlive</code></td><td>MLT XML + melt renderer</td>-<td align="center">�?155</td>+<td align="center">??155</td></tr><tr>-<td align="center"><strong>🎬 Shotcut</strong></td>+<td align="center"><strong>?? Shotcut</strong></td><td>Video Editing</td><td><code>cli-anything-shotcut</code></td><td>Direct MLT XML + melt</td>-<td align="center">�?154</td>+<td align="center">??154</td></tr><tr>-<td align="center"><strong>🎬 <a href="openscreen/agent-harness/">Openscreen</a></strong></td>+<td align="center"><strong>?? <a href="openscreen/agent-harness/">Openscreen</a></strong></td><td>Screen Recording Editor</td><td><code>cli-anything-openscreen</code></td><td>ffmpeg backend</td>-<td align="center">�?101</td>+<td align="center">??101</td></tr><tr>-<td align="center"><strong>📞 Zoom</strong></td>+<td align="center"><strong>?? Zoom</strong></td><td>Video Conferencing</td><td><code>cli-anything-zoom</code></td><td>Zoom REST API (OAuth2)</td>-<td align="center">�?22</td>+<td align="center">??22</td></tr><tr>-<td align="center"><strong>🎵 MuseScore</strong></td>+<td align="center"><strong>?? MuseScore</strong></td><td>Music Notation</td><td><code>cli-anything-musescore</code></td><td>mscore CLI (MSCX/MusicXML)</td>-<td align="center">�?56</td>+<td align="center">??56</td></tr><tr>-<td align="center"><strong>📐 Draw.io</strong></td>+<td align="center"><strong>?? Draw.io</strong></td><td>Diagramming</td><td><code>cli-anything-drawio</code></td><td>mxGraph XML + draw.io CLI</td>-<td align="center">�?138</td>+<td align="center">??138</td></tr><tr>-<td align="center"><strong>⛓️ ETH2 QuickStart</strong></td>+<td align="center"><strong>?? ETH2 QuickStart</strong></td><td>DevOps / Ethereum</td><td><code>cli-anything-eth2-quickstart</code></td><td>eth2-quickstart shell automation + JSON health checks</td>-<td align="center">�?18</td>+<td align="center">??18</td></tr><tr>-<td align="center"><strong>🧜 Mermaid Live Editor</strong></td>+<td align="center"><strong>?? Mermaid Live Editor</strong></td><td>Diagramming</td><td><code>cli-anything-mermaid</code></td><td>Mermaid state + mermaid.ink renderer</td>-<td align="center">�?10</td>+<td align="center">??10</td></tr><tr>-<td align="center"><strong>�?AnyGen</strong></td>+<td align="center"><strong>??AnyGen</strong></td><td>AI Content Generation</td><td><code>cli-anything-anygen</code></td><td>AnyGen REST API (anygen.io)</td>-<td align="center">�?50</td>+<td align="center">??50</td></tr><tr>-<td align="center"><strong>🧠 NotebookLM</strong></td>+<td align="center"><strong>?? NotebookLM</strong></td><td>AI Research Assistant</td><td><code>cli-anything-notebooklm</code></td><td>NotebookLM CLI wrapper (experimental)</td>-<td align="center">�?21</td>+<td align="center">??21</td></tr><tr>-<td align="center"><strong>🧩 <a href="dify-workflow/agent-harness/">Dify Workflow</a></strong></td>+<td align="center"><strong>?? <a href="dify-workflow/agent-harness/">Dify Workflow</a></strong></td><td>Dify DSL Editing</td><td><code>cli-anything-dify-workflow</code></td><td>Wrapper around the open-source dify-workflow CLI</td>-<td align="center">�?11</td>+<td align="center">??11</td></tr><tr>-<td align="center"><strong>🖼�?ComfyUI</strong></td>+<td align="center"><strong>????ComfyUI</strong></td><td>AI Image Generation</td><td><code>cli-anything-comfyui</code></td><td>ComfyUI REST API</td>-<td align="center">�?70</td>+<td align="center">??70</td></tr><tr>-<td align="center"><strong>🛡�?AdGuard Home</strong></td>+<td align="center"><strong>????AdGuard Home</strong></td><td>Network-wide Ad Blocking</td><td><code>cli-anything-adguardhome</code></td><td>AdGuard Home REST API</td>-<td align="center">�?36</td>+<td align="center">??36</td></tr><tr>-<td align="center"><strong>🦙 Ollama</strong></td>+<td align="center"><strong>?? Ollama</strong></td><td>Local LLM Inference</td><td><code>cli-anything-ollama</code></td><td>Ollama REST API</td>-<td align="center">�?98</td>+<td align="center">??98</td></tr><tr>-<td align="center"><strong>🧬 <a href="unimol_tools/agent-harness/">Uni-Mol Tools</a></strong></td>+<td align="center"><strong>?? <a href="unimol_tools/agent-harness/">Uni-Mol Tools</a></strong></td><td>Molecular Property Prediction (AI4S)</td><td><code>cli-anything-unimol-tools</code></td><td>Uni-Mol molecular ML backend</td>-<td align="center">�?67</td>+<td align="center">??67</td></tr><tr>-<td align="center"><strong>🎬 <a href="videocaptioner/agent-harness/">VideoCaptioner</a></strong></td>+<td align="center"><strong>?? <a href="videocaptioner/agent-harness/">VideoCaptioner</a></strong></td><td>AI Video Captioning</td><td><code>cli-anything-videocaptioner</code></td><td>videocaptioner CLI (PyPI)</td>-<td align="center">�?26</td>+<td align="center">??26</td></tr><tr>-<td align="center"><strong>🎨 Sketch</strong></td>+<td align="center"><strong>?? Sketch</strong></td><td>UI Design</td><td><code>sketch-cli</code></td><td>sketch-constructor (Node.js)</td>-<td align="center">�?19</td>+<td align="center">??19</td></tr><tr>-<td align="center"><strong>🎮 Godot Engine</strong></td>+<td align="center"><strong>?? Godot Engine</strong></td><td>Game Development</td><td><code>cli-anything-godot</code></td><td>Godot 4.x headless subprocess</td>-<td align="center">�?24</td>+<td align="center">??24</td></tr><tr>-<td align="center"><strong>📦 <a href="sbox/agent-harness/">s&box</a></strong></td>+<td align="center"><strong>?? <a href="sbox/agent-harness/">s&box</a></strong></td><td>Game Development</td><td><code>cli-anything-sbox</code></td><td>Source 2 game engine - direct file I/O on .scene/.prefab/.vmat/.vsnd JSON</td>-<td align="center">�?244</td>+<td align="center">??244</td></tr><tr>-<td align="center"><strong>🐞 <a href="lldb/agent-harness/">LLDB</a></strong></td>+<td align="center"><strong>?? <a href="lldb/agent-harness/">LLDB</a></strong></td><td>Native Debugging</td><td><code>cli-anything-lldb</code></td><td>LLDB Python API</td>-<td align="center">�?27</td>+<td align="center">??27</td></tr><tr>-<td align="center"><strong>🟩 <a href="nsight-graphics/agent-harness/">Nsight Graphics CLI</a></strong></td>+<td align="center"><strong>?? <a href="nsight-graphics/agent-harness/">Nsight Graphics CLI</a></strong></td><td>GPU Debugging & Profiling</td><td><code>cli-anything-nsight-graphics</code></td><td>Official ngfx / ngfx-capture orchestration + GPU Trace summary + replay analysis</td>-<td align="center">�?51</td>+<td align="center">??51</td></tr><tr>-<td align="center"><strong>🔍 <a href="exa/agent-harness/">Exa</a></strong></td>+<td align="center"><strong>?? <a href="exa/agent-harness/">Exa</a></strong></td><td>AI-Native Web Search</td><td><code>cli-anything-exa</code></td><td>exa-py SDK</td>-<td align="center">�?40</td>+<td align="center">??40</td></tr><tr>-<td align="center"><strong>📈 <a href="unrealinsights/agent-harness/">Unreal Insights</a></strong></td>+<td align="center"><strong>?? <a href="unrealinsights/agent-harness/">Unreal Insights</a></strong></td><td>Performance Profiling</td><td><code>cli-anything-unrealinsights</code></td><td>Background trace sessions + engine-matched UnrealInsights build + headless export</td>-<td align="center">�?50</td>+<td align="center">??50</td></tr><tr>-<td align="center"><strong>☁️ <a href="cloudanalyzer/agent-harness/">CloudAnalyzer</a></strong></td>+<td align="center"><strong>?? <a href="cloudanalyzer/agent-harness/">CloudAnalyzer</a></strong></td><td>Point cloud / trajectory QA</td><td><code>cli-anything-cloudanalyzer</code></td><td>CloudAnalyzer (Python API)</td>-<td align="center">�?14</td>+<td align="center">??14</td></tr><tr>-<td align="center"><strong>🗺�?<a href="QGIS/agent-harness/">QGIS</a></strong></td>+<td align="center"><strong>????<a href="QGIS/agent-harness/">QGIS</a></strong></td><td>Geospatial Analysis & Mapping</td><td><code>cli-anything-qgis</code></td><td>PyQGIS + qgis_process</td>-<td align="center">�?22</td>+<td align="center">??22</td></tr><tr><td align="center" colspan="4"><strong>Total</strong></td>-<td align="center"><strong>✅ 2,392</strong></td>+<td align="center"><strong>? 2,392</strong></td></tr></table>-> **100% pass rate** across all 2,392 tests �?1,682 unit tests + 579 end-to-end tests + 19 Node.js tests.+> **100% pass rate** across all 2,392 tests ??1,682 unit tests + 579 end-to-end tests + 19 Node.js tests.----## 📊 Test Results+## ?? Test ResultsEach CLI harness undergoes rigorous multi-layered testing to ensure production reliability:| Layer | What it tests | Example ||-------|---------------|---------|-| **Unit tests** | Every core function in isolation with synthetic data | `test_core.py` �?project creation, layer ops, filter params |+| **Unit tests** | Every core function in isolation with synthetic data | `test_core.py` ??project creation, layer ops, filter params || **E2E tests (native)** | Project file generation pipeline | Valid ODF ZIP structure, correct MLT XML, SVG well-formedness |-| **E2E tests (true backend)** | Real software invocation + output verification | LibreOffice �?PDF with `%PDF-` magic bytes, Blender �?rendered PNG |-| **CLI subprocess tests** | Installed command via `subprocess.run` | `cli-anything-gimp --json project new` �?valid JSON output |+| **E2E tests (true backend)** | Real software invocation + output verification | LibreOffice ??PDF with `%PDF-` magic bytes, Blender ??rendered PNG |+| **CLI subprocess tests** | Installed command via `subprocess.run` | `cli-anything-gimp --json project new` ??valid JSON output |```================================ Test Summary ================================-gimp 107 passed �? (64 unit + 43 e2e)-blender 208 passed �? (150 unit + 58 e2e)-inkscape 202 passed �? (148 unit + 54 e2e)-audacity 161 passed �? (107 unit + 54 e2e)-libreoffice 158 passed �? (89 unit + 69 e2e)-mubu 96 passed �? (85 unit + 11 e2e)-obs-studio 153 passed �? (116 unit + 37 e2e)-nslogger 139 passed �? (97 unit + 42 e2e)-kdenlive 155 passed �? (111 unit + 44 e2e)-shotcut 154 passed �? (110 unit + 44 e2e)-zoom 22 passed �? (22 unit + 0 e2e)-drawio 138 passed �? (116 unit + 22 e2e)-eth2-quickstart 18 passed �? (18 unit + 3 e2e skipped)-mermaid 10 passed �? (5 unit + 5 e2e)-anygen 50 passed �? (40 unit + 10 e2e)-notebooklm 21 passed �? (21 unit + 0 e2e)-comfyui 70 passed �? (60 unit + 10 e2e)-adguardhome 36 passed �? (24 unit + 12 e2e)-ollama 98 passed �? (87 unit + 11 e2e)-sketch 19 passed �? (19 jest, Node.js)-renderdoc 59 passed �? (45 unit + 14 e2e)-cloudcompare 88 passed �? (49 unit + 39 e2e)-openscreen 101 passed �? (78 unit + 23 e2e)-lldb 27 passed �? (23 unit + 4 e2e)-nsight-graphics 51 passed �? (46 unit/CLI + 5 local e2e)-unrealinsights 50 passed �? (49 unit + 1 e2e, 9 backend-gated e2e skipped)-cloudanalyzer 14 passed �? (7 unit + 7 e2e)-joplin 112 passed ✅ (85 unit + 27 e2e, 2 skipped on Windows)-──────────────────────────────────────────────────────────────────────────────-TOTAL 2,392 passed �? 100% pass rate+gimp 107 passed ?? (64 unit + 43 e2e)+blender 208 passed ?? (150 unit + 58 e2e)+inkscape 202 passed ?? (148 unit + 54 e2e)+audacity 161 passed ?? (107 unit + 54 e2e)+libreoffice 158 passed ?? (89 unit + 69 e2e)+mubu 96 passed ?? (85 unit + 11 e2e)+obs-studio 153 passed ?? (116 unit + 37 e2e)+nslogger 139 passed ?? (97 unit + 42 e2e)+kdenlive 155 passed ?? (111 unit + 44 e2e)+shotcut 154 passed ?? (110 unit + 44 e2e)+zoom 22 passed ?? (22 unit + 0 e2e)+drawio 138 passed ?? (116 unit + 22 e2e)+eth2-quickstart 18 passed ?? (18 unit + 3 e2e skipped)+mermaid 10 passed ?? (5 unit + 5 e2e)+anygen 50 passed ?? (40 unit + 10 e2e)+notebooklm 21 passed ?? (21 unit + 0 e2e)+comfyui 70 passed ?? (60 unit + 10 e2e)+adguardhome 36 passed ?? (24 unit + 12 e2e)+ollama 98 passed ?? (87 unit + 11 e2e)+sketch 19 passed ?? (19 jest, Node.js)+renderdoc 59 passed ?? (45 unit + 14 e2e)+cloudcompare 88 passed ?? (49 unit + 39 e2e)+openscreen 101 passed ?? (78 unit + 23 e2e)+lldb 27 passed ?? (23 unit + 4 e2e)+nsight-graphics 51 passed ?? (46 unit/CLI + 5 local e2e)+unrealinsights 50 passed ?? (49 unit + 1 e2e, 9 backend-gated e2e skipped)+cloudanalyzer 14 passed ?? (7 unit + 7 e2e)+joplin 112 passed ? (91 unit + 27 e2e, 1 skipped on Windows)+������������������������������������������������������������������������������������������������������������������������������������������������������������+TOTAL 2,392 passed ?? 100% pass rate```----## 🏗�?CLI-Anything's Architecture+## ????CLI-Anything's Architecture<p align="center"><img src="assets/architecture.png" alt="CLI-Anything Architecture" width="750"></p>-### 🎯 Core Design Principles+### ?? Core Design Principles-1. **Authentic Software Integration** �?The CLI generates valid project files (ODF, MLT XML, SVG) and delegates to real applications for rendering. **We build structured interfaces TO software, not replacements**.+1. **Authentic Software Integration** ??The CLI generates valid project files (ODF, MLT XML, SVG) and delegates to real applications for rendering. **We build structured interfaces TO software, not replacements**.-2. **Flexible Interaction Models** �?Every CLI operates in dual modes: stateful REPL for interactive agent sessions + subcommand interface for scripting/pipelines. **Run bare command �?enter REPL mode**.+2. **Flexible Interaction Models** ??Every CLI operates in dual modes: stateful REPL for interactive agent sessions + subcommand interface for scripting/pipelines. **Run bare command ??enter REPL mode**.-3. **Consistent User Experience** �?All generated CLIs share unified REPL interface (repl_skin.py) with branded banners, styled prompts, command history, progress indicators, and standardized formatting.+3. **Consistent User Experience** ??All generated CLIs share unified REPL interface (repl_skin.py) with branded banners, styled prompts, command history, progress indicators, and standardized formatting.-4. **Agent-Native Design** �?Built-in --json flag on every command delivers structured data for machine consumption, while human-readable tables serve interactive use. **Agents discover capabilities via standard --help and which commands**.+4. **Agent-Native Design** ??Built-in --json flag on every command delivers structured data for machine consumption, while human-readable tables serve interactive use. **Agents discover capabilities via standard --help and which commands**.-5. **Zero Compromise Dependencies** �?Real software is a hard requirement �?no fallbacks, no graceful degradation. **Tests fail (not skip) when backends are missing, ensuring authentic functionality**.+5. **Zero Compromise Dependencies** ??Real software is a hard requirement ??no fallbacks, no graceful degradation. **Tests fail (not skip) when backends are missing, ensuring authentic functionality**.----## 📂 Project Structure+## ?? Project Structure```cli-anything/-├── 📄 README.md # You are here-├── 📁 assets/ # Images and media-�? ├── icon.png # Project icon-�? └── teaser.png # Teaser figure-�?-├── 🔌 cli-anything-plugin/ # The Claude Code plugin-�? ├── HARNESS.md # Methodology SOP (source of truth)-�? ├── README.md # Plugin documentation-�? ├── QUICKSTART.md # 5-minute getting started-�? ├── PUBLISHING.md # Distribution guide-�? ├── repl_skin.py # Unified REPL interface-�? ├── commands/ # Plugin command definitions-�? �? ├── cli-anything.md # Main build command-�? �? ├── refine.md # Expand existing harness coverage-�? �? ├── test.md # Test runner-�? �? └── validate.md # Standards validation-�? └── scripts/-�? └── setup-cli-anything.sh # Setup script-�?-├── 🤖 codex-skill/ # Codex skill entry point-├── 🎨 gimp/agent-harness/ # GIMP CLI (107 tests)-├── 🧊 blender/agent-harness/ # Blender CLI (208 tests)-├── ✏️ inkscape/agent-harness/ # Inkscape CLI (202 tests)-├── 🎵 audacity/agent-harness/ # Audacity CLI (161 tests)-├── 🌐 browser/agent-harness/ # Browser CLI (DOMShell MCP, new)-├── 📄 libreoffice/agent-harness/ # LibreOffice CLI (158 tests)-├── 📧 mailchimp/agent-harness/ # Mailchimp Marketing API CLI (303 commands, 36 unit tests)-├── 📚 zotero/agent-harness/ # Zotero CLI (new, write import support)+������ ?? README.md # You are here+������ ?? assets/ # Images and media+?? ������ icon.png # Project icon+?? ������ teaser.png # Teaser figure+??+������ ?? cli-anything-plugin/ # The Claude Code plugin+?? ������ HARNESS.md # Methodology SOP (source of truth)+?? ������ README.md # Plugin documentation+?? ������ QUICKSTART.md # 5-minute getting started+?? ������ PUBLISHING.md # Distribution guide+?? ������ repl_skin.py # Unified REPL interface+?? ������ commands/ # Plugin command definitions+?? ?? ������ cli-anything.md # Main build command+?? ?? ������ refine.md # Expand existing harness coverage+?? ?? ������ test.md # Test runner+?? ?? ������ validate.md # Standards validation+?? ������ scripts/+?? ������ setup-cli-anything.sh # Setup script+??+������ ?? codex-skill/ # Codex skill entry point+������ ?? gimp/agent-harness/ # GIMP CLI (107 tests)+������ ?? blender/agent-harness/ # Blender CLI (208 tests)+������ ?? inkscape/agent-harness/ # Inkscape CLI (202 tests)+������ ?? audacity/agent-harness/ # Audacity CLI (161 tests)+������ ?? browser/agent-harness/ # Browser CLI (DOMShell MCP, new)+������ ?? libreoffice/agent-harness/ # LibreOffice CLI (158 tests)+������ ?? mailchimp/agent-harness/ # Mailchimp Marketing API CLI (303 commands, 36 unit tests)+������ ?? zotero/agent-harness/ # Zotero CLI (new, write import support)$1112 tests, new)-├── 📝 mubu/agent-harness/ # Mubu CLI (96 tests)-├── 📹 obs-studio/agent-harness/ # OBS Studio CLI (153 tests)-├── 📱 nslogger/agent-harness/ # NSLogger CLI (139 tests)-├── 🎞�?kdenlive/agent-harness/ # Kdenlive CLI (155 tests)-├── 🎬 shotcut/agent-harness/ # Shotcut CLI (154 tests)-├── 📞 zoom/agent-harness/ # Zoom CLI (22 tests)-├── 🎵 musescore/agent-harness/ # MuseScore CLI (56 tests)-├── 📐 drawio/agent-harness/ # Draw.io CLI (138 tests)-├── ⛓️ eth2-quickstart/agent-harness/ # ETH2 QuickStart CLI (18 unit, 3 e2e skipped)-├── 🧜 mermaid/agent-harness/ # Mermaid Live Editor CLI (10 tests)-├── �?anygen/agent-harness/ # AnyGen CLI (50 tests)-├── 🖼�?comfyui/agent-harness/ # ComfyUI CLI (70 tests)-├── 🧠 notebooklm/agent-harness/ # NotebookLM CLI (experimental, 21 tests)-├── 🧩 dify-workflow/agent-harness/ # Dify Workflow CLI wrapper (11 tests)-├── 🛡�?adguardhome/agent-harness/ # AdGuard Home CLI (36 tests)-├── 🦙 ollama/agent-harness/ # Ollama CLI (98 tests)-├── 🎮 godot/agent-harness/ # Godot Engine CLI (24 tests)-├── 📦 sbox/agent-harness/ # s&box CLI (244 tests: 157 unit + 17 orchestrator + 50 e2e + 20 exit-code)-├── 🎨 sketch/agent-harness/ # Sketch CLI (19 tests, Node.js)-├── 🔬 renderdoc/agent-harness/ # RenderDoc CLI (59 tests)-├── 🟩 nsight-graphics/agent-harness/ # Nsight Graphics CLI (51 tests)-├── 🐞 lldb/agent-harness/ # LLDB CLI (27 tests)-├── 📈 unrealinsights/agent-harness/ # Unreal Insights CLI (50 tests)-├── 🎬 videocaptioner/agent-harness/ # VideoCaptioner CLI (26 tests)-├── 🎬 openscreen/agent-harness/ # Openscreen CLI �?screen recording editor (101 tests)-├── ☁️ cloudcompare/agent-harness/ # CloudCompare CLI (88 tests)-├── 🔍 exa/agent-harness/ # Exa CLI (40 tests)-└── �?cloudanalyzer/agent-harness/ # CloudAnalyzer CLI (14 tests)+������ ?? mubu/agent-harness/ # Mubu CLI (96 tests)+������ ?? obs-studio/agent-harness/ # OBS Studio CLI (153 tests)+������ ?? nslogger/agent-harness/ # NSLogger CLI (139 tests)+������ ????kdenlive/agent-harness/ # Kdenlive CLI (155 tests)+������ ?? shotcut/agent-harness/ # Shotcut CLI (154 tests)+������ ?? zoom/agent-harness/ # Zoom CLI (22 tests)+������ ?? musescore/agent-harness/ # MuseScore CLI (56 tests)+������ ?? drawio/agent-harness/ # Draw.io CLI (138 tests)+������ ?? eth2-quickstart/agent-harness/ # ETH2 QuickStart CLI (18 unit, 3 e2e skipped)+������ ?? mermaid/agent-harness/ # Mermaid Live Editor CLI (10 tests)+������ ??anygen/agent-harness/ # AnyGen CLI (50 tests)+������ ????comfyui/agent-harness/ # ComfyUI CLI (70 tests)+������ ?? notebooklm/agent-harness/ # NotebookLM CLI (experimental, 21 tests)+������ ?? dify-workflow/agent-harness/ # Dify Workflow CLI wrapper (11 tests)+������ ????adguardhome/agent-harness/ # AdGuard Home CLI (36 tests)+������ ?? ollama/agent-harness/ # Ollama CLI (98 tests)+������ ?? godot/agent-harness/ # Godot Engine CLI (24 tests)+������ ?? sbox/agent-harness/ # s&box CLI (244 tests: 157 unit + 17 orchestrator + 50 e2e + 20 exit-code)+������ ?? sketch/agent-harness/ # Sketch CLI (19 tests, Node.js)+������ ?? renderdoc/agent-harness/ # RenderDoc CLI (59 tests)+������ ?? nsight-graphics/agent-harness/ # Nsight Graphics CLI (51 tests)+������ ?? lldb/agent-harness/ # LLDB CLI (27 tests)+������ ?? unrealinsights/agent-harness/ # Unreal Insights CLI (50 tests)+������ ?? videocaptioner/agent-harness/ # VideoCaptioner CLI (26 tests)+������ ?? openscreen/agent-harness/ # Openscreen CLI ??screen recording editor (101 tests)+������ ?? cloudcompare/agent-harness/ # CloudCompare CLI (88 tests)+������ ?? exa/agent-harness/ # Exa CLI (40 tests)+������ ??cloudanalyzer/agent-harness/ # CloudAnalyzer CLI (14 tests)```Each `agent-harness/` contains an installable Python package under `cli_anything.<software>/` with Click CLI, core modules, utils (including `repl_skin.py` and backend wrapper), and comprehensive tests.----## 🎯 Plugin Commands+## ?? Plugin Commands| Command | Description ||---------|-------------|-| `/cli-anything <software-path-or-repo>` | Build complete CLI harness �?all 7 phases |-| `/cli-anything:refine <software-path> [focus]` | Refine an existing harness �?expand coverage with gap analysis |+| `/cli-anything <software-path-or-repo>` | Build complete CLI harness ??all 7 phases |+| `/cli-anything:refine <software-path> [focus]` | Refine an existing harness ??expand coverage with gap analysis || `/cli-anything:test <software-path-or-repo>` | Run tests and update TEST.md with results || `/cli-anything:validate <software-path-or-repo>` | Validate against HARNESS.md standards |@@ -1244,7 +1244,7 @@ Each `agent-harness/` contains an installable Python package under `cli_anything# Build from a GitHub repo/cli-anything https://github.com/blender/blender-# Refine an existing harness �?broad gap analysis+# Refine an existing harness ??broad gap analysis/cli-anything:refine /home/user/gimp# Refine with a specific focus area@@ -1259,25 +1259,25 @@ Each `agent-harness/` contains an installable Python package under `cli_anything----## 🎮 Demo: Using a Generated CLI+## ?? Demo: Using a Generated CLIHere's what an agent can do with `cli-anything-libreoffice`:```bash# Create a new Writer document$ cli-anything-libreoffice document new -o report.json --type writer-�?Created Writer document: report.json+??Created Writer document: report.json# Add content$ cli-anything-libreoffice --project report.json writer add-heading -t "Q1 Report" --level 1-�?Added heading: "Q1 Report"+??Added heading: "Q1 Report"$ cli-anything-libreoffice --project report.json writer add-table --rows 4 --cols 3-�?Added 4×3 table+??Added 4��3 table# Export to real PDF via LibreOffice headless$ cli-anything-libreoffice --project report.json export render output.pdf -p pdf --overwrite-�?Exported: output.pdf (42,831 bytes) via libreoffice-headless+??Exported: output.pdf (42,831 bytes) via libreoffice-headless# JSON mode for agent consumption$ cli-anything-libreoffice --json document info --project report.json@@ -1294,27 +1294,27 @@ $ cli-anything-libreoffice --json document info --project report.json```$ cli-anything-blender-╔══════════════════════════════════════════╗-�? cli-anything-blender v1.0.0 �?-�? Blender CLI for AI Agents �?-╚══════════════════════════════════════════╝+�X�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�[+?? cli-anything-blender v1.0.0 ??+?? Blender CLI for AI Agents ??+�^�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�T�ablender> scene new --name ProductShot-�?Created scene: ProductShot+??Created scene: ProductShotblender[ProductShot]> object add-mesh --type cube --location 0 0 1-�?Added mesh: Cube at (0, 0, 1)+??Added mesh: Cube at (0, 0, 1)blender[ProductShot]*> render execute --output render.png --engine CYCLES-�?Rendered: render.png (1920×1080, 2.3 MB) via blender --background+??Rendered: render.png (1920��1080, 2.3 MB) via blender --backgroundblender[ProductShot]> exit-Goodbye! 👋+Goodbye! ??```----## 📖 The Standard Playbook: HARNESS.md+## ?? The Standard Playbook: HARNESS.mdHARNESS.md is our definitive SOP for making any software agent-accessible via automated CLI generation.@@ -1326,17 +1326,17 @@ The playbook distills key insights from successfully building all 18 diverse, pr| Lesson | Description ||--------|-------------|-| **Use the real software** | The CLI MUST call the actual application for rendering. No Pillow replacements for GIMP, no custom renderers for Blender. Generate valid project files �?invoke the real backend. |-| **The Rendering Gap** | GUI apps apply effects at render time. If your CLI manipulates project files but uses a naive export tool, effects get silently dropped. Solution: native renderer �?filter translation �?render script. |-| **Filter Translation** | When mapping effects between formats (MLT �?ffmpeg), watch for duplicate filter merging, interleaved stream ordering, parameter space differences, and unmappable effects. |-| **Timecode Precision** | Non-integer frame rates (29.97fps) cause cumulative rounding. Use `round()` not `int()`, integer arithmetic for display, and ±1 frame tolerance in tests. |+| **Use the real software** | The CLI MUST call the actual application for rendering. No Pillow replacements for GIMP, no custom renderers for Blender. Generate valid project files ??invoke the real backend. |+| **The Rendering Gap** | GUI apps apply effects at render time. If your CLI manipulates project files but uses a naive export tool, effects get silently dropped. Solution: native renderer ??filter translation ??render script. |+| **Filter Translation** | When mapping effects between formats (MLT ??ffmpeg), watch for duplicate filter merging, interleaved stream ordering, parameter space differences, and unmappable effects. |+| **Timecode Precision** | Non-integer frame rates (29.97fps) cause cumulative rounding. Use `round()` not `int()`, integer arithmetic for display, and ��1 frame tolerance in tests. || **Output Verification** | Never trust that export worked because it exited 0. Verify: magic bytes, ZIP/OOXML structure, pixel analysis, audio RMS levels, duration checks. |> See the full methodology: [`cli-anything-plugin/HARNESS.md`](cli-anything-plugin/HARNESS.md)----## 📦 Installation & Usage+## ?? Installation & Usage### For Plugin Users (Claude Code)@@ -1378,20 +1378,20 @@ CLI_ANYTHING_FORCE_INSTALLED=1 python3 -m pytest cli_anything/<software>/tests/----## 🤝 Contributing+## ?? ContributingWe welcome contributions! CLI-Anything is designed to be extensible:-- **New software targets** �?Use the plugin to generate a CLI for any software with a codebase, then submit your harness via [`cli-anything-plugin/PUBLISHING.md`](cli-anything-plugin/PUBLISHING.md).-- **Methodology improvements** �?PRs to `HARNESS.md` that encode new lessons learned-- **Plugin enhancements** �?New commands, phase improvements, better validation-- **Test coverage** �?More E2E scenarios, edge cases, workflow tests+- **New software targets** ??Use the plugin to generate a CLI for any software with a codebase, then submit your harness via [`cli-anything-plugin/PUBLISHING.md`](cli-anything-plugin/PUBLISHING.md).+- **Methodology improvements** ??PRs to `HARNESS.md` that encode new lessons learned+- **Plugin enhancements** ??New commands, phase improvements, better validation+- **Test coverage** ??More E2E scenarios, edge cases, workflow tests### Limitations-- **Requires strong foundation models** �?CLI-Anything relies on frontier-class models (e.g., Claude Opus 4.6, Claude Sonnet 4.6, GPT-5.4) for reliable harness generation. Weaker or smaller models may produce incomplete or incorrect CLIs that require significant manual correction.-- **Relies on available source code** �?The 7-phase pipeline analyzes and generates from source code. When the target software only provides compiled binaries that require decompilation, harness quality and coverage will degrade substantially.-- **May require iterative refinement** �?A single `/cli-anything` run may not fully cover all capabilities. Running `/refine` one or more times is often needed to push the CLI's performance and coverage to production quality.+- **Requires strong foundation models** ??CLI-Anything relies on frontier-class models (e.g., Claude Opus 4.6, Claude Sonnet 4.6, GPT-5.4) for reliable harness generation. Weaker or smaller models may produce incomplete or incorrect CLIs that require significant manual correction.+- **Relies on available source code** ??The 7-phase pipeline analyzes and generates from source code. When the target software only provides compiled binaries that require decompilation, harness quality and coverage will degrade substantially.+- **May require iterative refinement** ??A single `/cli-anything` run may not fully cover all capabilities. Running `/refine` one or more times is often needed to push the CLI's performance and coverage to production quality.### Roadmap@@ -1404,24 +1404,24 @@ We welcome contributions! CLI-Anything is designed to be extensible:----## 📖 Documentation+## ?? Documentation| Document | Description ||----------|-------------|-| [`cli-anything-plugin/HARNESS.md`](cli-anything-plugin/HARNESS.md) | The methodology SOP �?single source of truth |-| [`cli-anything-plugin/README.md`](cli-anything-plugin/README.md) | Plugin documentation �?commands, options, phases |+| [`cli-anything-plugin/HARNESS.md`](cli-anything-plugin/HARNESS.md) | The methodology SOP ??single source of truth |+| [`cli-anything-plugin/README.md`](cli-anything-plugin/README.md) | Plugin documentation ??commands, options, phases || [`cli-anything-plugin/QUICKSTART.md`](cli-anything-plugin/QUICKSTART.md) | 5-minute getting started guide || [`cli-anything-plugin/PUBLISHING.md`](cli-anything-plugin/PUBLISHING.md) | Distribution and publishing guide |Each generated harness also includes:-- `<SOFTWARE>.md` �?Architecture SOP specific to that application-- `tests/TEST.md` �?Test plan and results documentation+- `<SOFTWARE>.md` ??Architecture SOP specific to that application+- `tests/TEST.md` ??Test plan and results documentation----## �?Star History+## ??Star History-If CLI-Anything helps make your software Agent-native, give us a star! �?+If CLI-Anything helps make your software Agent-native, give us a star! ??<div align="center"><a href="https://star-history.com/#HKUDS/CLI-Anything&Date">@@ -1435,15 +1435,15 @@ If CLI-Anything helps make your software Agent-native, give us a star! �?----## 📄 License+## ?? License-Apache License 2.0 �?free to use, modify, and distribute.+Apache License 2.0 ??free to use, modify, and distribute.---<div align="center">-**CLI-Anything** �?*Make any software with a codebase Agent-native.*+**CLI-Anything** ??*Make any software with a codebase Agent-native.*<sub>A methodology for the age of AI agents | 18 professional software demos | 2,392 passing tests</sub>@@ -1454,6 +1454,6 @@ Apache License 2.0 �?free to use, modify, and distribute.</div><p align="center">- <em> Thanks for visiting �?CLI-Anything!</em><br><br>+ <em> Thanks for visiting ??CLI-Anything!</em><br><br><img src="https://visitor-badge.laobi.icu/badge?page_id=HKUDS.CLI-Anything&style=for-the-badge&color=00d4ff" alt="Views">-├── 📓 joplin/agent-harness/ # Joplin CLI (112 tests, new)+������ ?? joplin/agent-harness/ # Joplin CLI (112 tests, new)diff --git a/README_CN.md b/README_CN.mdindex 0807834c4..314c354a9 100644--- a/README_CN.md+++ b/README_CN.md@@ -2,29 +2,29 @@<p align="center"><strong>今天的软件为人而生👨💻,明天的用户是 Agent🤖<br>-CLI-Anything:连接 AI Agent 与全世界软件的桥梁</strong><br>+CLI-Anything:连�?AI Agent 与全世界软件的桥�?/strong><br></p>-**🌐 [CLI-Hub](https://hkuds.github.io/CLI-Anything/)**:在 **[CLI-Hub](https://hkuds.github.io/CLI-Anything/)** 探索社区已构建的所有 CLI,一条命令即可安装。想贡献你的 CLI?[提交 PR](https://github.com/HKUDS/CLI-Anything/blob/main/CONTRIBUTING.md) — Hub 会即时更新。+**🌐 [CLI-Hub](https://hkuds.github.io/CLI-Anything/)**:在 **[CLI-Hub](https://hkuds.github.io/CLI-Anything/)** 探索社区已构建的所�?CLI,一条命令即可安装。想贡献你的 CLI?[提交 PR](https://github.com/HKUDS/CLI-Anything/blob/main/CONTRIBUTING.md) �?Hub 会即时更新�?<p align="center">- <a href="#-快速上手"><img src="https://img.shields.io/badge/快速上手-5_分钟-blue?style=for-the-badge" alt="Quick Start"></a>- <a href="#-实测展示"><img src="https://img.shields.io/badge/Demo-13_款软件-green?style=for-the-badge" alt="Demos"></a>+ <a href="#-快速上�?><img src="https://img.shields.io/badge/快速上�?5_分钟-blue?style=for-the-badge" alt="Quick Start"></a>+ <a href="#-实测展示"><img src="https://img.shields.io/badge/Demo-13_款软�?green?style=for-the-badge" alt="Demos"></a><a href="#-测试结果"><img src="https://img.shields.io/badge/测试-1%2C741_通过-brightgreen?style=for-the-badge" alt="Tests"></a><a href="LICENSE"><img src="https://img.shields.io/badge/License-Apache_2.0-yellow?style=for-the-badge" alt="License"></a></p><p align="center">- <img src="https://img.shields.io/badge/python-≥3.10-blue?logo=python&logoColor=white" alt="Python">- <img src="https://img.shields.io/badge/click-≥8.0-green" alt="Click">+ <img src="https://img.shields.io/badge/python-�?.10-blue?logo=python&logoColor=white" alt="Python">+ <img src="https://img.shields.io/badge/click-�?.0-green" alt="Click"><img src="https://img.shields.io/badge/pytest-100%25_pass-brightgreen" alt="Pytest"><img src="https://img.shields.io/badge/coverage-unit_%2B_e2e-orange" alt="Coverage"><img src="https://img.shields.io/badge/output-JSON_%2B_Human-blueviolet" alt="Output">- <a href="https://github.com/HKUDS/.github/blob/main/profile/README.md"><img src="https://img.shields.io/badge/飞书-交流群-E9DBFC?style=flat&logo=feishu&logoColor=white" alt="Feishu"></a>-<a href="https://github.com/HKUDS/.github/blob/main/profile/README.md"><img src="https://img.shields.io/badge/微信-交流群-C5EAB4?style=flat&logo=wechat&logoColor=white" alt="WeChat"></a>+ <a href="https://github.com/HKUDS/.github/blob/main/profile/README.md"><img src="https://img.shields.io/badge/飞书-交流�?E9DBFC?style=flat&logo=feishu&logoColor=white" alt="Feishu"></a>+<a href="https://github.com/HKUDS/.github/blob/main/profile/README.md"><img src="https://img.shields.io/badge/微信-交流�?C5EAB4?style=flat&logo=wechat&logoColor=white" alt="WeChat"></a></p>-**一行命令**,让任意软件接入 OpenClaw、nanobot、Cursor、Claude Code 等 Agent 框架。+**一行命�?*,让任意软件接入 OpenClaw、nanobot、Cursor、Claude Code �?Agent 框架�?<p align="center"><img src="assets/cli-typing.gif" alt="CLI-Anything typing demo" width="800">@@ -36,38 +36,38 @@ CLI-Anything:连接 AI Agent 与全世界软件的桥梁</strong><br>----## 🤔 为什么是 CLI?+## 🤔 为什么是 CLI�?-CLI 是人类和 AI Agent 共通的万能接口:+CLI 是人类和 AI Agent 共通的万能接口�?-• **结构化、可组合** - 文本命令天然匹配 LLM 的输入格式,可自由串联成复杂工作流+�?**结构化、可组合** - 文本命令天然匹配 LLM 的输入格式,可自由串联成复杂工作�?-• **轻量且通用** - 几乎零开销,跨平台运行,不依赖额外环境+�?**轻量且通用** - 几乎零开销,跨平台运行,不依赖额外环境-• **自描述** - 一个 `--help` 就能让 Agent 自动发现所有功能+�?**自描�?* - 一�?`--help` 就能�?Agent 自动发现所有功�?-• **久经验证** - Claude Code 每天通过 CLI 执行数以千计的真实任务+�?**久经验证** - Claude Code 每天通过 CLI 执行数以千计的真实任�?-• **Agent 友好** - 结构化 JSON 输出,Agent 无需任何额外解析+�?**Agent 友好** - 结构�?JSON 输出,Agent 无需任何额外解析-• **确定且可靠** - 输出稳定一致,Agent 行为可预测+�?**确定且可�?* - 输出稳定一致,Agent 行为可预�?-## 🚀 快速上手+## 🚀 快速上�?### 环境要求- **Python 3.10+**-- 目标软件已安装(如 GIMP、Blender、LibreOffice 或你自己的应用)-- 支持的 AI 编程工具之一:[Claude Code](#-claude-code) | [OpenClaw](#-openclaw) | [OpenCode](#-opencode) | [Codex](#-codex) | [Qodercli](#-qodercli) | [GitHub Copilot CLI](#-github-copilot-cli) | [更多平台](#-更多平台即将支持)+- 目标软件已安装(�?GIMP、Blender、LibreOffice 或你自己的应用)+- 支持�?AI 编程工具之一:[Claude Code](#-claude-code) | [OpenClaw](#-openclaw) | [OpenCode](#-opencode) | [Codex](#-codex) | [Qodercli](#-qodercli) | [GitHub Copilot CLI](#-github-copilot-cli) | [更多平台](#-更多平台即将支持)### 选择你的平台<details open>-<summary><h4 id="-claude-code">⚡ Claude Code</h4></summary>+<summary><h4 id="-claude-code">�?Claude Code</h4></summary>**第一步:添加插件市场**-CLI-Anything 以 Claude Code 插件市场的形式托管在 GitHub 上。+CLI-Anything �?Claude Code 插件市场的形式托管在 GitHub 上�?```bash# 添加 CLI-Anything 插件市场@@ -77,20 +77,20 @@ CLI-Anything 以 Claude Code 插件市场的形式托管在 GitHub 上。**第二步:安装插件**```bash-# 从市场安装 cli-anything 插件+# 从市场安�?cli-anything 插件/plugin install cli-anything```-搞定。插件已经在你的 Claude Code 会话中可用了。+搞定。插件已经在你的 Claude Code 会话中可用了�?-**Windows 注意:** Claude Code 通过 `bash` 执行命令。Windows 下请安装 Git for Windows(包含 `bash` 和 `cygpath`)-或使用 WSL,否则可能出现 `cygpath: command not found`。+**Windows 注意�?* Claude Code 通过 `bash` 执行命令。Windows 下请安装 Git for Windows(包�?`bash` �?`cygpath`�?+或使�?WSL,否则可能出�?`cygpath: command not found`�?-**第三步:一行命令生成 CLI**+**第三步:一行命令生�?CLI**```bash# /cli-anything <软件路径或仓库地址>-# 为 GIMP 生成完整的 CLI(7 个阶段全自动)+# �?GIMP 生成完整�?CLI�? 个阶段全自动�?/cli-anything ./gimp# 兼容写法(旧版本 Claude Code 可重试)@@ -98,13 +98,13 @@ CLI-Anything 以 Claude Code 插件市场的形式托管在 GitHub 上。```Claude Code 不同版本的命令兼容说明:-- 优先使用 `/cli-anything` 作为主入口。-- 在已**确认插件已安装并加载**的情况下,若旧版本的 Claude Code 不识别 `/cli-anything`,可尝试兼容写法 `/cli-anything:cli-anything`。-- 其他辅助命令保持 `:子命令` 形式(例如 `/cli-anything:refine`)。+- 优先使用 `/cli-anything` 作为主入口�?+- 在已**确认插件已安装并加载**的情况下,若旧版本的 Claude Code 不识�?`/cli-anything`,可尝试兼容写法 `/cli-anything:cli-anything`�?+- 其他辅助命令保持 `:子命令` 形式(例�?`/cli-anything:refine`)�?-如果出现 `Unknown skill: cli-anything`,两种写法都引用同一个 skill 名称,切换写法无法解决,请优先排查插件是否已安装/加载:+如果出现 `Unknown skill: cli-anything`,两种写法都引用同一�?skill 名称,切换写法无法解决,请优先排查插件是否已安装/加载�?1. 重新加载插件命令:`/reload-plugins`-2. 验证插件是否已加载:`/help cli-anything`(能看到 CLI-Anything 帮助即表示已加载)+2. 验证插件是否已加载:`/help cli-anything`(能看到 CLI-Anything 帮助即表示已加载�?3. 如仍未识别,重新从市场安装:- `/plugin marketplace add HKUDS/CLI-Anything`- `/plugin install cli-anything`@@ -113,38 +113,38 @@ Claude Code 不同版本的命令兼容说明:- 仅旧版本:`/cli-anything:cli-anything ./gimp`完整流水线自动执行:-1. 🔍 **分析** — 扫描源码,将 GUI 操作映射到 API-2. 📐 **设计** — 规划命令分组、状态模型、输出格式-3. 🔨 **实现** — 构建 Click CLI,包含 REPL、JSON 输出、撤销/重做-4. 📋 **规划测试** — 生成 TEST.md,涵盖单元测试和端到端测试计划-5. 🧪 **编写测试** — 实现完整测试套件-6. 📝 **文档** — 更新 TEST.md,写入测试结果-7. 📦 **发布** — 生成 `setup.py`,安装到 PATH+1. 🔍 **分析** �?扫描源码,将 GUI 操作映射�?API+2. 📐 **设计** �?规划命令分组、状态模型、输出格�?+3. 🔨 **实现** �?构建 Click CLI,包�?REPL、JSON 输出、撤销/重做+4. 📋 **规划测试** �?生成 TEST.md,涵盖单元测试和端到端测试计�?+5. 🧪 **编写测试** �?实现完整测试套件+6. 📝 **文档** �?更新 TEST.md,写入测试结�?+7. 📦 **发布** �?生成 `setup.py`,安装到 PATH**第四步(可选):优化和扩展 CLI**-初始构建完成后,你可以迭代优化 CLI,扩展覆盖面并补充缺失的功能:+初始构建完成后,你可以迭代优�?CLI,扩展覆盖面并补充缺失的功能�?```bash-# 全面优化 — Agent 分析所有功能的覆盖差距+# 全面优化 �?Agent 分析所有功能的覆盖差距/cli-anything:refine ./gimp-# 定向优化 — 指定特定功能领域+# 定向优化 �?指定特定功能领域/cli-anything:refine ./gimp "我需要更多图像批处理和滤镜相关的 CLI"```-优化命令会对软件的完整功能与当前 CLI 覆盖范围进行差距分析,然后为识别到的差距实现新命令、测试和文档。你可以多次运行该命令,逐步扩大功能覆盖范围 — 每次运行都是增量的、非破坏性的。+优化命令会对软件的完整功能与当前 CLI 覆盖范围进行差距分析,然后为识别到的差距实现新命令、测试和文档。你可以多次运行该命令,逐步扩大功能覆盖范围 �?每次运行都是增量的、非破坏性的�?<details><summary><strong>备选方案:手动安装</strong></summary>-如果你不想用插件市场:+如果你不想用插件市场�?```bash# 克隆仓库git clone https://github.com/HKUDS/CLI-Anything.git-# 复制插件到 Claude Code 插件目录+# 复制插件�?Claude Code 插件目录cp -r CLI-Anything/cli-anything-plugin ~/.claude/plugins/cli-anything# 重新加载插件@@ -156,13 +156,13 @@ cp -r CLI-Anything/cli-anything-plugin ~/.claude/plugins/cli-anything</details><details>-<summary><h4 id="-opencode">⚡ OpenCode (实验性支持)</h4></summary>+<summary><h4 id="-opencode">�?OpenCode (实验性支持)</h4></summary>**第一步:安装命令**-**注意:** 请升级到最新 OpenCode,旧版本可能使用不同的命令目录路径。+**注意�?* 请升级到最�?OpenCode,旧版本可能使用不同的命令目录路径�?-将 CLI-Anything 命令**和** `HARNESS.md` 复制到 OpenCode 命令目录:+�?CLI-Anything 命令**�?* `HARNESS.md` 复制�?OpenCode 命令目录�?```bash# 克隆仓库@@ -177,29 +177,29 @@ cp CLI-Anything/opencode-commands/*.md .opencode/commands/cp CLI-Anything/cli-anything-plugin/HARNESS.md .opencode/commands/```-> **注意:** `HARNESS.md` 是所有命令引用的方法论规范,必须和命令文件放在同一目录下。+> **注意�?* `HARNESS.md` 是所有命令引用的方法论规范,必须和命令文件放在同一目录下�?-安装后获得 5 个斜杠命令:`/cli-anything`、`/cli-anything-refine`、`/cli-anything-test`、`/cli-anything-validate` 和 `/cli-anything-list`。+安装后获�?5 个斜杠命令:`/cli-anything`、`/cli-anything-refine`、`/cli-anything-test`、`/cli-anything-validate` �?`/cli-anything-list`�?-**第二步:一行命令生成 CLI**+**第二步:一行命令生�?CLI**```bash-# 为 GIMP 生成完整的 CLI(7 个阶段全自动)+# �?GIMP 生成完整�?CLI�? 个阶段全自动�?/cli-anything ./gimp-# 从 GitHub 仓库构建+# �?GitHub 仓库构建/cli-anything https://github.com/blender/blender```-命令以子任务方式运行,遵循与 Claude Code 相同的 7 阶段方法论。+命令以子任务方式运行,遵循与 Claude Code 相同�?7 阶段方法论�?**第三步(可选):优化和扩展 CLI**```bash-# 全面优化 — Agent 分析所有功能的覆盖差距+# 全面优化 �?Agent 分析所有功能的覆盖差距/cli-anything-refine ./gimp-# 定向优化 — 指定特定功能领域+# 定向优化 �?指定特定功能领域/cli-anything-refine ./gimp "批处理和滤镜"```@@ -207,7 +207,7 @@ cp CLI-Anything/cli-anything-plugin/HARNESS.md .opencode/commands/<details>-<summary><h4 id="-qodercli">⚡ Qodercli <sup><code>社区贡献</code></sup></h4></summary>+<summary><h4 id="-qodercli">�?Qodercli <sup><code>社区贡献</code></sup></h4></summary>**第一步:注册插件**@@ -216,9 +216,9 @@ git clone https://github.com/HKUDS/CLI-Anything.gitbash CLI-Anything/qoder-plugin/setup-qodercli.sh```-脚本会将 cli-anything 插件注册到 `~/.qoder.json`。注册后开启新的 Qodercli 会话即可使用。+脚本会将 cli-anything 插件注册�?`~/.qoder.json`。注册后开启新�?Qodercli 会话即可使用�?-**第二步:在 Qodercli 中使用 CLI-Anything**+**第二步:�?Qodercli 中使�?CLI-Anything**```bash/cli-anything:cli-anything ./gimp@@ -229,11 +229,11 @@ bash CLI-Anything/qoder-plugin/setup-qodercli.sh<details>-<summary><h4 id="-openclaw">⚡ OpenClaw</h4></summary>+<summary><h4 id="-openclaw">�?OpenClaw</h4></summary>**第一步:安装 Skill**-CLI-Anything 提供了原生的 OpenClaw `SKILL.md` 文件。请将其复制到你的 OpenClaw 技能目录:+CLI-Anything 提供了原生的 OpenClaw `SKILL.md` 文件。请将其复制到你�?OpenClaw 技能目录:```bash# Clone the repo@@ -246,17 +246,17 @@ cp CLI-Anything/openclaw-skill/SKILL.md ~/.openclaw/skills/cli-anything/SKILL.md**第二步:构建 CLI**-安装完成后,你就可以在 OpenClaw 中直接调用:+安装完成后,你就可以�?OpenClaw 中直接调用:`@cli-anything build a CLI for ./gimp`-该技能采用了与 Claude Code 和 OpenCode 一致的 7 步构建流程。+该技能采用了�?Claude Code �?OpenCode 一致的 7 步构建流程�?</details><details>-<summary><h4 id="-codex">⚡ Codex <sup><code>实验性</code></sup> <sup><code>社区贡献</code></sup></h4></summary>+<summary><h4 id="-codex">�?Codex <sup><code>实验�?/code></sup> <sup><code>社区贡献</code></sup></h4></summary>**第一步:安装 Skill**@@ -270,17 +270,17 @@ git clone https://github.com/HKUDS/CLI-Anything.gitbash CLI-Anything/codex-skill/scripts/install.sh```-在 Windows PowerShell 中,可以使用:+�?Windows PowerShell 中,可以使用�?```powershell.\CLI-Anything\codex-skill\scripts\install.ps1```-脚本会把 skill 安装到 `$CODEX_HOME/skills/cli-anything`;如果没有设置 `CODEX_HOME`,则默认安装到 `~/.codex/skills/cli-anything`。+脚本会把 skill 安装�?`$CODEX_HOME/skills/cli-anything`;如果没有设�?`CODEX_HOME`,则默认安装�?`~/.codex/skills/cli-anything`�?-安装后重启 Codex,让它重新发现这个 skill。+安装后重�?Codex,让它重新发现这�?skill�?-**第二步:在 Codex 里使用 CLI-Anything**+**第二步:�?Codex 里使�?CLI-Anything**直接用自然语言描述任务,例如:@@ -290,14 +290,14 @@ Use CLI-Anything to refine ./shotcut for picture-in-picture workflowsUse CLI-Anything to validate ./libreoffice```-这个 Codex skill 复用了 Claude Code 插件和 OpenCode 命令所使用的同一套方法论,-不会改变生成出来的 Python harness 结构。+这个 Codex skill 复用�?Claude Code 插件�?OpenCode 命令所使用的同一套方法论�?+不会改变生成出来�?Python harness 结构�?</details><details>-<summary><h4 id="-github-copilot-cli">⚡ GitHub Copilot CLI <sup><code>社区贡献</code></sup></h4></summary>+<summary><h4 id="-github-copilot-cli">�?GitHub Copilot CLI <sup><code>社区贡献</code></sup></h4></summary>**第一步:安装插件**@@ -307,9 +307,9 @@ cd CLI-Anythingcopilot plugin install ./cli-anything-plugin```-这将 CLI-Anything 插件安装到 GitHub Copilot CLI 中。插件应该已经在你的 GitHub Copilot CLI 会话中可用了。+这将 CLI-Anything 插件安装�?GitHub Copilot CLI 中。插件应该已经在你的 GitHub Copilot CLI 会话中可用了�?-**第二步:在 GitHub Copilot CLI 中使用 CLI-Anything**+**第二步:�?GitHub Copilot CLI 中使�?CLI-Anything**```bash/cli-anything:cli-anything ./gimp@@ -322,12 +322,12 @@ copilot plugin install ./cli-anything-plugin<details><summary><h4 id="-更多平台即将支持">🔮 更多平台(即将支持)</h4></summary>-CLI-Anything 的设计是平台无关的,计划支持更多 AI 编程工具:+CLI-Anything 的设计是平台无关的,计划支持更多 AI 编程工具�?-- **Codex** — 已通过 `codex-skill/` 提供接入-- **Cursor** — 即将支持-- **Windsurf** — 即将支持-- **你喜欢的工具** — 欢迎贡献!参考 `opencode-commands/` 目录的实现。+- **Codex** �?已通过 `codex-skill/` 提供接入+- **Cursor** �?即将支持+- **Windsurf** �?即将支持+- **你喜欢的工具** �?欢迎贡献!参�?`opencode-commands/` 目录的实现�?</details>@@ -336,7 +336,7 @@ CLI-Anything 的设计是平台无关的,计划支持更多 AI 编程工具:无论你用哪个平台构建,生成的 CLI 使用方式完全一样:```bash-# 安装到 PATH+# 安装�?PATHcd gimp/agent-harness && pip install -e .# 随处可用@@ -344,19 +344,19 @@ cli-anything-gimp --helpcli-anything-gimp project new --width 1920 --height 1080 -o poster.jsoncli-anything-gimp --json layer add -n "Background" --type solid --color "#1a1a2e"-# 进入交互式 REPL+# 进入交互�?REPLcli-anything-gimp```----## 💡 CLI-Anything 的愿景:构建 Agent 原生的软件生态+## 💡 CLI-Anything 的愿景:构建 Agent 原生的软件生�?-• 🌐 **无门槛接入** - 任何软件都能通过结构化 CLI 即刻被 Agent 操控。+�?🌐 **无门槛接�?* - 任何软件都能通过结构�?CLI 即刻�?Agent 操控�?-• 🔗 **无缝集成** - 不需要专门的 API、不需要操控 GUI、不需要重构代码,也不需要复杂的适配层。+�?🔗 **无缝集成** - 不需要专门的 API、不需要操�?GUI、不需要重构代码,也不需要复杂的适配层�?-• 🚀 **面向未来** - 一条命令,就能把为人类设计的软件变成 Agent 的原生工具。+�?🚀 **面向未来** - 一条命令,就能把为人类设计的软件变�?Agent 的原生工具�?---@@ -364,33 +364,33 @@ cli-anything-gimp| 类别 | 如何接入 Agent | 典型软件 ||------|--------------|---------|-| **📂 GitHub 开源项目** | 通过自动生成 CLI,将任意开源项目转化为 Agent 可控工具 | VSCodium、WordPress、Calibre、Zotero、Joplin、Logseq、Penpot、Super Productivity |-| **🤖 AI/ML 平台** | 用结构化命令驱动模型训练、推理流水线和超参搜索 | Stable Diffusion WebUI、ComfyUI、InvokeAI、Text-generation-webui、Open WebUI、Fooocus、Kohya_ss、AnythingLLM、SillyTavern |-| **📊 数据与分析** | 以编程方式完成数据处理、可视化和统计分析工作流 | JupyterLab、Apache Superset、Metabase、Redash、DBeaver、KNIME、Orange、OpenSearch Dashboards、Lightdash |-| **💻 开发工具** | 通过 CLI 串联代码编辑、构建、测试与部署流程 | Jenkins、Gitea、Hoppscotch、Portainer、pgAdmin、SonarQube、ArgoCD、OpenLens、Insomnia、Beekeeper Studio |-| **🎨 创意与媒体** | 以编程方式控制内容创作、编辑和渲染工作流 | Blender、GIMP、OBS Studio、Audacity、Krita、Kdenlive、Shotcut、Inkscape、Darktable、LMMS、Ardour |+| **📂 GitHub 开源项�?* | 通过自动生成 CLI,将任意开源项目转化为 Agent 可控工具 | VSCodium、WordPress、Calibre、Zotero、Joplin、Logseq、Penpot、Super Productivity |+| **🤖 AI/ML 平台** | 用结构化命令驱动模型训练、推理流水线和超参搜�?| Stable Diffusion WebUI、ComfyUI、InvokeAI、Text-generation-webui、Open WebUI、Fooocus、Kohya_ss、AnythingLLM、SillyTavern |+| **📊 数据与分�?* | 以编程方式完成数据处理、可视化和统计分析工作流 | JupyterLab、Apache Superset、Metabase、Redash、DBeaver、KNIME、Orange、OpenSearch Dashboards、Lightdash |+| **💻 开发工�?* | 通过 CLI 串联代码编辑、构建、测试与部署流程 | Jenkins、Gitea、Hoppscotch、Portainer、pgAdmin、SonarQube、ArgoCD、OpenLens、Insomnia、Beekeeper Studio |+| **🎨 创意与媒�?* | 以编程方式控制内容创作、编辑和渲染工作�?| Blender、GIMP、OBS Studio、Audacity、Krita、Kdenlive、Shotcut、Inkscape、Darktable、LMMS、Ardour || **📐 图表与可视化** | 以编程方式创建和操作流程图、架构图、ER 图等各类图表 | Draw.io (diagrams.net)、Mermaid、PlantUML、Excalidraw、yEd || **🔬 科学计算** | 自动化科研工作流、仿真模拟和复杂计算 | ImageJ、FreeCAD、QGIS、ParaView、Gephi、LibreCAD、Stellarium、KiCad、JASP、Jamovi |-| **🏢 企业与办公** | 将商业应用和生产力工具转化为 Agent 可访问的系统 | NextCloud、GitLab、Grafana、Mattermost、LibreOffice、AppFlowy、NocoDB、Odoo (Community)、Plane、ERPNext |-| **📞 通信与协作** | 通过结构化 CLI 自动化会议调度、参会人管理、录制获取和报告生成 | Zoom、Jitsi Meet、BigBlueButton、Mattermost |+| **🏢 企业与办�?* | 将商业应用和生产力工具转化为 Agent 可访问的系统 | NextCloud、GitLab、Grafana、Mattermost、LibreOffice、AppFlowy、NocoDB、Odoo (Community)、Plane、ERPNext |+| **📞 通信与协�?* | 通过结构�?CLI 自动化会议调度、参会人管理、录制获取和报告生成 | Zoom、Jitsi Meet、BigBlueButton、Mattermost |----## CLI-Anything 的核心优势+## CLI-Anything 的核心优�?### Agent 与软件之间的鸿沟-AI Agent 推理能力很强,但操控真实专业软件的能力很弱。现有方案要么是脆弱的 GUI 自动化,要么是覆盖面有限的 API,要么是阉割了 90% 功能的重新实现。+AI Agent 推理能力很强,但操控真实专业软件的能力很弱。现有方案要么是脆弱�?GUI 自动化,要么是覆盖面有限�?API,要么是阉割�?90% 功能的重新实现�?-**CLI-Anything 的解法**:把任何专业软件变成 Agent 原生工具,功能一个不少。+**CLI-Anything 的解�?*:把任何专业软件变成 Agent 原生工具,功能一个不少�?-| **现有痛点** | **CLI-Anything 怎么解** |+| **现有痛点** | **CLI-Anything 怎么�?* ||------------|----------------------|-| 🤖 "AI 用不了真正的专业工具" | 直接对接真实软件后端(Blender、LibreOffice、FFmpeg)—— 完整的专业能力,零妥协 |+| 🤖 "AI 用不了真正的专业工具" | 直接对接真实软件后端(Blender、LibreOffice、FFmpeg)—�?完整的专业能力,零妥�?|| 💸 "GUI 自动化三天两头崩" | 告别截图、点击和 RPA 的脆弱性,纯命令行操控,结构化接口 |-| 📊 "Agent 需要结构化数据" | 内置 JSON 输出供 Agent 直接消费,同时保留可读格式方便调试 |-| 🔧 "定制集成太贵了" | 一个插件就能为任意代码库自动生成 CLI,经过验证的 7 阶段流水线 |-| ⚡ "原型和生产之间差十万八千里" | 1,774+ 测试用例,全部在真实软件上验证通过,覆盖 13 款主流应用 |+| 📊 "Agent 需要结构化数据" | 内置 JSON 输出�?Agent 直接消费,同时保留可读格式方便调�?|+| 🔧 "定制集成太贵�? | 一个插件就能为任意代码库自动生�?CLI,经过验证的 7 阶段流水�?|+| �?"原型和生产之间差十万八千�? | 1,774+ 测试用例,全部在真实软件上验证通过,覆�?13 款主流应�?|---@@ -400,23 +400,23 @@ AI Agent 推理能力很强,但操控真实专业软件的能力很弱。现<tr><td width="33%">-### 🛠️ 让 Agent 接管你的工作流+### 🛠�?�?Agent 接管你的工作�?-不管是专业场景还是日常事务 —— 把代码库扔给 `/cli-anything` 就行。GIMP、Blender、Shotcut 搞创作,LibreOffice、OBS Studio 干日常。没有源码?找个开源替代品,照样能用。你会立刻得到一套 Agent 可以直接调用的完整 CLI。+不管是专业场景还是日常事�?—�?把代码库扔给 `/cli-anything` 就行。GIMP、Blender、Shotcut 搞创作,LibreOffice、OBS Studio 干日常。没有源码?找个开源替代品,照样能用。你会立刻得到一�?Agent 可以直接调用的完�?CLI�?</td><td width="33%">-### 🔗 把散装 API 统一成一个 CLI+### 🔗 把散�?API 统一成一�?CLI-受够了一堆零碎的 Web 服务 API?把文档或 SDK 手册喂给 `/cli-anything`,你的 Agent 就能拿到一个**有状态的、功能完整的 CLI**,把那些零散的接口整合成逻辑清晰的命令组。一个工具可替代几十个裸 API 调用 —— 能力更强,token 更省。+受够了一堆零碎的 Web 服务 API?把文档�?SDK 手册喂给 `/cli-anything`,你�?Agent 就能拿到一�?*有状态的、功能完整的 CLI**,把那些零散的接口整合成逻辑清晰的命令组。一个工具可替代几十个裸 API 调用 —�?能力更强,token 更省�?</td><td width="33%">### 🚀 取代 GUI Agent,或让它更强-CLI-Anything 可直接**替代基于 GUI 的 Agent 方案** —— 无需截图,也无需繁琐地点击像素操作。更实用的是:只要你对 GUI 软件执行过 `/cli-anything` 命令,就能**全自动生成 Agent 任务、评测器及 Benchmark** —— 全程采用纯代码与终端操作,支持迭代优化,显著提升效率。+CLI-Anything 可直�?*替代基于 GUI �?Agent 方案** —�?无需截图,也无需繁琐地点击像素操作。更实用的是:只要你�?GUI 软件执行�?`/cli-anything` 命令,就�?*全自动生�?Agent 任务、评测器�?Benchmark** —�?全程采用纯代码与终端操作,支持迭代优化,显著提升效率�?</td></tr>@@ -424,22 +424,22 @@ CLI-Anything 可直接**替代基于 GUI 的 Agent 方案** —— 无需截图----## ✨ ⚙️ CLI-Anything 的工作方式+## �?⚙️ CLI-Anything 的工作方�?<table><tr><td width="50%">-### 🏗️ 全自动 7 阶段流水线+### 🏗�?全自�?7 阶段流水�?-从代码分析到发布上线 —— 插件自动完成架构设计、代码实现、测试规划、测试编写和文档生成,全程无需人工介入。+从代码分析到发布上线 —�?插件自动完成架构设计、代码实现、测试规划、测试编写和文档生成,全程无需人工介入�?</td><td width="50%">### 🎯 真实软件集成-直接调用真实应用进行渲染。LibreOffice 生成 PDF,Blender 渲染 3D 场景,Audacity 通过 sox 处理音频。**零妥协**,**零玩具实现**。+直接调用真实应用进行渲染。LibreOffice 生成 PDF,Blender 渲染 3D 场景,Audacity 通过 sox 处理音频�?*零妥�?*�?*零玩具实�?*�?</td></tr>@@ -448,30 +448,30 @@ CLI-Anything 可直接**替代基于 GUI 的 Agent 方案** —— 无需截图### 🔁 智能会话管理-持久化项目状态,支持撤销/重做,加上统一的 REPL 交互界面(ReplSkin),所有 CLI 的使用体验保持一致。+持久化项目状态,支持撤销/重做,加上统一�?REPL 交互界面(ReplSkin),所�?CLI 的使用体验保持一致�?</td><td width="50%">-### 📦 零配置安装+### 📦 零配置安�?-`pip install -e .` 即可将 cli-anything-<软件名> 装到 PATH。Agent 通过标准的 `which` 命令发现工具,不需要额外配置。+`pip install -e .` 即可�?cli-anything-<软件�? 装到 PATH。Agent 通过标准�?`which` 命令发现工具,不需要额外配置�?</td></tr><tr><td width="50%">-### 🧪 生产级测试+### 🧪 生产级测�?-多层验证:使用合成数据的单元测试、使用真实文件和软件的端到端测试,外加已安装命令的 CLI 子进程验证。+多层验证:使用合成数据的单元测试、使用真实文件和软件的端到端测试,外加已安装命令�?CLI 子进程验证�?</td><td width="50%">### 🐍 干净的包架构-所有 CLI 统一在 cli_anything.* 命名空间下 —— 无冲突、可 pip 安装、命名规范统一:cli-anything-gimp、cli-anything-blender 等。+所�?CLI 统一�?cli_anything.* 命名空间�?—�?无冲突、可 pip 安装、命名规范统一:cli-anything-gimp、cli-anything-blender 等�?</td></tr>@@ -481,21 +481,21 @@ CLI-Anything 可直接**替代基于 GUI 的 Agent 方案** —— 无需截图## 🎬 实测展示-### 🎯 通用性+### 🎯 通用�?-CLI-Anything 适用于任何有代码库的软件 —— 不限领域,不限架构。+CLI-Anything 适用于任何有代码库的软件 —�?不限领域,不限架构�?-### 🏭 专业级测试+### 🏭 专业级测�?-在 13 款复杂应用上进行了实测,涵盖创意、生产力、通信、图表、原生调试、GPU 分析和 AI 内容生成领域 —— 这些软件此前对 AI Agent 来说几乎不可触及。+�?13 款复杂应用上进行了实测,涵盖创意、生产力、通信、图表、原生调试、GPU 分析�?AI 内容生成领域 —�?这些软件此前�?AI Agent 来说几乎不可触及�?### 🎨 覆盖多元领域-从创意工作流(图像编辑、3D 建模、矢量图形)到生产工具(音频、办公、直播、视频剪辑)。+从创意工作流(图像编辑�?D 建模、矢量图形)到生产工具(音频、办公、直播、视频剪辑)�?-### ✅ 完整的 CLI 生成+### �?完整�?CLI 生成-每款软件都生成了完整的、可投产的 CLI 接口 —— 不是 demo,而是保留全部功能的完整工具接入。+每款软件都生成了完整的、可投产�?CLI 接口 —�?不是 demo,而是保留全部功能的完整工具接入�?<table><tr>@@ -510,181 +510,181 @@ CLI-Anything 适用于任何有代码库的软件 —— 不限领域,不限<td>图像编辑</td><td><code>cli-anything-gimp</code></td><td>Pillow + GEGL/Script-Fu</td>-<td align="center">✅ 107</td>+<td align="center">�?107</td></tr><tr><td align="center"><strong>🧊 Blender</strong></td>-<td>3D 建模与渲染</td>+<td>3D 建模与渲�?/td><td><code>cli-anything-blender</code></td><td>bpy (Python scripting)</td>-<td align="center">✅ 208</td>+<td align="center">�?208</td></tr><tr><td align="center"><strong>✏️ Inkscape</strong></td><td>矢量图形</td><td><code>cli-anything-inkscape</code></td><td>Direct SVG/XML manipulation</td>-<td align="center">✅ 202</td>+<td align="center">�?202</td></tr><tr><td align="center"><strong>🎵 Audacity</strong></td><td>音频制作</td><td><code>cli-anything-audacity</code></td><td>Python wave + sox</td>-<td align="center">✅ 161</td>+<td align="center">�?161</td></tr><tr><td align="center"><strong>📄 LibreOffice</strong></td>-<td>办公套件(Writer、Calc、Impress)</td>+<td>办公套件(Writer、Calc、Impress�?/td><td><code>cli-anything-libreoffice</code></td><td>ODF generation + headless LO</td>-<td align="center">✅ 158</td>+<td align="center">�?158</td></tr><tr><td align="center"><strong>📚 <a href="zotero/agent-harness/">Zotero</a></strong></td>-<td>文献管理与引用</td>+<td>文献管理与引�?/td><td><code>cli-anything-zotero</code></td><td>Local SQLite + connector + Local API</td>-<td align="center">✅ <a href="zotero/agent-harness/">新增</a></td>+<td align="center">�?<a href="zotero/agent-harness/">新增</a></td></tr><tr><td align="center"><strong>📓 <a href="joplin/agent-harness/">Joplin</a></strong></td>-<td>笔记与待办事项</td>+<td>笔记与待办事�?/td><td><code>cli-anything-joplin</code></td>-<td>Joplin 终端 CLI 子进程</td>-<td align="center">✅ 112</td>+<td>Joplin 终端 CLI 子进�?/td>+<td align="center">�?112</td></tr><tr><td align="center"><strong>📹 OBS Studio</strong></td>-<td>直播与录制</td>+<td>直播与录�?/td><td><code>cli-anything-obs-studio</code></td><td>JSON scene + obs-websocket</td>-<td align="center">✅ 153</td>+<td align="center">�?153</td></tr><tr>-<td align="center"><strong>🎞️ Kdenlive</strong></td>+<td align="center"><strong>🎞�?Kdenlive</strong></td><td>视频剪辑</td><td><code>cli-anything-kdenlive</code></td><td>MLT XML + melt renderer</td>-<td align="center">✅ 155</td>+<td align="center">�?155</td></tr><tr><td align="center"><strong>🎬 Shotcut</strong></td><td>视频剪辑</td><td><code>cli-anything-shotcut</code></td><td>Direct MLT XML + melt</td>-<td align="center">✅ 154</td>+<td align="center">�?154</td></tr><tr><td align="center"><strong>🎬 <a href="openscreen/agent-harness/">Openscreen</a></strong></td>-<td>屏幕录像编辑器</td>+<td>屏幕录像编辑�?/td><td><code>cli-anything-openscreen</code></td><td>ffmpeg backend</td>-<td align="center">✅ 101</td>+<td align="center">�?101</td></tr><tr><td align="center"><strong>📞 Zoom</strong></td><td>视频会议</td><td><code>cli-anything-zoom</code></td><td>Zoom REST API (OAuth2)</td>-<td align="center">✅ 22</td>+<td align="center">�?22</td></tr><tr><td align="center"><strong>📐 Draw.io</strong></td><td>图表绘制</td><td><code>cli-anything-drawio</code></td><td>mxGraph XML + draw.io CLI</td>-<td align="center">✅ 138</td>+<td align="center">�?138</td></tr><tr>-<td align="center"><strong>✨ AnyGen</strong></td>+<td align="center"><strong>�?AnyGen</strong></td><td>AI 内容生成</td><td><code>cli-anything-anygen</code></td><td>AnyGen REST API (anygen.io)</td>-<td align="center">✅ 50</td>+<td align="center">�?50</td></tr><tr><td align="center"><strong>🐞 <a href="lldb/agent-harness/">LLDB</a></strong></td><td>原生调试</td><td><code>cli-anything-lldb</code></td><td>LLDB Python API</td>-<td align="center">✅ 27</td>+<td align="center">�?27</td></tr><tr><td align="center"><strong>🟩 <a href="nsight-graphics/agent-harness/">Nsight Graphics CLI</a></strong></td>-<td>GPU 调试与分析</td>+<td>GPU 调试与分�?/td><td><code>cli-anything-nsight-graphics</code></td><td>官方 ngfx / ngfx-capture 编排 + GPU Trace 摘要 + replay 分析</td>-<td align="center">✅ 51</td>+<td align="center">�?51</td></tr><tr><td align="center"><strong>📈 <a href="unrealinsights/agent-harness/">Unreal Insights</a></strong></td><td>性能分析</td><td><code>cli-anything-unrealinsights</code></td>-<td>后台 trace 会话 + 匹配版 UnrealInsights 构建 + 无头导出</td>-<td align="center">✅ 50</td>+<td>后台 trace 会话 + 匹配�?UnrealInsights 构建 + 无头导出</td>+<td align="center">�?50</td></tr><tr><td align="center"><strong>📦 <a href="sbox/agent-harness/">s&box</a></strong></td>-<td>游戏开发</td>+<td>游戏开�?/td><td><code>cli-anything-sbox</code></td><td>Source 2 游戏引擎 - 直接读写 .scene/.prefab/.vmat/.vsnd JSON</td>-<td align="center">✅ 244</td>+<td align="center">�?244</td></tr><tr><td align="center"><strong>🎨 Sketch</strong></td><td>UI 设计</td><td><code>sketch-cli</code></td><td>sketch-constructor (Node.js)</td>-<td align="center">✅ 19</td>+<td align="center">�?19</td></tr><tr><td align="center" colspan="4"><strong>合计</strong></td>-<td align="center"><strong>✅ 1,774</strong></td>+<td align="center"><strong>�?1,774</strong></td></tr></table>-> 全部 1,774 项测试 **100% 通过** - 1,268 项单元测试 + 487 项端到端测试 + 19 项 Node.js 测试。+> 全部 1,774 项测�?**100% 通过** - 1,268 项单元测�?+ 487 项端到端测试 + 19 �?Node.js 测试�?---## 📊 测试结果-每个 CLI 都经过多层严格测试,确保生产可用:+每个 CLI 都经过多层严格测试,确保生产可用�?-| 测试层级 | 测什么 | 示例 |+| 测试层级 | 测什�?| 示例 ||---------|-------|------|-| **单元测试** | 每个核心函数的隔离验证,使用合成数据 | `test_core.py` — 项目创建、图层操作、滤镜参数 |-| **端到端测试(原生)** | 项目文件的完整生成流程 | ODF ZIP 结构合法性、MLT XML 正确性、SVG 格式完整性 |-| **端到端测试(真实后端)** | 调用真实软件并验证输出 | LibreOffice → 含 `%PDF-` 魔术字节的 PDF,Blender → 渲染后的 PNG |-| **CLI 子进程测试** | 通过 `subprocess.run` 调用已安装命令 | `cli-anything-gimp --json project new` → 合法 JSON 输出 |+| **单元测试** | 每个核心函数的隔离验证,使用合成数据 | `test_core.py` �?项目创建、图层操作、滤镜参�?|+| **端到端测试(原生�?* | 项目文件的完整生成流�?| ODF ZIP 结构合法性、MLT XML 正确性、SVG 格式完整�?|+| **端到端测试(真实后端�?* | 调用真实软件并验证输�?| LibreOffice �?�?`%PDF-` 魔术字节�?PDF,Blender �?渲染后的 PNG |+| **CLI 子进程测�?* | 通过 `subprocess.run` 调用已安装命�?| `cli-anything-gimp --json project new` �?合法 JSON 输出 |```================================ Test Summary ================================-gimp 107 passed ✅ (64 unit + 43 e2e)-blender 208 passed ✅ (150 unit + 58 e2e)-inkscape 202 passed ✅ (148 unit + 54 e2e)-audacity 161 passed ✅ (107 unit + 54 e2e)-libreoffice 158 passed ✅ (89 unit + 69 e2e)-obs-studio 153 passed ✅ (116 unit + 37 e2e)-kdenlive 155 passed ✅ (111 unit + 44 e2e)-shotcut 154 passed ✅ (110 unit + 44 e2e)-openscreen 101 passed ✅ (78 unit + 23 e2e)-zoom 22 passed ✅ (22 unit + 0 e2e)-drawio 138 passed ✅ (116 unit + 22 e2e)-anygen 50 passed ✅ (40 unit + 10 e2e)-lldb 27 passed ✅ (23 unit + 4 e2e)-nsight-graphics 51 passed ✅ (46 unit/CLI + 5 local e2e)-unrealinsights 50 passed ✅ (49 unit + 1 e2e, 9 backend-gated e2e skipped)-sketch 19 passed ✅ (19 jest, Node.js)-joplin 112 passed ✅ (85 unit + 27 e2e, 2 skipped on Windows)+gimp 107 passed �? (64 unit + 43 e2e)+blender 208 passed �? (150 unit + 58 e2e)+inkscape 202 passed �? (148 unit + 54 e2e)+audacity 161 passed �? (107 unit + 54 e2e)+libreoffice 158 passed �? (89 unit + 69 e2e)+obs-studio 153 passed �? (116 unit + 37 e2e)+kdenlive 155 passed �? (111 unit + 44 e2e)+shotcut 154 passed �? (110 unit + 44 e2e)+openscreen 101 passed �? (78 unit + 23 e2e)+zoom 22 passed �? (22 unit + 0 e2e)+drawio 138 passed �? (116 unit + 22 e2e)+anygen 50 passed �? (40 unit + 10 e2e)+lldb 27 passed �? (23 unit + 4 e2e)+nsight-graphics 51 passed �? (46 unit/CLI + 5 local e2e)+unrealinsights 50 passed �? (49 unit + 1 e2e, 9 backend-gated e2e skipped)+sketch 19 passed �? (19 jest, Node.js)+joplin 112 passed �? (91 unit + 27 e2e, 1 skipped on Windows)──────────────────────────────────────────────────────────────────────────────-TOTAL 1,886 passed ✅ 100% pass rate+TOTAL 1,886 passed �? 100% pass rate```----## 🏗️ CLI-Anything 的架构+## 🏗�?CLI-Anything 的架�?<p align="center"><img src="assets/architecture.png" alt="CLI-Anything Architecture" width="750">@@ -692,11 +692,11 @@ TOTAL 1,886 passed ✅ 100% pass rate### 🎯 核心设计原则-1. **真实软件集成** — CLI 生成合法的项目文件(ODF、MLT XML、SVG),然后交给真实应用去渲染。**我们做的是软件的结构化接口,而不是替代品**。-2. **灵活的交互模式** — 每个 CLI 都支持两种模式:有状态的 REPL 用于 Agent 交互会话,子命令模式用于脚本和流水线。**直接运行命令即进入 REPL**。-3. **一致的使用体验** — 所有生成的 CLI 共享统一的 REPL 界面(repl_skin.py),带有品牌横幅、风格化提示符、命令历史、进度指示器和标准化格式。-4. **Agent 原生设计** — 每个命令内置 `--json` 参数,输出结构化数据供 Agent 消费,同时可读的表格格式服务于交互调试。**Agent 通过标准的 `--help` 和 `which` 命令发现能力**。-5. **零妥协的依赖策略** — 真实软件是硬性要求 —— 没有兜底,没有降级。**后端缺失时测试直接失败(而非跳过),确保功能的真实性**。+1. **真实软件集成** �?CLI 生成合法的项目文件(ODF、MLT XML、SVG),然后交给真实应用去渲染�?*我们做的是软件的结构化接口,而不是替代品**�?+2. **灵活的交互模�?* �?每个 CLI 都支持两种模式:有状态的 REPL 用于 Agent 交互会话,子命令模式用于脚本和流水线�?*直接运行命令即进�?REPL**�?+3. **一致的使用体验** �?所有生成的 CLI 共享统一�?REPL 界面(repl_skin.py),带有品牌横幅、风格化提示符、命令历史、进度指示器和标准化格式�?+4. **Agent 原生设计** �?每个命令内置 `--json` 参数,输出结构化数据�?Agent 消费,同时可读的表格格式服务于交互调试�?*Agent 通过标准�?`--help` �?`which` 命令发现能力**�?+5. **零妥协的依赖策略** �?真实软件是硬性要�?—�?没有兜底,没有降级�?*后端缺失时测试直接失败(而非跳过),确保功能的真实�?*�?---@@ -706,55 +706,55 @@ TOTAL 1,886 passed ✅ 100% pass ratecli-anything/├── 📄 README.md # 英文文档├── 📄 README_CN.md # 中文文档(你在这里)-├── 📁 assets/ # 图片和媒体文件-│ ├── icon.png # 项目图标-│ └── teaser.png # 概览图-│+├── 📁 assets/ # 图片和媒体文�?+�? ├── icon.png # 项目图标+�? └── teaser.png # 概览�?+�?├── 🔌 cli-anything-plugin/ # Claude Code 插件-│ ├── HARNESS.md # 方法论 SOP(唯一权威来源)-│ ├── README.md # 插件文档-│ ├── QUICKSTART.md # 5 分钟快速上手-│ ├── PUBLISHING.md # 分发与发布指南-│ ├── repl_skin.py # 统一 REPL 界面-│ ├── commands/ # 插件命令定义-│ │ ├── cli-anything.md # 主构建命令-│ │ ├── refine.md # 扩展已有 harness 覆盖面-│ │ ├── test.md # 测试运行器-│ │ ├── validate.md # 标准验证-│ │ └── list.md # 列出所有 CLI 工具-│ └── scripts/-│ └── setup-cli-anything.sh # 安装脚本-│+�? ├── HARNESS.md # 方法�?SOP(唯一权威来源�?+�? ├── README.md # 插件文档+�? ├── QUICKSTART.md # 5 分钟快速上�?+�? ├── PUBLISHING.md # 分发与发布指�?+�? ├── repl_skin.py # 统一 REPL 界面+�? ├── commands/ # 插件命令定义+�? �? ├── cli-anything.md # 主构建命�?+�? �? ├── refine.md # 扩展已有 harness 覆盖�?+�? �? ├── test.md # 测试运行�?+�? �? ├── validate.md # 标准验证+�? �? └── list.md # 列出所�?CLI 工具+�? └── scripts/+�? └── setup-cli-anything.sh # 安装脚本+�?├── 📋 opencode-commands/ # OpenCode 命令-│ ├── cli-anything.md # 主构建命令-│ ├── cli-anything-refine.md # 优化扩展命令-│ ├── cli-anything-test.md # 测试运行器-│ ├── cli-anything-validate.md # 标准验证-│ └── cli-anything-list.md # 列出所有 CLI 工具-│-├── 🤖 codex-skill/ # Codex skill 接入层-├── 🎨 gimp/agent-harness/ # GIMP CLI(107 项测试)-├── 🧊 blender/agent-harness/ # Blender CLI(208 项测试)-├── ✏️ inkscape/agent-harness/ # Inkscape CLI(202 项测试)-├── 🎵 audacity/agent-harness/ # Audacity CLI(161 项测试)-├── 📄 libreoffice/agent-harness/ # LibreOffice CLI(158 项测试)-├── 📚 zotero/agent-harness/ # Zotero CLI(新增,支持文献导入)-├── 📓 joplin/agent-harness/ # Joplin CLI(112 项测试,新增)-├── 📹 obs-studio/agent-harness/ # OBS Studio CLI(153 项测试)-├── 🎞️ kdenlive/agent-harness/ # Kdenlive CLI(155 项测试)-├── 🎬 shotcut/agent-harness/ # Shotcut CLI(154 项测试)-├── 🎬 openscreen/agent-harness/ # Openscreen CLI — 屏幕录像编辑器(101 项测试)-├── 📞 zoom/agent-harness/ # Zoom CLI(22 项测试)-├── 📐 drawio/agent-harness/ # Draw.io CLI(138 项测试)-├── ✨ anygen/agent-harness/ # AnyGen CLI(50 项测试)-├── 🟩 nsight-graphics/agent-harness/ # Nsight Graphics CLI(51 项测试)-├── 🐞 lldb/agent-harness/ # LLDB CLI(27 项测试)-├── 📈 unrealinsights/agent-harness/ # Unreal Insights CLI(50 项测试)-├── 📦 sbox/agent-harness/ # s&box CLI(244 项测试: 157 单元 + 17 orchestrator + 50 e2e + 20 exit-code)-└── 🎨 sketch/agent-harness/ # Sketch CLI(19 项测试,Node.js)+�? ├── cli-anything.md # 主构建命�?+�? ├── cli-anything-refine.md # 优化扩展命令+�? ├── cli-anything-test.md # 测试运行�?+�? ├── cli-anything-validate.md # 标准验证+�? └── cli-anything-list.md # 列出所�?CLI 工具+�?+├── 🤖 codex-skill/ # Codex skill 接入�?+├── 🎨 gimp/agent-harness/ # GIMP CLI�?07 项测试)+├── 🧊 blender/agent-harness/ # Blender CLI�?08 项测试)+├── ✏️ inkscape/agent-harness/ # Inkscape CLI�?02 项测试)+├── 🎵 audacity/agent-harness/ # Audacity CLI�?61 项测试)+├── 📄 libreoffice/agent-harness/ # LibreOffice CLI�?58 项测试)+├── 📚 zotero/agent-harness/ # Zotero CLI(新增,支持文献导入�?+├── 📓 joplin/agent-harness/ # Joplin CLI�?12 项测试,新增�?+├── 📹 obs-studio/agent-harness/ # OBS Studio CLI�?53 项测试)+├── 🎞�?kdenlive/agent-harness/ # Kdenlive CLI�?55 项测试)+├── 🎬 shotcut/agent-harness/ # Shotcut CLI�?54 项测试)+├── 🎬 openscreen/agent-harness/ # Openscreen CLI �?屏幕录像编辑器(101 项测试)+├── 📞 zoom/agent-harness/ # Zoom CLI�?2 项测试)+├── 📐 drawio/agent-harness/ # Draw.io CLI�?38 项测试)+├── �?anygen/agent-harness/ # AnyGen CLI�?0 项测试)+├── 🟩 nsight-graphics/agent-harness/ # Nsight Graphics CLI�?1 项测试)+├── 🐞 lldb/agent-harness/ # LLDB CLI�?7 项测试)+├── 📈 unrealinsights/agent-harness/ # Unreal Insights CLI�?0 项测试)+├── 📦 sbox/agent-harness/ # s&box CLI�?44 项测�? 157 单元 + 17 orchestrator + 50 e2e + 20 exit-code�?+└── 🎨 sketch/agent-harness/ # Sketch CLI�?9 项测试,Node.js�?```-每个 `agent-harness/` 包含一个可安装的 Python 包,位于 `cli_anything.<软件名>/` 下,包含 Click CLI、核心模块、工具类(含 `repl_skin.py` 和后端适配器)以及完整的测试。+每个 `agent-harness/` 包含一个可安装�?Python 包,位于 `cli_anything.<软件�?/` 下,包含 Click CLI、核心模块、工具类(含 `repl_skin.py` 和后端适配器)以及完整的测试�?---@@ -762,11 +762,11 @@ cli-anything/| 命令 | 说明 ||-----|------|-| `/cli-anything <软件路径或仓库>` | 构建完整的 CLI —— 全部 7 个阶段 |-| `/cli-anything:refine <软件路径> [聚焦方向]` | 优化已有的 CLI —— 通过差距分析扩展覆盖面 |-| `/cli-anything:test <软件路径或仓库>` | 运行测试并更新 TEST.md |-| `/cli-anything:validate <软件路径或仓库>` | 按照 HARNESS.md 标准进行验证 |-| `/cli-anything:list` | 列出所有已安装和已生成的 CLI 工具 |+| `/cli-anything <软件路径或仓�?` | 构建完整�?CLI —�?全部 7 个阶�?|+| `/cli-anything:refine <软件路径> [聚焦方向]` | 优化已有�?CLI —�?通过差距分析扩展覆盖�?|+| `/cli-anything:test <软件路径或仓�?` | 运行测试并更�?TEST.md |+| `/cli-anything:validate <软件路径或仓�?` | 按照 HARNESS.md 标准进行验证 |+| `/cli-anything:list` | 列出所有已安装和已生成�?CLI 工具 |### 使用示例@@ -774,16 +774,16 @@ cli-anything/# 从本地源码为 GIMP 构建完整 CLI/cli-anything /home/user/gimp-# 从 GitHub 仓库构建+# �?GitHub 仓库构建/cli-anything https://github.com/blender/blender-# 优化已有的 CLI —— 全面差距分析+# 优化已有�?CLI —�?全面差距分析/cli-anything:refine /home/user/gimp# 带聚焦方向的优化/cli-anything:refine /home/user/shotcut "画中画和视频叠加合成"-# 运行测试并更新 TEST.md+# 运行测试并更�?TEST.md/cli-anything:test /home/user/inkscape# 按照 HARNESS.md 标准验证@@ -794,25 +794,25 @@ cli-anything/## 🎮 实际操作演示-以 `cli-anything-libreoffice` 为例,看看 Agent 能做什么:+�?`cli-anything-libreoffice` 为例,看�?Agent 能做什么:```bash-# 创建一个 Writer 文档+# 创建一�?Writer 文档$ cli-anything-libreoffice document new -o report.json --type writer-✓ Created Writer document: report.json+�?Created Writer document: report.json# 添加内容$ cli-anything-libreoffice --project report.json writer add-heading -t "Q1 Report" --level 1-✓ Added heading: "Q1 Report"+�?Added heading: "Q1 Report"$ cli-anything-libreoffice --project report.json writer add-table --rows 4 --cols 3-✓ Added 4×3 table+�?Added 4×3 table-# 通过 LibreOffice headless 导出为真实 PDF+# 通过 LibreOffice headless 导出为真�?PDF$ cli-anything-libreoffice --project report.json export render output.pdf -p pdf --overwrite-✓ Exported: output.pdf (42,831 bytes) via libreoffice-headless+�?Exported: output.pdf (42,831 bytes) via libreoffice-headless-# JSON 模式供 Agent 消费+# JSON 模式�?Agent 消费$ cli-anything-libreoffice --json document info --project report.json{"name": "Q1 Report",@@ -828,18 +828,18 @@ $ cli-anything-libreoffice --json document info --project report.json```$ cli-anything-blender╔══════════════════════════════════════════╗-║ cli-anything-blender v1.0.0 ║-║ Blender CLI for AI Agents ║+�? cli-anything-blender v1.0.0 �?+�? Blender CLI for AI Agents �?╚══════════════════════════════════════════╝blender> scene new --name ProductShot-✓ Created scene: ProductShot+�?Created scene: ProductShotblender[ProductShot]> object add-mesh --type cube --location 0 0 1-✓ Added mesh: Cube at (0, 0, 1)+�?Added mesh: Cube at (0, 0, 1)blender[ProductShot]*> render execute --output render.png --engine CYCLES-✓ Rendered: render.png (1920×1080, 2.3 MB) via blender --background+�?Rendered: render.png (1920×1080, 2.3 MB) via blender --backgroundblender[ProductShot]> exitGoodbye! 👋@@ -849,37 +849,37 @@ Goodbye! 👋## 📖 标准手册:HARNESS.md-HARNESS.md 是我们通过自动化 CLI 生成,使任意软件具备 Agent 可用性的权威标准操作流程(SOP)。+HARNESS.md 是我们通过自动�?CLI 生成,使任意软件具备 Agent 可用性的权威标准操作流程(SOP)�?-它记录了在自动化生成过程中经验证并沉淀出的模式与方法论。+它记录了在自动化生成过程中经验证并沉淀出的模式与方法论�?-这本手册提炼了成功构建全部 13 套生产级 CLI 的关键经验。+这本手册提炼了成功构建全�?13 套生产级 CLI 的关键经验�?### 核心经验| 经验 | 说明 ||-----|------|-| **必须用真实软件** | CLI 必须调用真实应用进行渲染。不能用 Pillow 替代 GIMP,不能自己写渲染器替代 Blender。正确做法:生成合法的项目文件 → 调用真实后端。 |-| **渲染鸿沟** | GUI 应用在渲染时才应用特效。如果你的 CLI 操作了项目文件但用了简陋的导出工具,特效会被静默丢弃。正确做法:原生渲染器 → 滤镜转译 → 渲染脚本。 |-| **滤镜转译** | 在不同格式间映射特效时(如 MLT → ffmpeg),要注意:重复滤镜合并、交错的流排序、参数空间差异、无法映射的特效。 |-| **时间码精度** | 非整数帧率(如 29.97fps)会导致累积舍入误差。用 `round()` 而非 `int()`,显示时用整数运算,测试中允许 ±1 帧容差。 |-| **输出验证** | 永远不要因为进程退出码为 0 就信任导出成功。要验证:魔术字节、ZIP/OOXML 结构、像素分析、音频 RMS 电平、时长检查。 |+| **必须用真实软�?* | CLI 必须调用真实应用进行渲染。不能用 Pillow 替代 GIMP,不能自己写渲染器替�?Blender。正确做法:生成合法的项目文�?�?调用真实后端�?|+| **渲染鸿沟** | GUI 应用在渲染时才应用特效。如果你�?CLI 操作了项目文件但用了简陋的导出工具,特效会被静默丢弃。正确做法:原生渲染�?�?滤镜转译 �?渲染脚本�?|+| **滤镜转译** | 在不同格式间映射特效时(�?MLT �?ffmpeg),要注意:重复滤镜合并、交错的流排序、参数空间差异、无法映射的特效�?|+| **时间码精�?* | 非整数帧率(�?29.97fps)会导致累积舍入误差。用 `round()` 而非 `int()`,显示时用整数运算,测试中允�?±1 帧容差�?|+| **输出验证** | 永远不要因为进程退出码�?0 就信任导出成功。要验证:魔术字节、ZIP/OOXML 结构、像素分析、音�?RMS 电平、时长检查�?|> 完整方法论见:[`cli-anything-plugin/HARNESS.md`](cli-anything-plugin/HARNESS.md)----## 📦 安装与使用+## 📦 安装与使�?### Claude Code 用户```bash-# 添加市场并安装(推荐)+# 添加市场并安装(推荐�?/plugin marketplace add HKUDS/CLI-Anything/plugin install cli-anything# 为任何有代码库的软件生成 CLI-/cli-anything:cli-anything <软件路径或仓库>+/cli-anything:cli-anything <软件路径或仓�?```### OpenCode 用户@@ -888,58 +888,58 @@ HARNESS.md 是我们通过自动化 CLI 生成,使任意软件具备 Agent 可# 克隆仓库git clone https://github.com/HKUDS/CLI-Anything.git-# 请确保使用最新 OpenCode,旧版本可能使用不同的命令目录路径-# 复制命令和 HARNESS.md 到 OpenCode 命令目录+# 请确保使用最�?OpenCode,旧版本可能使用不同的命令目录路�?+# 复制命令�?HARNESS.md �?OpenCode 命令目录cp CLI-Anything/opencode-commands/*.md ~/.config/opencode/commands/cp CLI-Anything/cli-anything-plugin/HARNESS.md ~/.config/opencode/commands/# 为任何有代码库的软件生成 CLI-/cli-anything <软件路径或仓库>+/cli-anything <软件路径或仓�?```-### 使用生成的 CLI+### 使用生成�?CLI```bash-# 安装任意生成的 CLI-cd <软件名>/agent-harness+# 安装任意生成�?CLI+cd <软件�?/agent-harnesspip install -e .# 验证安装-which cli-anything-<软件名>+which cli-anything-<软件�?-# 开始使用-cli-anything-<软件名> --help-cli-anything-<软件名> # 进入 REPL-cli-anything-<软件名> --json <命令> # JSON 输出供 Agent 使用+# 开始使�?+cli-anything-<软件�? --help+cli-anything-<软件�? # 进入 REPL+cli-anything-<软件�? --json <命令> # JSON 输出�?Agent 使用```### 运行测试```bash-# 运行某个 CLI 的测试-cd <软件名>/agent-harness-python3 -m pytest cli_anything/<软件名>/tests/ -v+# 运行某个 CLI 的测�?+cd <软件�?/agent-harness+python3 -m pytest cli_anything/<软件�?/tests/ -v# 强制安装模式(推荐用于验证)-CLI_ANYTHING_FORCE_INSTALLED=1 python3 -m pytest cli_anything/<软件名>/tests/ -v -s+CLI_ANYTHING_FORCE_INSTALLED=1 python3 -m pytest cli_anything/<软件�?/tests/ -v -s```---## 🤝 参与贡献-欢迎贡献!CLI-Anything 天然支持扩展:+欢迎贡献!CLI-Anything 天然支持扩展�?-- **新的目标软件** — 用插件为任意有代码库的软件生成 CLI,然后通过 [`cli-anything-plugin/PUBLISHING.md`](cli-anything-plugin/PUBLISHING.md) 提交你的成果。-- **方法论改进** — 向 `HARNESS.md` 提 PR,把新的经验教训沉淀下来-- **插件增强** — 新命令、阶段优化、更好的验证逻辑-- **测试覆盖** — 更多端到端场景、边界情况、工作流测试+- **新的目标软件** �?用插件为任意有代码库的软件生�?CLI,然后通过 [`cli-anything-plugin/PUBLISHING.md`](cli-anything-plugin/PUBLISHING.md) 提交你的成果�?+- **方法论改�?* �?�?`HARNESS.md` �?PR,把新的经验教训沉淀下来+- **插件增强** �?新命令、阶段优化、更好的验证逻辑+- **测试覆盖** �?更多端到端场景、边界情况、工作流测试-### 已知局限+### 已知局�?-- **依赖强大的基础模型** — CLI-Anything 依赖前沿级别的模型(如 Claude Opus 4.6、Claude Sonnet 4.6、GPT-5.4)才能可靠地生成 harness。较弱或较小的模型可能产出不完整或有误的 CLI,需要大量人工修正。-- **依赖可用的源代码** — `/cli-anything` 基于源码进行分析和生成。如果目标软件只提供编译后的二进制文件,需要反编译才能获取代码,harness 的质量和覆盖率会显著下降。-- **可能需要迭代优化** — 单次 `/cli-anything` 运行不一定能完整覆盖所有功能。通常需要执行一次或多次 `/refine` 命令,才能将 CLI 的性能和覆盖率推到生产级水平。+- **依赖强大的基础模型** �?CLI-Anything 依赖前沿级别的模型(�?Claude Opus 4.6、Claude Sonnet 4.6、GPT-5.4)才能可靠地生成 harness。较弱或较小的模型可能产出不完整或有误的 CLI,需要大量人工修正�?+- **依赖可用的源代码** �?`/cli-anything` 基于源码进行分析和生成。如果目标软件只提供编译后的二进制文件,需要反编译才能获取代码,harness 的质量和覆盖率会显著下降�?+- **可能需要迭代优�?* �?单次 `/cli-anything` 运行不一定能完整覆盖所有功能。通常需要执行一次或多次 `/refine` 命令,才能将 CLI 的性能和覆盖率推到生产级水平�?---@@ -947,21 +947,21 @@ CLI_ANYTHING_FORCE_INSTALLED=1 python3 -m pytest cli_anything/<软件名>/tests/| 文档 | 说明 ||-----|------|-| [`cli-anything-plugin/HARNESS.md`](cli-anything-plugin/HARNESS.md) | 方法论 SOP — 唯一权威来源 |-| [`cli-anything-plugin/README.md`](cli-anything-plugin/README.md) | 插件文档 — 命令、选项、阶段 |-| [`cli-anything-plugin/QUICKSTART.md`](cli-anything-plugin/QUICKSTART.md) | 5 分钟快速上手 |-| [`cli-anything-plugin/PUBLISHING.md`](cli-anything-plugin/PUBLISHING.md) | 分发与发布指南 |+| [`cli-anything-plugin/HARNESS.md`](cli-anything-plugin/HARNESS.md) | 方法�?SOP �?唯一权威来源 |+| [`cli-anything-plugin/README.md`](cli-anything-plugin/README.md) | 插件文档 �?命令、选项、阶�?|+| [`cli-anything-plugin/QUICKSTART.md`](cli-anything-plugin/QUICKSTART.md) | 5 分钟快速上�?|+| [`cli-anything-plugin/PUBLISHING.md`](cli-anything-plugin/PUBLISHING.md) | 分发与发布指�?|-每个生成的 CLI 还包含:+每个生成�?CLI 还包含:-- `<软件名>.md` — 该应用的架构 SOP-- `tests/TEST.md` — 测试计划和结果文档+- `<软件�?.md` �?该应用的架构 SOP+- `tests/TEST.md` �?测试计划和结果文�?----## ⭐ Star History+## �?Star History-如果 CLI-Anything 帮到了你,给个 Star 吧!⭐+如果 CLI-Anything 帮到了你,给�?Star 吧!�?<!-- Uncomment when published:<div align="center">@@ -979,15 +979,15 @@ CLI_ANYTHING_FORCE_INSTALLED=1 python3 -m pytest cli_anything/<软件名>/tests/## 📄 License-Apache License 2.0 — 可自由使用、修改和分发。+Apache License 2.0 �?可自由使用、修改和分发�?---<div align="center">-**CLI-Anything** — *一行命令,让任何软件成为 Agent 的原生工具。*+**CLI-Anything** �?*一行命令,让任何软件成�?Agent 的原生工具�?-<sub>为 AI Agent 时代而生 | 13 款专业软件实测 | 1,774 项测试全部通过</sub>+<sub>�?AI Agent 时代而生 | 13 款专业软件实�?| 1,774 项测试全部通过</sub><br>@@ -996,6 +996,6 @@ Apache License 2.0 — 可自由使用、修改和分发。</div><p align="center">- <em>感谢访问 ✨ CLI-Anything!</em><br><br>+ <em>感谢访问 �?CLI-Anything�?/em><br><br><img src="https://visitor-badge.laobi.icu/badge?page_id=HKUDS.CLI-Anything&style=for-the-badge&color=00d4ff" alt="Views"></p>diff --git a/README_JA.md b/README_JA.mdindex 9fd0aa518..4fea932d7 100644--- a/README_JA.md+++ b/README_JA.md@@ -1,22 +1,22 @@-<h1 align="center"><img src="assets/icon.png" alt="" width="64" style="vertical-align: middle;"> CLI-Anything: すべてのソフトウェアをエージェントネイティブに</h1>+<h1 align="center"><img src="assets/icon.png" alt="" width="64" style="vertical-align: middle;"> CLI-Anything: すべてのソフトウェアをエージェントネイティブ�?/h1><p align="center">- <strong>今日のソフトウェアは人間👨💻のためのもの。明日のユーザーはエージェント🤖。<br>+ <strong>今日のソフトウェアは人間👨💻のためのもの。明日のユーザーはエージェント🤖�?br>CLI-Anything: AIエージェントと世界のソフトウェアの架け橋</strong><br></p>-**🌐 [CLI-Hub](https://hkuds.github.io/CLI-Anything/)**: コミュニティが構築した全CLIを **[CLI-Hub](https://hkuds.github.io/CLI-Anything/)** で探索、ワンコマンドでインストール。自分のCLIを追加したい?[PRを送信](https://github.com/HKUDS/CLI-Anything/blob/main/CONTRIBUTING.md) — Hubは即座に更新されます。+**🌐 [CLI-Hub](https://hkuds.github.io/CLI-Anything/)**: コミュニティが構築した全CLI�?**[CLI-Hub](https://hkuds.github.io/CLI-Anything/)** で探索、ワンコマンドでインストール。自分のCLIを追加したい?[PRを送信](https://github.com/HKUDS/CLI-Anything/blob/main/CONTRIBUTING.md) �?Hubは即座に更新されます�?<p align="center"><a href="#-クイックスタート"><img src="https://img.shields.io/badge/Quick_Start-5_min-blue?style=for-the-badge" alt="クイックスタート"></a><a href="#-デモンストレーション"><img src="https://img.shields.io/badge/Demos-12_Apps-green?style=for-the-badge" alt="デモ"></a>- <a href="#-テスト結果"><img src="https://img.shields.io/badge/Tests-1%2C540_Passing-brightgreen?style=for-the-badge" alt="テスト"></a>- <a href="LICENSE"><img src="https://img.shields.io/badge/License-Apache_2.0-yellow?style=for-the-badge" alt="ライセンス"></a>+ <a href="#-テスト結�?><img src="https://img.shields.io/badge/Tests-1%2C540_Passing-brightgreen?style=for-the-badge" alt="テス�?></a>+ <a href="LICENSE"><img src="https://img.shields.io/badge/License-Apache_2.0-yellow?style=for-the-badge" alt="ライセン�?></a></p><p align="center">- <img src="https://img.shields.io/badge/python-≥3.10-blue?logo=python&logoColor=white" alt="Python">- <img src="https://img.shields.io/badge/click-≥8.0-green" alt="Click">+ <img src="https://img.shields.io/badge/python-�?.10-blue?logo=python&logoColor=white" alt="Python">+ <img src="https://img.shields.io/badge/click-�?.0-green" alt="Click"><img src="https://img.shields.io/badge/pytest-100%25_pass-brightgreen" alt="Pytest"><img src="https://img.shields.io/badge/coverage-unit_%2B_e2e-orange" alt="Coverage"><img src="https://img.shields.io/badge/output-JSON_%2B_Human-blueviolet" alt="Output">@@ -24,33 +24,33 @@ CLI-Anything: AIエージェントと世界のソフトウェアの架け橋</st<a href="https://github.com/HKUDS/.github/blob/main/profile/README.md"><img src="https://img.shields.io/badge/WeChat-Group-C5EAB4?style=flat&logo=wechat&logoColor=white" alt="WeChat"></a></p>-**ワンコマンド**: あらゆるソフトウェアをOpenClaw、nanobot、Cursor、Claude Codeなどのエージェント対応に。 [**English**](README.md) | [**中文文档**](README_CN.md)+**ワンコマンド**: あらゆるソフトウェアをOpenClaw、nanobot、Cursor、Claude Codeなどのエージェント対応に�?nbsp; [**English**](README.md) | [**中文文档**](README_CN.md)<p align="center">- <img src="assets/cli-typing.gif" alt="CLI-Anything タイピングデモ" width="800">+ <img src="assets/cli-typing.gif" alt="CLI-Anything タイピングデ�? width="800"></p><p align="center">- <img src="assets/teaser.png" alt="CLI-Anything ティーザー" width="800">+ <img src="assets/teaser.png" alt="CLI-Anything ティーザ�? width="800"></p>---## 🤔 なぜCLIなのか?-CLIは人間とAIエージェント両方にとって普遍的なインターフェースです:+CLIは人間とAIエージェント両方にとって普遍的なインターフェースです�?-• **構造化 & 組み合わせ可能** - テキストコマンドはLLMのフォーマットに適合し、複雑なワークフローのために連鎖可能+�?**構造化 & 組み合わせ可�?* - テキストコマンドはLLMのフォーマットに適合し、複雑なワークフローのために連鎖可能-• **軽量 & 汎用的** - 最小限のオーバーヘッドで、依存関係なくすべてのシステムで動作+�?**軽量 & 汎用�?* - 最小限のオーバーヘッドで、依存関係なくすべてのシステムで動作-• **自己記述的** - --helpフラグがエージェントが発見できる自動ドキュメントを提供+�?**自己記述�?* - --helpフラグがエージェントが発見できる自動ドキュメントを提�?-• **実証済みの成功** - Claude Codeは毎日何千もの実際のワークフローをCLIを通じて実行+�?**実証済みの成�?* - Claude Codeは毎日何千もの実際のワークフローをCLIを通じて実�?-• **エージェントファースト設計** - 構造化されたJSON出力がパース処理の複雑さを排除+�?**エージェントファースト設�?* - 構造化されたJSON出力がパース処理の複雑さを排�?-• **決定論的 & 信頼性** - 一貫した結果が予測可能なエージェントの動作を実現+�?**決定論的 & 信頼�?* - 一貫した結果が予測可能なエージェントの動作を実�?## 🚀 クイックスタート@@ -60,14 +60,14 @@ CLIは人間とAIエージェント両方にとって普遍的なインターフ- 対象ソフトウェアがインストール済みであること(例:GIMP、Blender、LibreOffice、または独自のアプリケーション)- サポートされているAIコーディングエージェント: [Claude Code](#-claude-code) | [OpenClaw](#-openclaw) | [OpenCode](#-opencode) | [Codex](#-codex) | [Qodercli](#-qodercli) | [GitHub Copilot CLI](#-github-copilot-cli) | [その他のプラットフォーム](#-その他のプラットフォーム近日公開)-### プラットフォームを選択+### プラットフォームを選�?<details open>-<summary><h4 id="-claude-code">⚡ Claude Code</h4></summary>+<summary><h4 id="-claude-code">�?Claude Code</h4></summary>**ステップ1: マーケットプレイスの追加**-CLI-AnythingはGitHub上でホストされるClaude Codeプラグインマーケットプレイスとして配布されています。+CLI-AnythingはGitHub上でホストされるClaude Codeプラグインマーケットプレイスとして配布されています�?```bash# CLI-Anythingマーケットプレイスを追加@@ -81,40 +81,40 @@ CLI-AnythingはGitHub上でホストされるClaude Codeプラグインマーケ/plugin install cli-anything```-これで完了です。プラグインがClaude Codeセッションで利用可能になります。+これで完了です。プラグインがClaude Codeセッションで利用可能になります�?-**ステップ3: ワンコマンドでCLIを構築**+**ステップ3: ワンコマンドでCLIを構�?*```bash-# /cli-anything:cli-anything <ソフトウェアのパスまたはリポジトリ>-# GIMPの完全なCLIを生成(全7フェーズ)+# /cli-anything:cli-anything <ソフトウェアのパスまたはリポジト�?+# GIMPの完全なCLIを生成(�?フェーズ�?/cli-anything:cli-anything ./gimp-# 注: Claude Codeが2.x未満の場合は、"/cli-anything"を代わりに使用してください。+# �? Claude Code�?.x未満の場合は�?/cli-anything"を代わりに使用してください�?```これにより完全なパイプラインが実行されます:-1. 🔍 **分析** — ソースコードをスキャンし、GUIアクションをAPIにマッピング-2. 📐 **設計** — コマンドグループ、状態モデル、出力フォーマットを設計-3. 🔨 **実装** — REPL、JSON出力、アンドゥ/リドゥ機能を備えたClick CLIを構築-4. 📋 **テスト計画** — ユニットテスト + E2Eテスト計画のTEST.mdを作成-5. 🧪 **テスト作成** — 包括的なテストスイートを実装-6. 📝 **ドキュメント** — TEST.mdを結果で更新-7. 📦 **公開** — `setup.py`を作成し、PATHにインストール+1. 🔍 **分析** �?ソースコードをスキャンし、GUIアクションをAPIにマッピング+2. 📐 **設計** �?コマンドグループ、状態モデル、出力フォーマットを設計+3. 🔨 **実装** �?REPL、JSON出力、アンド�?リドゥ機能を備えたClick CLIを構�?+4. 📋 **テスト計�?* �?ユニットテス�?+ E2Eテスト計画のTEST.mdを作�?+5. 🧪 **テスト作�?* �?包括的なテストスイートを実装+6. 📝 **ドキュメント** �?TEST.mdを結果で更新+7. 📦 **公開** �?`setup.py`を作成し、PATHにインストー�?-**ステップ4(オプション): CLIの改善と拡張**+**ステップ4(オプション�? CLIの改善と拡張**-初回ビルド後、CLIを反復的に改善してカバレッジを拡大し、不足している機能を追加できます:+初回ビルド後、CLIを反復的に改善してカバレッジを拡大し、不足している機能を追加できます�?```bash-# 広範な改善 — エージェントがすべての機能のギャップを分析+# 広範な改�?�?エージェントがすべての機能のギャップを分�?/cli-anything:refine ./gimp-# 集中的な改善 — 特定の機能領域をターゲット+# 集中的な改善 �?特定の機能領域をターゲッ�?/cli-anything:refine ./gimp "画像のバッチ処理とフィルタのCLIを追加したい"```-refineコマンドは、ソフトウェアの全機能と現在のCLIカバレッジの間のギャップ分析を行い、特定されたギャップに対して新しいコマンド、テスト、ドキュメントを実装します。複数回実行してカバレッジを着実に拡大できます — 各実行はインクリメンタルで非破壊的です。+refineコマンドは、ソフトウェアの全機能と現在のCLIカバレッジの間のギャップ分析を行い、特定されたギャップに対して新しいコマンド、テスト、ドキュメントを実装します。複数回実行してカバレッジを着実に拡大できます �?各実行はインクリメンタルで非破壊的です�?<details><summary><strong>代替方法: 手動インストール</strong></summary>@@ -137,11 +137,11 @@ cp -r CLI-Anything/cli-anything-plugin ~/.claude/plugins/cli-anything</details><details>-<summary><h4 id="-opencode">⚡ OpenCode(実験的)</h4></summary>+<summary><h4 id="-opencode">�?OpenCode(実験的�?/h4></summary>-**ステップ1: コマンドのインストール**+**ステップ1: コマンドのインストー�?*-CLI-Anythingのコマンド**と** `HARNESS.md` をOpenCodeのコマンドディレクトリにコピーします:+CLI-Anythingのコマン�?*�?* `HARNESS.md` をOpenCodeのコマンドディレクトリにコピーします�?```bash# リポジトリをクローン@@ -151,34 +151,34 @@ git clone https://github.com/HKUDS/CLI-Anything.gitcp CLI-Anything/opencode-commands/*.md ~/.config/opencode/commands/cp CLI-Anything/cli-anything-plugin/HARNESS.md ~/.config/opencode/commands/-# またはプロジェクトレベルのインストール+# またはプロジェクトレベルのインストー�?cp CLI-Anything/opencode-commands/*.md .opencode/commands/cp CLI-Anything/cli-anything-plugin/HARNESS.md .opencode/commands/```-> **注:** `HARNESS.md`はすべてのコマンドが参照する方法論の仕様書です。コマンドと同じディレクトリに配置する必要があります。+> **�?** `HARNESS.md`はすべてのコマンドが参照する方法論の仕様書です。コマンドと同じディレクトリに配置する必要があります�?-これにより5つのスラッシュコマンドが追加されます: `/cli-anything`、`/cli-anything-refine`、`/cli-anything-test`、`/cli-anything-validate`、`/cli-anything-list`。+これによ�?つのスラッシュコマンドが追加されます: `/cli-anything`、`/cli-anything-refine`、`/cli-anything-test`、`/cli-anything-validate`、`/cli-anything-list`�?-**ステップ2: ワンコマンドでCLIを構築**+**ステップ2: ワンコマンドでCLIを構�?*```bash-# GIMPの完全なCLIを生成(全7フェーズ)+# GIMPの完全なCLIを生成(�?フェーズ�?/cli-anything ./gimp# GitHubリポジトリからビルド/cli-anything https://github.com/blender/blender```-コマンドはサブタスクとして実行され、Claude Codeと同じ7フェーズの方法論に従います。+コマンドはサブタスクとして実行され、Claude Codeと同�?フェーズの方法論に従います�?-**ステップ3(オプション): CLIの改善と拡張**+**ステップ3(オプション�? CLIの改善と拡張**```bash-# 広範な改善 — エージェントがすべての機能のギャップを分析+# 広範な改�?�?エージェントがすべての機能のギャップを分�?/cli-anything-refine ./gimp-# 集中的な改善 — 特定の機能領域をターゲット+# 集中的な改善 �?特定の機能領域をターゲッ�?/cli-anything-refine ./gimp "バッチ処理とフィルタ"```@@ -186,7 +186,7 @@ cp CLI-Anything/cli-anything-plugin/HARNESS.md .opencode/commands/<details>-<summary><h4 id="-qodercli">⚡ Qodercli <sup><code>コミュニティ</code></sup></h4></summary>+<summary><h4 id="-qodercli">�?Qodercli <sup><code>コミュニティ</code></sup></h4></summary>**ステップ1: プラグインの登録**@@ -195,9 +195,9 @@ git clone https://github.com/HKUDS/CLI-Anything.gitbash CLI-Anything/qoder-plugin/setup-qodercli.sh```-これにより`~/.qoder.json`にcli-anythingプラグインが登録されます。登録後、新しいQodercliセッションを開始してください。+これにより`~/.qoder.json`にcli-anythingプラグインが登録されます。登録後、新しいQodercliセッションを開始してください�?-**ステップ2: QodercliからCLI-Anythingを使用**+**ステップ2: QodercliからCLI-Anythingを使�?*```bash/cli-anything:cli-anything ./gimp@@ -208,38 +208,38 @@ bash CLI-Anything/qoder-plugin/setup-qodercli.sh<details>-<summary><h4 id="-openclaw">⚡ OpenClaw</h4></summary>+<summary><h4 id="-openclaw">�?OpenClaw</h4></summary>**ステップ1: スキルのインストール**-CLI-Anything はネイティブな OpenClaw `SKILL.md` ファイルを提供しています。OpenClaw のスキルディレクトリにコピーしてください:+CLI-Anything はネイティブ�?OpenClaw `SKILL.md` ファイルを提供しています。OpenClaw のスキルディレクトリにコピーしてください�?```bash# リポジトリをクローンgit clone https://github.com/HKUDS/CLI-Anything.git-# グローバルスキルフォルダにインストール+# グローバルスキルフォルダにインストー�?mkdir -p ~/.openclaw/skills/cli-anythingcp CLI-Anything/openclaw-skill/SKILL.md ~/.openclaw/skills/cli-anything/SKILL.md```-**ステップ2: CLIの構築**+**ステップ2: CLIの構�?*-インストール後、OpenClaw 内で以下のようにスキルを呼び出せます:+インストール後、OpenClaw 内で以下のようにスキルを呼び出せます�?`@cli-anything build a CLI for ./gimp`-このスキルは Claude Code や OpenCode と同じ7段階の方法論に従っています。+このスキルは Claude Code �?OpenCode と同�?段階の方法論に従っています�?</details><details>-<summary><h4 id="-codex">⚡ Codex <sup><code>実験的</code></sup> <sup><code>コミュニティ</code></sup></h4></summary>+<summary><h4 id="-codex">�?Codex <sup><code>実験�?/code></sup> <sup><code>コミュニティ</code></sup></h4></summary>**ステップ1: スキルのインストール**-同梱のインストーラーを実行します:+同梱のインストーラーを実行します�?```bash# リポジトリをクローン@@ -255,26 +255,26 @@ Windows PowerShellの場合:.\CLI-Anything\codex-skill\scripts\install.ps1```-これにより`$CODEX_HOME/skills/cli-anything`(`CODEX_HOME`が未設定の場合は`~/.codex/skills/cli-anything`)にスキルがインストールされます。+これにより`$CODEX_HOME/skills/cli-anything`(`CODEX_HOME`が未設定の場合は`~/.codex/skills/cli-anything`)にスキルがインストールされます�?-インストール後、検出されるようにCodexを再起動してください。+インストール後、検出されるようにCodexを再起動してください�?-**ステップ2: CodexからCLI-Anythingを使用**+**ステップ2: CodexからCLI-Anythingを使�?*-自然言語でタスクを説明します。例:+自然言語でタスクを説明します。例�?```textCLI-Anythingを使って./gimpのハーネスを構築してCLI-Anythingを使って./shotcutのピクチャーインピクチャーワークフローを改善して-CLI-Anythingを使って./libreofficeを検証して+CLI-Anythingを使って./libreofficeを検証し�?```-CodexスキルはClaude CodeプラグインおよびOpenCodeコマンドと同じ方法論を適用しつつ、生成されるPythonハーネスのフォーマットは変更されません。+CodexスキルはClaude CodeプラグインおよびOpenCodeコマンドと同じ方法論を適用しつつ、生成されるPythonハーネスのフォーマットは変更されません�?</details><details>-<summary><h4 id="-github-copilot-cli">⚡ GitHub Copilot CLI <sup><code>コミュニティ</code></sup></h4></summary>+<summary><h4 id="-github-copilot-cli">�?GitHub Copilot CLI <sup><code>コミュニティ</code></sup></h4></summary>**ステップ1: プラグインのインストール**@@ -284,9 +284,9 @@ cd CLI-Anythingcopilot plugin install ./cli-anything-plugin```-これにより、CLI-Anything プラグインが GitHub Copilot CLI にインストールされます。プラグインはすでに GitHub Copilot CLI セッションで利用できるはずです。+これにより、CLI-Anything プラグインが GitHub Copilot CLI にインストールされます。プラグインはすでに GitHub Copilot CLI セッションで利用できるはずです�?-**ステップ2: GitHub Copilot CLIからCLI-Anythingを使用**+**ステップ2: GitHub Copilot CLIからCLI-Anythingを使�?*```bash/cli-anything:cli-anything ./gimp@@ -301,19 +301,19 @@ copilot plugin install ./cli-anything-pluginCLI-Anythingはプラットフォーム非依存で設計されています。より多くのAIコーディングエージェントのサポートを予定しています:-- **Codex** — `codex-skill/` 内の同梱スキルで利用可能-- **Cursor** — 近日公開-- **Windsurf** — 近日公開-- **お好みのツール** — コントリビューション歓迎!リファレンス実装については`opencode-commands/`ディレクトリをご覧ください。+- **Codex** �?`codex-skill/` 内の同梱スキルで利用可能+- **Cursor** �?近日公開+- **Windsurf** �?近日公開+- **お好みのツー�?* �?コントリビューション歓迎!リファレンス実装については`opencode-commands/`ディレクトリをご覧ください�?</details>-### 生成されたCLIの使用+### 生成されたCLIの使�?どのプラットフォームでビルドしても、生成されたCLIは同じ方法で動作します:```bash-# PATHにインストール+# PATHにインストー�?cd gimp/agent-harness && pip install -e .# どこからでも使用可能@@ -321,79 +321,79 @@ cli-anything-gimp --helpcli-anything-gimp project new --width 1920 --height 1080 -o poster.jsoncli-anything-gimp --json layer add -n "Background" --type solid --color "#1a1a2e"-# インタラクティブREPLに入る+# インタラクティブREPLに入�?cli-anything-gimp```----## 💡 CLI-Anythingのビジョン: エージェントネイティブソフトウェアの構築+## 💡 CLI-Anythingのビジョ�? エージェントネイティブソフトウェアの構築-• 🌐 **ユニバーサルアクセス** - すべてのソフトウェアが構造化されたCLIを通じて即座にエージェント制御可能に。+�?🌐 **ユニバーサルアクセス** - すべてのソフトウェアが構造化されたCLIを通じて即座にエージェント制御可能に�?-• 🔗 **シームレスな統合** - エージェントがAPI、GUI、再構築、複雑なラッパーなしにあらゆるアプリケーションを制御。+�?🔗 **シームレスな統合** - エージェントがAPI、GUI、再構築、複雑なラッパーなしにあらゆるアプリケーションを制御�?-• 🚀 **未来志向のエコシステム** - ワンコマンドで人間向けに設計されたソフトウェアをエージェントネイティブツールに変換。+�?🚀 **未来志向のエコシステ�?* - ワンコマンドで人間向けに設計されたソフトウェアをエージェントネイティブツールに変換�?---## 🔧 CLI-Anythingの活用シーン-| カテゴリ | エージェントネイティブにする方法 | 代表例 |+| カテゴリ | エージェントネイティブにする方法 | 代表�?||----------|----------------------|----------|-| **📂 GitHubリポジトリ** | あらゆるオープンソースプロジェクトを自動CLI生成でエージェント制御可能なツールに変換 | VSCodium, WordPress, Calibre, Zotero, Joplin, Logseq, Penpot, Super Productivity |+| **📂 GitHubリポジト�?* | あらゆるオープンソースプロジェクトを自動CLI生成でエージェント制御可能なツールに変換 | VSCodium, WordPress, Calibre, Zotero, Joplin, Logseq, Penpot, Super Productivity || **🤖 AI/MLプラットフォーム** | 構造化されたコマンドでモデルの訓練、推論パイプライン、ハイパーパラメータチューニングを自動化 | Stable Diffusion WebUI, ComfyUI, InvokeAI, Text-generation-webui, Open WebUI, Fooocus, Kohya_ss, AnythingLLM, SillyTavern |-| **📊 データ & アナリティクス** | プログラマティックなデータ処理、可視化、統計分析ワークフローを実現 | JupyterLab, Apache Superset, Metabase, Redash, DBeaver, KNIME, Orange, OpenSearch Dashboards, Lightdash |-| **💻 開発ツール** | コマンドインターフェースでコード編集、ビルド、テスト、デプロイプロセスを効率化 | Jenkins, Gitea, Hoppscotch, Portainer, pgAdmin, SonarQube, ArgoCD, OpenLens, Insomnia, Beekeeper Studio |-| **🎨 クリエイティブ & メディア** | コンテンツ作成、編集、レンダリングワークフローをプログラムで制御 | Blender, GIMP, OBS Studio, Audacity, Krita, Kdenlive, Shotcut, Inkscape, Darktable, LMMS, Ardour |+| **📊 デー�?& アナリティク�?* | プログラマティックなデータ処理、可視化、統計分析ワークフローを実現 | JupyterLab, Apache Superset, Metabase, Redash, DBeaver, KNIME, Orange, OpenSearch Dashboards, Lightdash |+| **💻 開発ツー�?* | コマンドインターフェースでコード編集、ビルド、テスト、デプロイプロセスを効率�?| Jenkins, Gitea, Hoppscotch, Portainer, pgAdmin, SonarQube, ArgoCD, OpenLens, Insomnia, Beekeeper Studio |+| **🎨 クリエイティ�?& メディア** | コンテンツ作成、編集、レンダリングワークフローをプログラムで制御 | Blender, GIMP, OBS Studio, Audacity, Krita, Kdenlive, Shotcut, Inkscape, Darktable, LMMS, Ardour || **🔬 科学計算** | 研究ワークフロー、シミュレーション、複雑な計算を自動化 | ImageJ, FreeCAD, QGIS, ParaView, Gephi, LibreCAD, Stellarium, KiCad, JASP, Jamovi || **🏢 エンタープライズ & オフィス** | ビジネスアプリケーションと生産性ツールをエージェントがアクセス可能なシステムに変換 | NextCloud, GitLab, Grafana, Mattermost, LibreOffice, AppFlowy, NocoDB, Odoo (Community), Plane, ERPNext |-| **📞 コミュニケーション & コラボレーション** | 構造化されたCLIで会議のスケジュール、参加者管理、録画取得、レポートを自動化 | Zoom, Jitsi Meet, BigBlueButton, Mattermost |-| **📐 ダイアグラム & ビジュアライゼーション** | ダイアグラム、フローチャート、アーキテクチャ図、ビジュアルドキュメントをプログラムで作成・操作 | Draw.io (diagrams.net), Mermaid, PlantUML, Excalidraw, yEd |-| **✨ AIコンテンツ生成** | AI搭載のクラウドAPIを通じてプロフェッショナルな成果物(スライド、ドキュメント、ダイアグラム、ウェブサイト、調査レポート)を生成 | [AnyGen](https://www.anygen.io), Gamma, Beautiful.ai, Tome |+| **📞 コミュニケーショ�?& コラボレーション** | 構造化されたCLIで会議のスケジュール、参加者管理、録画取得、レポートを自動�?| Zoom, Jitsi Meet, BigBlueButton, Mattermost |+| **📐 ダイアグラ�?& ビジュアライゼーショ�?* | ダイアグラム、フローチャート、アーキテクチャ図、ビジュアルドキュメントをプログラムで作成・操作 | Draw.io (diagrams.net), Mermaid, PlantUML, Excalidraw, yEd |+| **�?AIコンテンツ生�?* | AI搭載のクラウドAPIを通じてプロフェッショナルな成果物(スライド、ドキュメント、ダイアグラム、ウェブサイト、調査レポート)を生�?| [AnyGen](https://www.anygen.io), Gamma, Beautiful.ai, Tome |----## CLI-Anythingの主な特徴+## CLI-Anythingの主な特�?### エージェントとソフトウェアのギャップ-AIエージェントは推論には優れていますが、実際のプロフェッショナルソフトウェアの操作は苦手です。現在のソリューションは脆弱なUI自動化、限定的なAPI、または機能の90%を失う簡素化された再実装です。+AIエージェントは推論には優れていますが、実際のプロフェッショナルソフトウェアの操作は苦手です。現在のソリューションは脆弱なUI自動化、限定的なAPI、または機能�?0%を失う簡素化された再実装です�?-**CLI-Anythingの解決策**: あらゆるプロフェッショナルソフトウェアを機能を損なうことなくエージェントネイティブツールに変換。+**CLI-Anythingの解決策**: あらゆるプロフェッショナルソフトウェアを機能を損なうことなくエージェントネイティブツールに変換�?-| **現在の課題** | **CLI-Anythingの解決策** |+| **現在の課�?* | **CLI-Anythingの解決策** ||----------|----------------------|-| 🤖 「AIは実際のツールを使えない」 | 実際のソフトウェアバックエンド(Blender、LibreOffice、FFmpeg)との直接統合 — フルプロフェッショナル機能、妥協ゼロ |-| 💸 「UI自動化はすぐ壊れる」 | スクリーンショットなし、クリックなし、RPA的な脆弱性なし。構造化インターフェースによる純粋なコマンドラインの信頼性 |-| 📊 「エージェントには構造化データが必要」 | シームレスなエージェント利用のための組み込みJSON出力 + デバッグ用の人間が読める形式 |-| 🔧 「カスタム統合はコストが高い」 | 1つのClaudeプラグインが実証済みの7フェーズパイプラインで任意のコードベースのCLIを自動生成 |-| ⚡ 「プロトタイプと本番のギャップ」 | 1,508以上のテストと実際のソフトウェアでの検証。11の主要アプリケーションで実戦検証済み |+| 🤖 「AIは実際のツールを使えない�?| 実際のソフトウェアバックエンド(Blender、LibreOffice、FFmpeg)との直接統�?�?フルプロフェッショナル機能、妥協ゼ�?|+| 💸 「UI自動化はすぐ壊れる�?| スクリーンショットなし、クリックなし、RPA的な脆弱性なし。構造化インターフェースによる純粋なコマンドラインの信頼�?|+| 📊 「エージェントには構造化データが必要�?| シームレスなエージェント利用のための組み込みJSON出力 + デバッグ用の人間が読める形式 |+| 🔧 「カスタム統合はコストが高い�?| 1つのClaudeプラグインが実証済み�?フェーズパイプラインで任意のコードベースのCLIを自動生�?|+| �?「プロトタイプと本番のギャップ�?| 1,508以上のテストと実際のソフトウェアでの検証�?1の主要アプリケーションで実戦検証済み |----## 🎯 CLI-Anythingで何ができる?+## 🎯 CLI-Anythingで何ができる�?<table><tr><td width="33%">-### 🛠️ エージェントにワークフローを任せる+### 🛠�?エージェントにワークフローを任せ�?-プロフェッショナルでも日常でも — コードベースを`/cli-anything`に渡すだけ。クリエイティブ作業にはGIMP、Blender、Shotcut。日常タスクにはLibreOffice、OBS Studio。ソースがない?オープンソースの代替を見つけてそれを渡しましょう。エージェントが使える完全なCLIが即座に手に入ります。+プロフェッショナルでも日常で�?�?コードベースを`/cli-anything`に渡すだけ。クリエイティブ作業にはGIMP、Blender、Shotcut。日常タスクにはLibreOffice、OBS Studio。ソースがない?オープンソースの代替を見つけてそれを渡しましょう。エージェントが使える完全なCLIが即座に手に入ります�?</td><td width="33%">-### 🔗 散在するAPIを1つのCLIに統合+### 🔗 散在するAPI�?つのCLIに統�?-断片化されたWebサービスAPIの管理にうんざりしていませんか?ドキュメントやSDKの原稿を`/cli-anything`に渡せば、エージェントが個々のエンドポイントを一貫したコマンドグループにまとめた**強力でステートフルなCLI**を手に入れます。数十のAPIコール代わりに1つのツール — トークンを節約しながらより強力な機能を。+断片化されたWebサービスAPIの管理にうんざりしていませんか?ドキュメントやSDKの原稿を`/cli-anything`に渡せば、エージェントが個々のエンドポイントを一貫したコマンドグループにまとめた**強力でステートフルなCLI**を手に入れます。数十のAPIコール代わり�?つのツー�?�?トークンを節約しながらより強力な機能を�?</td><td width="33%">### 🚀 GUIエージェントの置き換えまたは強化-CLI-Anythingは**GUIベースのエージェントアプローチを完全に置き換え**可能 — スクリーンショットも脆弱なピクセルクリックも不要。さらに面白いのは:ソフトウェアを`/cli-anything`すれば、コードとターミナルだけで**エージェントタスク、評価器、ベンチマークを合成**できます — 完全自動化、反復改善可能、圧倒的に効率的。+CLI-Anything�?*GUIベースのエージェントアプローチを完全に置き換�?*可能 �?スクリーンショットも脆弱なピクセルクリックも不要。さらに面白いのは:ソフトウェアを`/cli-anything`すれば、コードとターミナルだけ�?*エージェントタスク、評価器、ベンチマークを合成**できます �?完全自動化、反復改善可能、圧倒的に効率的�?</td></tr>@@ -401,34 +401,34 @@ CLI-Anythingは**GUIベースのエージェントアプローチを完全に置----## ✨ ⚙️ CLI-Anythingの仕組み+## �?⚙️ CLI-Anythingの仕組み<table><tr><td width="50%">-### 🏗️ 完全自動化された7フェーズパイプライン-コードベース分析からPyPI公開まで — プラグインがアーキテクチャ設計、実装、テスト計画、テスト作成、ドキュメンテーションを完全に自動で処理します。+### 🏗�?完全自動化された7フェーズパイプライン+コードベース分析からPyPI公開まで �?プラグインがアーキテクチャ設計、実装、テスト計画、テスト作成、ドキュメンテーションを完全に自動で処理します�?</td><td width="50%">-### 🎯 本物のソフトウェア統合-実際のレンダリングのための実アプリケーションへの直接呼び出し。LibreOfficeがPDFを生成し、Blenderが3Dシーンをレンダリングし、Audacityがsoxを通じてオーディオを処理します。**妥協ゼロ**、**おもちゃの実装ゼロ**。+### 🎯 本物のソフトウェア統�?+実際のレンダリングのための実アプリケーションへの直接呼び出し。LibreOfficeがPDFを生成し、Blender�?Dシーンをレンダリングし、Audacityがsoxを通じてオーディオを処理します�?*妥協ゼロ**�?*おもちゃの実装ゼ�?*�?</td></tr><tr><td width="50%">-### 🔁 スマートセッション管理-アンドゥ/リドゥ機能を備えた永続的なプロジェクト状態と、すべてのCLIで一貫したインタラクティブ体験を提供する統合REPLインターフェース(ReplSkin)。+### 🔁 スマートセッション管�?+アンドゥ/リドゥ機能を備えた永続的なプロジェクト状態と、すべてのCLIで一貫したインタラクティブ体験を提供する統合REPLインターフェース(ReplSkin)�?</td><td width="50%">-### 📦 設定不要のインストール-シンプルな pip install -e . で cli-anything-<software> がPATHに直接追加されます。エージェントは標準的なwhichコマンドでツールを発見します。セットアップ不要、ラッパー不要。+### 📦 設定不要のインストー�?+シンプル�?pip install -e . �?cli-anything-<software> がPATHに直接追加されます。エージェントは標準的なwhichコマンドでツールを発見します。セットアップ不要、ラッパー不要�?</td></tr>@@ -436,13 +436,13 @@ CLI-Anythingは**GUIベースのエージェントアプローチを完全に置<td width="50%">### 🧪 プロダクショングレードのテスト-多層的な検証: 合成データによるユニットテスト、実際のファイルとソフトウェアによるエンドツーエンドテスト、さらにインストール済みコマンドのCLIサブプロセス検証。+多層的な検証: 合成データによるユニットテスト、実際のファイルとソフトウェアによるエンドツーエンドテスト、さらにインストール済みコマンドのCLIサブプロセス検証�?</td><td width="50%">-### 🐍 クリーンなパッケージアーキテクチャ-すべてのCLIがcli_anything.*名前空間で整理 — 競合なし、pip installable、一貫した命名規則: cli-anything-gimp、cli-anything-blenderなど。+### 🐍 クリーンなパッケージアーキテクチ�?+すべてのCLIがcli_anything.*名前空間で整�?�?競合なし、pip installable、一貫した命名規�? cli-anything-gimp、cli-anything-blenderなど�?</td></tr>@@ -453,16 +453,16 @@ CLI-Anythingは**GUIベースのエージェントアプローチを完全に置## 🎬 デモンストレーション### 🎯 汎用-CLI-Anythingはコードベースを持つあらゆるソフトウェアで動作します — ドメインの制限やアーキテクチャの制約はありません。+CLI-Anythingはコードベースを持つあらゆるソフトウェアで動作します �?ドメインの制限やアーキテクチャの制約はありません�?-### 🏭 プロフェッショナルグレードのテスト-クリエイティブ、生産性、コミュニケーション、ダイアグラム、AIコンテンツ生成、GPUデバッグなど、以前はAIエージェントがアクセスできなかった12の多様で複雑なアプリケーションでテスト済み。+### 🏭 プロフェッショナルグレードのテス�?+クリエイティブ、生産性、コミュニケーション、ダイアグラム、AIコンテンツ生成、GPUデバッグなど、以前はAIエージェントがアクセスできなかっ�?2の多様で複雑なアプリケーションでテスト済み�?### 🎨 多様なドメインカバレッジ-クリエイティブワークフロー(画像編集、3Dモデリング、ベクターグラフィックス)からプロダクションツール(オーディオ、オフィス、ライブストリーミング、動画編集)まで。+クリエイティブワークフロー(画像編集�?Dモデリング、ベクターグラフィックス)からプロダクションツール(オーディオ、オフィス、ライブストリーミング、動画編集)まで�?-### ✅ 完全なCLI生成-各アプリケーションに対して完全な本番対応のCLIインターフェースを生成 — デモではなく、全機能へのアクセスを保持した包括的なツールアクセス。+### �?完全なCLI生成+各アプリケーションに対して完全な本番対応のCLIインターフェースを生�?�?デモではなく、全機能へのアクセスを保持した包括的なツールアクセス�?<table><tr>@@ -470,229 +470,229 @@ CLI-Anythingはコードベースを持つあらゆるソフトウェアで動<th align="center">ドメイン</th><th align="center">CLIコマンド</th><th align="center">バックエンド</th>-<th align="center">テスト</th>+<th align="center">テス�?/th></tr><tr><td align="center"><strong>🎨 GIMP</strong></td><td>画像編集</td><td><code>cli-anything-gimp</code></td><td>Pillow + GEGL/Script-Fu</td>-<td align="center">✅ 107</td>+<td align="center">�?107</td></tr><tr><td align="center"><strong>🧊 Blender</strong></td>-<td>3Dモデリング & レンダリング</td>+<td>3Dモデリン�?& レンダリン�?/td><td><code>cli-anything-blender</code></td><td>bpy (Pythonスクリプティング)</td>-<td align="center">✅ 208</td>+<td align="center">�?208</td></tr><tr><td align="center"><strong>✏️ Inkscape</strong></td>-<td>ベクターグラフィックス</td>+<td>ベクターグラフィック�?/td><td><code>cli-anything-inkscape</code></td><td>直接SVG/XML操作</td>-<td align="center">✅ 202</td>+<td align="center">�?202</td></tr><tr><td align="center"><strong>🎵 Audacity</strong></td>-<td>オーディオ制作</td>+<td>オーディオ制�?/td><td><code>cli-anything-audacity</code></td><td>Python wave + sox</td>-<td align="center">✅ 161</td>+<td align="center">�?161</td></tr><tr><td align="center"><strong>📄 LibreOffice</strong></td><td>オフィススイート (Writer, Calc, Impress)</td><td><code>cli-anything-libreoffice</code></td><td>ODF生成 + ヘッドレスLO</td>-<td align="center">✅ 158</td>+<td align="center">�?158</td></tr><tr><td align="center"><strong>📓 <a href="joplin/agent-harness/">Joplin</a></strong></td>-<td>ノート管理 & ToDo</td>+<td>ノート管�?& ToDo</td><td><code>cli-anything-joplin</code></td>-<td>Joplinターミナル CLI サブプロセス</td>-<td align="center">✅ 112</td>+<td>Joplinターミナ�?CLI サブプロセス</td>+<td align="center">�?112</td></tr><tr><td align="center"><strong>📹 OBS Studio</strong></td><td>ライブストリーミング & 録画</td><td><code>cli-anything-obs-studio</code></td>-<td>JSONシーン + obs-websocket</td>-<td align="center">✅ 153</td>+<td>JSONシー�?+ obs-websocket</td>+<td align="center">�?153</td></tr><tr>-<td align="center"><strong>🎞️ Kdenlive</strong></td>+<td align="center"><strong>🎞�?Kdenlive</strong></td><td>動画編集</td><td><code>cli-anything-kdenlive</code></td><td>MLT XML + meltレンダラー</td>-<td align="center">✅ 155</td>+<td align="center">�?155</td></tr><tr><td align="center"><strong>🎬 Shotcut</strong></td><td>動画編集</td><td><code>cli-anything-shotcut</code></td><td>直接MLT XML + melt</td>-<td align="center">✅ 154</td>+<td align="center">�?154</td></tr><tr><td align="center"><strong>📞 Zoom</strong></td>-<td>ビデオ会議</td>+<td>ビデオ会�?/td><td><code>cli-anything-zoom</code></td><td>Zoom REST API (OAuth2)</td>-<td align="center">✅ 22</td>+<td align="center">�?22</td></tr><tr><td align="center"><strong>📐 Draw.io</strong></td>-<td>ダイアグラム</td>+<td>ダイアグラ�?/td><td><code>cli-anything-drawio</code></td><td>mxGraph XML + draw.io CLI</td>-<td align="center">✅ 138</td>+<td align="center">�?138</td></tr><tr>-<td align="center"><strong>✨ AnyGen</strong></td>-<td>AIコンテンツ生成</td>+<td align="center"><strong>�?AnyGen</strong></td>+<td>AIコンテンツ生�?/td><td><code>cli-anything-anygen</code></td><td>AnyGen REST API (anygen.io)</td>-<td align="center">✅ 50</td>+<td align="center">�?50</td></tr><tr><td align="center"><strong>🟩 <a href="nsight-graphics/agent-harness/">Nsight Graphics CLI</a></strong></td><td>GPUデバッグ & プロファイリング</td><td><code>cli-anything-nsight-graphics</code></td><td>公式 ngfx / ngfx-capture オーケストレーション + GPU Trace サマリー</td>-<td align="center">✅ 40</td>+<td align="center">�?40</td></tr><tr><td align="center" colspan="4"><strong>合計</strong></td>-<td align="center"><strong>✅ 1,547</strong></td>+<td align="center"><strong>�?1,547</strong></td></tr></table>-> **全1,547テストで100%パス** — 1,108ユニットテスト + 439エンドツーエンドテスト。+> **�?,547テストで100%パス** �?1,108ユニットテス�?+ 439エンドツーエンドテスト�?----## 📊 テスト結果+## 📊 テスト結�?各CLIハーネスは本番環境の信頼性を確保するために厳格な多層テストを実施しています:-| レイヤー | テスト内容 | 例 |+| レイヤー | テスト内�?| �?||-------|---------------|---------|-| **ユニットテスト** | 合成データによるすべてのコア関数の分離テスト | `test_core.py` — プロジェクト作成、レイヤー操作、フィルタパラメータ |-| **E2Eテスト(ネイティブ)** | プロジェクトファイル生成パイプライン | 有効なODF ZIP構造、正しいMLT XML、SVGの整形式性 |-| **E2Eテスト(実バックエンド)** | 実際のソフトウェア呼び出し + 出力検証 | LibreOffice → `%PDF-`マジックバイトを持つPDF、Blender → レンダリングされたPNG |-| **CLIサブプロセステスト** | `subprocess.run`によるインストール済みコマンド | `cli-anything-gimp --json project new` → 有効なJSON出力 |+| **ユニットテス�?* | 合成データによるすべてのコア関数の分離テスト | `test_core.py` �?プロジェクト作成、レイヤー操作、フィルタパラメータ |+| **E2Eテスト(ネイティブ)** | プロジェクトファイル生成パイプライン | 有効なODF ZIP構造、正しいMLT XML、SVGの整形式�?|+| **E2Eテスト(実バックエンド)** | 実際のソフトウェア呼び出�?+ 出力検証 | LibreOffice �?`%PDF-`マジックバイトを持つPDF、Blender �?レンダリングされたPNG |+| **CLIサブプロセステス�?* | `subprocess.run`によるインストール済みコマン�?| `cli-anything-gimp --json project new` �?有効なJSON出力 |```-================================ テストサマリー ================================-gimp 107 passed ✅ (64 unit + 43 e2e)-blender 208 passed ✅ (150 unit + 58 e2e)-inkscape 202 passed ✅ (148 unit + 54 e2e)-audacity 161 passed ✅ (107 unit + 54 e2e)-libreoffice 158 passed ✅ (89 unit + 69 e2e)-obs-studio 153 passed ✅ (116 unit + 37 e2e)-kdenlive 155 passed ✅ (111 unit + 44 e2e)-shotcut 154 passed ✅ (110 unit + 44 e2e)-zoom 22 passed ✅ (22 unit + 0 e2e)-drawio 138 passed ✅ (116 unit + 22 e2e)-anygen 50 passed ✅ (40 unit + 10 e2e)-nsight-graphics 40 passed ✅ (36 unit + 4 e2e)-joplin 112 passed ✅ (85 unit + 27 e2e, 2 skipped on Windows)+================================ テストサマリ�?================================+gimp 107 passed �? (64 unit + 43 e2e)+blender 208 passed �? (150 unit + 58 e2e)+inkscape 202 passed �? (148 unit + 54 e2e)+audacity 161 passed �? (107 unit + 54 e2e)+libreoffice 158 passed �? (89 unit + 69 e2e)+obs-studio 153 passed �? (116 unit + 37 e2e)+kdenlive 155 passed �? (111 unit + 44 e2e)+shotcut 154 passed �? (110 unit + 44 e2e)+zoom 22 passed �? (22 unit + 0 e2e)+drawio 138 passed �? (116 unit + 22 e2e)+anygen 50 passed �? (40 unit + 10 e2e)+nsight-graphics 40 passed �? (36 unit + 4 e2e)+joplin 112 passed �? (91 unit + 27 e2e, 1 skipped on Windows)──────────────────────────────────────────────────────────────────────────────-合計 1,659 passed ✅ 100% パス率+合計 1,659 passed �? 100% パス�?```----## 🏗️ CLI-Anythingのアーキテクチャ+## 🏗�?CLI-Anythingのアーキテクチャ<p align="center">- <img src="assets/architecture.png" alt="CLI-Anything アーキテクチャ" width="750">+ <img src="assets/architecture.png" alt="CLI-Anything アーキテクチ�? width="750"></p>### 🎯 コア設計原則-1. **本物のソフトウェア統合** — CLIは有効なプロジェクトファイル(ODF、MLT XML、SVG)を生成し、レンダリングを実際のアプリケーションに委譲します。**ソフトウェアの代替ではなく、ソフトウェアへの構造化インターフェースを構築します**。+1. **本物のソフトウェア統�?* �?CLIは有効なプロジェクトファイル(ODF、MLT XML、SVG)を生成し、レンダリングを実際のアプリケーションに委譲します�?*ソフトウェアの代替ではなく、ソフトウェアへの構造化インターフェースを構築します**�?-2. **柔軟なインタラクションモデル** — すべてのCLIがデュアルモードで動作: インタラクティブなエージェントセッション用のステートフルREPL + スクリプティング/パイプライン用のサブコマンドインターフェース。**素のコマンドを実行 → REPLモードに入る**。+2. **柔軟なインタラクションモデル** �?すべてのCLIがデュアルモードで動�? インタラクティブなエージェントセッション用のステートフルREPL + スクリプティング/パイプライン用のサブコマンドインターフェース�?*素のコマンドを実�?�?REPLモードに入る**�?-3. **一貫したユーザー体験** — すべての生成CLIがブランドバナー、スタイル付きプロンプト、コマンド履歴、進捗表示、標準化されたフォーマットを持つ統合REPLインターフェース(repl_skin.py)を共有。+3. **一貫したユーザー体�?* �?すべての生成CLIがブランドバナー、スタイル付きプロンプト、コマンド履歴、進捗表示、標準化されたフォーマットを持つ統合REPLインターフェース(repl_skin.py)を共有�?-4. **エージェントネイティブ設計** — すべてのコマンドに組み込みの--jsonフラグがマシン向けの構造化データを提供し、人間が読めるテーブルがインタラクティブ用途に対応。**エージェントは標準の--helpとwhichコマンドで機能を発見**。+4. **エージェントネイティブ設�?* �?すべてのコマンドに組み込みの--jsonフラグがマシン向けの構造化データを提供し、人間が読めるテーブルがインタラクティブ用途に対応�?*エージェントは標準の--helpとwhichコマンドで機能を発見**�?-5. **妥協なしの依存関係** — 実際のソフトウェアは必須要件です — フォールバックなし、グレースフルデグラデーションなし。**バックエンドが見つからない場合、テストはスキップではなく失敗し、本物の機能を保証します**。+5. **妥協なしの依存関�?* �?実際のソフトウェアは必須要件です �?フォールバックなし、グレースフルデグラデーションなし�?*バックエンドが見つからない場合、テストはスキップではなく失敗し、本物の機能を保証します**�?----## 📂 プロジェクト構造+## 📂 プロジェクト構�?```cli-anything/├── 📄 README.md # 英語版README-├── 📁 assets/ # 画像とメディア-│ ├── icon.png # プロジェクトアイコン-│ └── teaser.png # ティーザー画像-│-├── 🔌 cli-anything-plugin/ # Claude Codeプラグイン-│ ├── HARNESS.md # 方法論SOP(信頼できる唯一の情報源)-│ ├── README.md # プラグインドキュメント-│ ├── QUICKSTART.md # 5分で始めるガイド-│ ├── PUBLISHING.md # 配布ガイド-│ ├── repl_skin.py # 統合REPLインターフェース-│ ├── commands/ # プラグインコマンド定義-│ │ ├── cli-anything.md # メインビルドコマンド-│ │ ├── refine.md # 既存ハーネスカバレッジの拡張-│ │ ├── test.md # テストランナー-│ │ └── validate.md # 標準検証-│ └── scripts/-│ └── setup-cli-anything.sh # セットアップスクリプト-│+├── 📁 assets/ # 画像とメディ�?+�? ├── icon.png # プロジェクトアイコン+�? └── teaser.png # ティーザー画�?+�?+├── 🔌 cli-anything-plugin/ # Claude Codeプラグイ�?+�? ├── HARNESS.md # 方法論SOP(信頼できる唯一の情報源�?+�? ├── README.md # プラグインドキュメン�?+�? ├── QUICKSTART.md # 5分で始めるガイド+�? ├── PUBLISHING.md # 配布ガイ�?+�? ├── repl_skin.py # 統合REPLインターフェース+�? ├── commands/ # プラグインコマンド定�?+�? �? ├── cli-anything.md # メインビルドコマンド+�? �? ├── refine.md # 既存ハーネスカバレッジの拡張+�? �? ├── test.md # テストランナ�?+�? �? └── validate.md # 標準検証+�? └── scripts/+�? └── setup-cli-anything.sh # セットアップスクリプ�?+�?├── 🤖 codex-skill/ # Codexスキルエントリーポイント-├── 🎨 gimp/agent-harness/ # GIMP CLI (107テスト)-├── 🧊 blender/agent-harness/ # Blender CLI (208テスト)-├── ✏️ inkscape/agent-harness/ # Inkscape CLI (202テスト)-├── 🎵 audacity/agent-harness/ # Audacity CLI (161テスト)-├── 📄 libreoffice/agent-harness/ # LibreOffice CLI (158テスト)-├── 📓 joplin/agent-harness/ # Joplin CLI (112テスト、新規)-├── 📹 obs-studio/agent-harness/ # OBS Studio CLI (153テスト)-├── 🎞️ kdenlive/agent-harness/ # Kdenlive CLI (155テスト)-├── 🎬 shotcut/agent-harness/ # Shotcut CLI (154テスト)-├── 📞 zoom/agent-harness/ # Zoom CLI (22テスト)-├── 📐 drawio/agent-harness/ # Draw.io CLI (138テスト)-├── ✨ anygen/agent-harness/ # AnyGen CLI (50テスト)-└── 🟩 nsight-graphics/agent-harness/ # Nsight Graphics CLI (40テスト)+├── 🎨 gimp/agent-harness/ # GIMP CLI (107テス�?+├── 🧊 blender/agent-harness/ # Blender CLI (208テス�?+├── ✏️ inkscape/agent-harness/ # Inkscape CLI (202テス�?+├── 🎵 audacity/agent-harness/ # Audacity CLI (161テス�?+├── 📄 libreoffice/agent-harness/ # LibreOffice CLI (158テス�?+├── 📓 joplin/agent-harness/ # Joplin CLI (112テスト、新�?+├── 📹 obs-studio/agent-harness/ # OBS Studio CLI (153テス�?+├── 🎞�?kdenlive/agent-harness/ # Kdenlive CLI (155テス�?+├── 🎬 shotcut/agent-harness/ # Shotcut CLI (154テス�?+├── 📞 zoom/agent-harness/ # Zoom CLI (22テス�?+├── 📐 drawio/agent-harness/ # Draw.io CLI (138テス�?+├── �?anygen/agent-harness/ # AnyGen CLI (50テス�?+└── 🟩 nsight-graphics/agent-harness/ # Nsight Graphics CLI (40テス�?```-各`agent-harness/`にはClick CLI、コアモジュール、ユーティリティ(`repl_skin.py`とバックエンドラッパーを含む)、包括的なテストを備えた`cli_anything.<software>/`配下のインストール可能なPythonパッケージが含まれています。+各`agent-harness/`にはClick CLI、コアモジュール、ユーティリティ(`repl_skin.py`とバックエンドラッパーを含む)、包括的なテストを備えた`cli_anything.<software>/`配下のインストール可能なPythonパッケージが含まれています�?----## 🎯 プラグインコマンド+## 🎯 プラグインコマン�?| コマンド | 説明 ||---------|-------------|-| `/cli-anything <ソフトウェアパスまたはリポジトリ>` | 完全なCLIハーネスを構築 — 全7フェーズ |-| `/cli-anything:refine <ソフトウェアパス> [フォーカス]` | 既存のハーネスを改善 — ギャップ分析でカバレッジを拡大 |+| `/cli-anything <ソフトウェアパスまたはリポジトリ>` | 完全なCLIハーネスを構�?�?�?フェーズ |+| `/cli-anything:refine <ソフトウェアパス> [フォーカス]` | 既存のハーネスを改善 �?ギャップ分析でカバレッジを拡�?|| `/cli-anything:test <ソフトウェアパスまたはリポジトリ>` | テストを実行しTEST.mdを結果で更新 || `/cli-anything:validate <ソフトウェアパスまたはリポジトリ>` | HARNESS.md標準に対して検証 |-### 使用例+### 使用�?```bash-# ローカルソースからGIMPの完全なCLIを構築+# ローカルソースからGIMPの完全なCLIを構�?/cli-anything /home/user/gimp# GitHubリポジトリからビルド/cli-anything https://github.com/blender/blender-# 既存のハーネスを改善 — 広範なギャップ分析+# 既存のハーネスを改善 �?広範なギャップ分�?/cli-anything:refine /home/user/gimp# 特定のフォーカスエリアで改善/cli-anything:refine /home/user/shotcut "ビデオインビデオとピクチャーインピクチャーの合成"-# テストを実行しTEST.mdを更新+# テストを実行しTEST.mdを更�?/cli-anything:test /home/user/inkscape# HARNESS.md標準に対して検証@@ -701,27 +701,27 @@ cli-anything/----## 🎮 デモ: 生成されたCLIの使用+## 🎮 デモ: 生成されたCLIの使�?`cli-anything-libreoffice`でエージェントができることの例:```bash-# 新しいWriterドキュメントを作成+# 新しいWriterドキュメントを作�?$ cli-anything-libreoffice document new -o report.json --type writer-✓ Writerドキュメントを作成: report.json+�?Writerドキュメントを作�? report.json# コンテンツを追加$ cli-anything-libreoffice --project report.json writer add-heading -t "Q1レポート" --level 1-✓ 見出しを追加: "Q1レポート"+�?見出しを追加: "Q1レポート"$ cli-anything-libreoffice --project report.json writer add-table --rows 4 --cols 3-✓ 4×3テーブルを追加+�?4×3テーブルを追�?-# LibreOfficeヘッドレスで実際のPDFにエクスポート+# LibreOfficeヘッドレスで実際のPDFにエクスポー�?$ cli-anything-libreoffice --project report.json export render output.pdf -p pdf --overwrite-✓ エクスポート完了: output.pdf (42,831 bytes) via libreoffice-headless+�?エクスポート完了: output.pdf (42,831 bytes) via libreoffice-headless-# エージェント用のJSONモード+# エージェント用のJSONモー�?$ cli-anything-libreoffice --json document info --project report.json{"name": "Q1 Report",@@ -732,23 +732,23 @@ $ cli-anything-libreoffice --json document info --project report.json}```-### REPLモード+### REPLモー�?```$ cli-anything-blender╔══════════════════════════════════════════╗-║ cli-anything-blender v1.0.0 ║-║ Blender CLI for AI Agents ║+�? cli-anything-blender v1.0.0 �?+�? Blender CLI for AI Agents �?╚══════════════════════════════════════════╝blender> scene new --name ProductShot-✓ シーンを作成: ProductShot+�?シーンを作成: ProductShotblender[ProductShot]> object add-mesh --type cube --location 0 0 1-✓ メッシュを追加: Cube at (0, 0, 1)+�?メッシュを追�? Cube at (0, 0, 1)blender[ProductShot]*> render execute --output render.png --engine CYCLES-✓ レンダリング完了: render.png (1920×1080, 2.3 MB) via blender --background+�?レンダリング完�? render.png (1920×1080, 2.3 MB) via blender --backgroundblender[ProductShot]> exitGoodbye! 👋@@ -758,21 +758,21 @@ Goodbye! 👋## 📖 標準プレイブック: HARNESS.md-HARNESS.mdは、自動CLI生成によってあらゆるソフトウェアをエージェントアクセス可能にするための決定版SOPです。+HARNESS.mdは、自動CLI生成によってあらゆるソフトウェアをエージェントアクセス可能にするための決定版SOPです�?-自動生成プロセスを通じて洗練された実証済みのパターンと方法論をエンコードしています。+自動生成プロセスを通じて洗練された実証済みのパターンと方法論をエンコードしています�?-このプレイブックは、11の多様な本番対応ハーネスの構築から得られた主要な知見を集約しています。+このプレイブックは�?1の多様な本番対応ハーネスの構築から得られた主要な知見を集約しています�?-### 重要な教訓+### 重要な教�?| 教訓 | 説明 ||--------|-------------|-| **実際のソフトウェアを使用する** | CLIはレンダリングのために実際のアプリケーションを呼び出す必要があります。GIMPの代わりにPillowを使ったり、Blenderのカスタムレンダラーを作ったりしないこと。有効なプロジェクトファイルを生成 → 実際のバックエンドを呼び出す。 |-| **レンダリングギャップ** | GUIアプリはレンダリング時にエフェクトを適用します。CLIがプロジェクトファイルを操作していても素朴なエクスポートツールを使うと、エフェクトが暗黙的にドロップされます。解決策: ネイティブレンダラー → フィルタ変換 → レンダースクリプト。 |-| **フィルタ変換** | フォーマット間でエフェクトをマッピング(MLT → ffmpeg)する際、重複フィルタのマージ、インターリーブされたストリーム順序、パラメータ空間の違い、マッピング不可能なエフェクトに注意。 |-| **タイムコード精度** | 非整数フレームレート(29.97fps)は累積的な丸め誤差を引き起こします。`int()`ではなく`round()`を使用し、表示には整数演算を使い、テストでは±1フレームの許容差を持たせること。 |-| **出力検証** | 終了コード0だからといってエクスポートが成功したと信頼しないこと。検証: マジックバイト、ZIP/OOXML構造、ピクセル分析、オーディオRMSレベル、長さチェック。 |+| **実際のソフトウェアを使用する** | CLIはレンダリングのために実際のアプリケーションを呼び出す必要があります。GIMPの代わりにPillowを使ったり、Blenderのカスタムレンダラーを作ったりしないこと。有効なプロジェクトファイルを生�?�?実際のバックエンドを呼び出す�?|+| **レンダリングギャッ�?* | GUIアプリはレンダリング時にエフェクトを適用します。CLIがプロジェクトファイルを操作していても素朴なエクスポートツールを使うと、エフェクトが暗黙的にドロップされます。解決策: ネイティブレンダラー �?フィルタ変換 �?レンダースクリプト�?|+| **フィルタ変換** | フォーマット間でエフェクトをマッピング(MLT �?ffmpeg)する際、重複フィルタのマージ、インターリーブされたストリーム順序、パラメータ空間の違い、マッピング不可能なエフェクトに注意�?|+| **タイムコード精度** | 非整数フレームレート�?9.97fps)は累積的な丸め誤差を引き起こします。`int()`ではなく`round()`を使用し、表示には整数演算を使い、テストでは±1フレームの許容差を持たせること�?|+| **出力検証** | 終了コー�?だからといってエクスポートが成功したと信頼しないこと。検�? マジックバイト、ZIP/OOXML構造、ピクセル分析、オーディオRMSレベル、長さチェック�?|> 完全な方法論はこちら: [`cli-anything-plugin/HARNESS.md`](cli-anything-plugin/HARNESS.md)@@ -780,21 +780,21 @@ HARNESS.mdは、自動CLI生成によってあらゆるソフトウェアをエ## 📦 インストール & 使用方法-### プラグインユーザー向け(Claude Code)+### プラグインユーザー向け(Claude Code�?```bash-# マーケットプレイスの追加とインストール(推奨)+# マーケットプレイスの追加とインストール(推奨�?/plugin marketplace add HKUDS/CLI-Anything/plugin install cli-anything-# 任意のコードベースを持つソフトウェアのCLIを構築-/cli-anything <ソフトウェア名>+# 任意のコードベースを持つソフトウェアのCLIを構�?+/cli-anything <ソフトウェア�?```### 生成されたCLI向け```bash-# 生成されたCLIをインストール+# 生成されたCLIをインストー�?cd <software>/agent-harnesspip install -e .@@ -803,14 +803,14 @@ which cli-anything-<software># 使用cli-anything-<software> --help-cli-anything-<software> # REPLに入る+cli-anything-<software> # REPLに入�?cli-anything-<software> --json <command> # エージェント用JSON出力```### テストの実行```bash-# 特定のCLIのテストを実行+# 特定のCLIのテストを実�?cd <software>/agent-harnesspython3 -m pytest cli_anything/<software>/tests/ -v@@ -822,27 +822,27 @@ CLI_ANYTHING_FORCE_INSTALLED=1 python3 -m pytest cli_anything/<software>/tests/## 🤝 コントリビューション-コントリビューションを歓迎します!CLI-Anythingは拡張可能に設計されています:+コントリビューションを歓迎します!CLI-Anythingは拡張可能に設計されています�?-- **新しいソフトウェアターゲット** — プラグインを使用して任意のコードベースのCLIを生成し、[`cli-anything-plugin/PUBLISHING.md`](cli-anything-plugin/PUBLISHING.md)を通じてハーネスを提出してください。-- **方法論の改善** — 新しい教訓をエンコードした`HARNESS.md`へのPR-- **プラグインの強化** — 新しいコマンド、フェーズの改善、より良い検証-- **テストカバレッジ** — より多くのE2Eシナリオ、エッジケース、ワークフローテスト+- **新しいソフトウェアターゲット** �?プラグインを使用して任意のコードベースのCLIを生成し、[`cli-anything-plugin/PUBLISHING.md`](cli-anything-plugin/PUBLISHING.md)を通じてハーネスを提出してください�?+- **方法論の改善** �?新しい教訓をエンコードした`HARNESS.md`へのPR+- **プラグインの強化** �?新しいコマンド、フェーズの改善、より良い検�?+- **テストカバレッジ** �?より多くのE2Eシナリオ、エッジケース、ワークフローテスト### 制限事項-- **強力な基盤モデルが必要** — CLI-Anythingは信頼性のあるハーネス生成のためにフロンティアクラスのモデル(例:Claude Opus 4.6、Claude Sonnet 4.6、GPT-5.4)に依存しています。弱いまたは小さいモデルでは、大幅な手動修正が必要な不完全または不正確なCLIが生成される可能性があります。-- **利用可能なソースコードに依存** — 7フェーズパイプラインはソースコードから分析・生成します。対象ソフトウェアがデコンパイルが必要なコンパイル済みバイナリのみを提供する場合、ハーネスの品質とカバレッジは大幅に低下します。-- **反復的な改善が必要な場合がある** — 1回の`/cli-anything`実行ですべての機能を完全にカバーできないことがあります。CLIのパフォーマンスとカバレッジを本番品質にするためには、`/refine`を1回以上実行することがしばしば必要です。+- **強力な基盤モデルが必�?* �?CLI-Anythingは信頼性のあるハーネス生成のためにフロンティアクラスのモデル(例:Claude Opus 4.6、Claude Sonnet 4.6、GPT-5.4)に依存しています。弱いまたは小さいモデルでは、大幅な手動修正が必要な不完全または不正確なCLIが生成される可能性があります�?+- **利用可能なソースコードに依存** �?7フェーズパイプラインはソースコードから分析・生成します。対象ソフトウェアがデコンパイルが必要なコンパイル済みバイナリのみを提供する場合、ハーネスの品質とカバレッジは大幅に低下します�?+- **反復的な改善が必要な場合があ�?* �?1回の`/cli-anything`実行ですべての機能を完全にカバーできないことがあります。CLIのパフォーマンスとカバレッジを本番品質にするためには、`/refine`�?回以上実行することがしばしば必要です�?### ロードマップ-- [ ] より多くのアプリケーションカテゴリのサポート(CAD、DAW、IDE、EDA、科学ツール)-- [ ] エージェントタスク完了率のベンチマークスイート+- [ ] より多くのアプリケーションカテゴリのサポート(CAD、DAW、IDE、EDA、科学ツール�?+- [ ] エージェントタスク完了率のベンチマークスイー�?- [ ] 社内/カスタムソフトウェア向けコミュニティ提供CLIハーネス- [ ] Claude Code以外の追加エージェントフレームワークとの統合-- [ ] クローズドソースソフトウェアとWebサービスのAPIをCLIにパッケージ化するサポート-- [ ] エージェントスキルの発見とオーケストレーション用のSKILL.mdをCLIと共に生成+- [ ] クローズドソースソフトウェアとWebサービスのAPIをCLIにパッケージ化するサポー�?+- [ ] エージェントスキルの発見とオーケストレーション用のSKILL.mdをCLIと共に生�?---@@ -850,44 +850,44 @@ CLI_ANYTHING_FORCE_INSTALLED=1 python3 -m pytest cli_anything/<software>/tests/| ドキュメント | 説明 ||----------|-------------|-| [`cli-anything-plugin/HARNESS.md`](cli-anything-plugin/HARNESS.md) | 方法論SOP — 信頼できる唯一の情報源 |-| [`cli-anything-plugin/README.md`](cli-anything-plugin/README.md) | プラグインドキュメント — コマンド、オプション、フェーズ |+| [`cli-anything-plugin/HARNESS.md`](cli-anything-plugin/HARNESS.md) | 方法論SOP �?信頼できる唯一の情報源 |+| [`cli-anything-plugin/README.md`](cli-anything-plugin/README.md) | プラグインドキュメン�?�?コマンド、オプション、フェー�?|| [`cli-anything-plugin/QUICKSTART.md`](cli-anything-plugin/QUICKSTART.md) | 5分で始めるガイド || [`cli-anything-plugin/PUBLISHING.md`](cli-anything-plugin/PUBLISHING.md) | 配布・公開ガイド |各生成ハーネスにも以下が含まれます:-- `<SOFTWARE>.md` — そのアプリケーション固有のアーキテクチャSOP-- `tests/TEST.md` — テスト計画と結果のドキュメント+- `<SOFTWARE>.md` �?そのアプリケーション固有のアーキテクチャSOP+- `tests/TEST.md` �?テスト計画と結果のドキュメン�?----## ⭐ スター履歴+## �?スター履�?-CLI-Anythingがあなたのソフトウェアをエージェントネイティブにするのに役立ったら、スターをお願いします! ⭐+CLI-Anythingがあなたのソフトウェアをエージェントネイティブにするのに役立ったら、スターをお願いします! �?<div align="center"><a href="https://star-history.com/#HKUDS/CLI-Anything&Date"><picture><source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/svg?repos=HKUDS/CLI-Anything&type=Date&theme=dark" /><source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/svg?repos=HKUDS/CLI-Anything&type=Date" />- <img alt="スター履歴チャート" src="https://api.star-history.com/svg?repos=HKUDS/CLI-Anything&type=Date" />+ <img alt="スター履歴チャー�? src="https://api.star-history.com/svg?repos=HKUDS/CLI-Anything&type=Date" /></picture></a></div>----## 📄 ライセンス+## 📄 ライセン�?-Apache License 2.0 — 自由に使用、変更、配布できます。+Apache License 2.0 �?自由に使用、変更、配布できます�?---<div align="center">-**CLI-Anything** — *コードベースを持つあらゆるソフトウェアをエージェントネイティブに。*+**CLI-Anything** �?*コードベースを持つあらゆるソフトウェアをエージェントネイティブに�?-<sub>AIエージェント時代のための方法論 | 11のプロフェッショナルソフトウェアデモ | 1,508のパステスト</sub>+<sub>AIエージェント時代のための方法�?| 11のプロフェッショナルソフトウェアデモ | 1,508のパステスト</sub><br>@@ -896,6 +896,6 @@ Apache License 2.0 — 自由に使用、変更、配布できます。</div><p align="center">- <em> CLI-Anythingをご覧いただきありがとうございます ✨</em><br><br>+ <em> CLI-Anythingをご覧いただきありがとうございま�?�?/em><br><br><img src="https://visitor-badge.laobi.icu/badge?page_id=HKUDS.CLI-Anything&style=for-the-badge&color=00d4ff" alt="Views"></p>diff --git a/joplin/agent-harness/JOPLIN.md b/joplin/agent-harness/JOPLIN.mdindex 04db57748..e16a0489e 100644--- a/joplin/agent-harness/JOPLIN.md+++ b/joplin/agent-harness/JOPLIN.md@@ -125,8 +125,8 @@ For real backend runs, ensure `joplin` is installed and available in `PATH`.Current validation baseline (Windows + Joplin CLI 3.6.2):-- `python -m pytest -q cli_anything/joplin/tests/test_core.py` �?`85 passed, 1 skipped`-- `python -m pytest -q cli_anything/joplin/tests` �?`112 passed, 2 skipped`+- `python -m pytest -q cli_anything/joplin/tests/test_core.py` �?`91 passed`+- `python -m pytest -q cli_anything/joplin/tests` �?`118 passed, 1 skipped`## Development notesdiff --git a/joplin/agent-harness/README.md b/joplin/agent-harness/README.mdindex 2f0812f89..415e8275c 100644--- a/joplin/agent-harness/README.md+++ b/joplin/agent-harness/README.md@@ -65,9 +65,9 @@ cli-anything-joplin --dry-run --project ./demo.joplin-harness.json todos createCurrent validation baseline (Windows + Joplin CLI 3.6.2):-- `python -m pytest -q cli_anything/joplin/tests/test_core.py` �?`85 passed, 1 skipped`-- `python -m pytest -q cli_anything/joplin/tests` �?`112 passed, 2 skipped`+- `python -m pytest -q cli_anything/joplin/tests/test_core.py` �?`91 passed`+- `python -m pytest -q cli_anything/joplin/tests` �?`118 passed, 1 skipped`-See `cli_anything/joplin/tests/TEST.md` for the full plan (85 unit + 27 e2e,+See `cli_anything/joplin/tests/TEST.md` for the full plan (91 unit + 27 e2e,2 skipped on Windows) and `cli_anything/joplin/WORKFLOWS.md` for the verifiedworkflow inventory.diff --git a/joplin/agent-harness/cli_anything/joplin/README.md b/joplin/agent-harness/cli_anything/joplin/README.mdindex 1a469907d..bba6da504 100644--- a/joplin/agent-harness/cli_anything/joplin/README.md+++ b/joplin/agent-harness/cli_anything/joplin/README.md@@ -121,8 +121,8 @@ CLI_ANYTHING_FORCE_INSTALLED=1 python -m pytest -v -s cli_anything/joplin/tests/Current validation baseline (Windows + Joplin CLI 3.6.2):-- `python -m pytest -q cli_anything/joplin/tests/test_core.py` �?`85 passed, 1 skipped`-- `python -m pytest -q cli_anything/joplin/tests` �?`112 passed, 2 skipped`+- `python -m pytest -q cli_anything/joplin/tests/test_core.py` �?`91 passed`+- `python -m pytest -q cli_anything/joplin/tests` �?`118 passed, 1 skipped`See `cli_anything/joplin/tests/TEST.md` for the full test plan and`cli_anything/joplin/WORKFLOWS.md` for the verified workflow inventory.diff --git a/joplin/agent-harness/cli_anything/joplin/WORKFLOWS.md b/joplin/agent-harness/cli_anything/joplin/WORKFLOWS.mdindex 77be88412..6da88ba0b 100644--- a/joplin/agent-harness/cli_anything/joplin/WORKFLOWS.md+++ b/joplin/agent-harness/cli_anything/joplin/WORKFLOWS.md@@ -79,7 +79,7 @@ tag.add, tag.remove, attach.add, interop.export, note.remove, notebook.remove| Layer | File / class | Backend needed | Workflows ||--------------------------|--------------------------------------|----------------|---------------------------------|-| Unit + CLI contract | `test_core.py` | No | 85 tests (1 skipped on Windows) |+| Unit + CLI contract | `test_core.py` | No | 91 tests || CLI subprocess | `TestCLISubprocess` | No | 10 tests || Real-backend commands | `TestBackendCommands` | Yes | 6 tests || Real-backend workflows | `TestBackendWorkflows` | Yes | 11 tests (1 skipped on Windows) |@@ -105,7 +105,7 @@ tag.add, tag.remove, attach.add, interop.export, note.remove, notebook.removenon-zero exit code is a real failure; they are not stripped from the returnedstreams (so multi-line note bodies and exports stay intact).- JSON error envelopes use the same `command` identifier as success responses- (`config.import_file`, `backend.export_sync_status`, `e2ee.decrypt_file`, �).+ (`config.import_file`, `backend.export_sync_status`, `e2ee.decrypt_file`, ?.## 7. Known limitationsdiff --git a/joplin/agent-harness/cli_anything/joplin/core/backend.py b/joplin/agent-harness/cli_anything/joplin/core/backend.pyindex da4217c9f..10df3fdf8 100644--- a/joplin/agent-harness/cli_anything/joplin/core/backend.py+++ b/joplin/agent-harness/cli_anything/joplin/core/backend.py@@ -155,7 +155,13 @@ def server_start(config: BackendConfig, exit_early: bool = True, quiet: bool = Fargs.append("--exit-early")if quiet:args.append("--quiet")- return run_joplin_command(args, config, timeout=300)+ # When exit_early is True the CLI returns as soon as the server is up+ # (~5 s), so a 300 s safety cap is reasonable. When exit_early is False+ # the CLI intentionally blocks for the lifetime of the server process;+ # imposing any fixed timeout would terminate a legitimately long-running+ # server, so we pass None (no timeout) in that mode.+ timeout = 300 if exit_early else None+ return run_joplin_command(args, config, timeout=timeout)def server_stop(config: BackendConfig) -> dict:diff --git a/joplin/agent-harness/cli_anything/joplin/skills/SKILL.md b/joplin/agent-harness/cli_anything/joplin/skills/SKILL.mdindex a707eab77..f473fef4b 100644--- a/joplin/agent-harness/cli_anything/joplin/skills/SKILL.md+++ b/joplin/agent-harness/cli_anything/joplin/skills/SKILL.md@@ -82,7 +82,7 @@ When `--json` is enabled, commands return:- Backend `stdout`/`stderr` in command results are verbatim; do not assumewarnings were stripped from note bodies or exports.- On failure, parse `error` using the same `command` field as success- (`config.import_file`, `e2ee.decrypt_file`, �). Multi-word subcommands use+ (`config.import_file`, `e2ee.decrypt_file`, ?. Multi-word subcommands usea single dot between group and subcommand.## Test workflow@@ -106,5 +106,5 @@ CLI_ANYTHING_FORCE_INSTALLED=1 python -m pytest -v -s cli_anything/joplin/tests/Current validation baseline (Windows + Joplin CLI 3.6.2):-- `python -m pytest -q cli_anything/joplin/tests/test_core.py` �?`85 passed, 1 skipped`-- `python -m pytest -q cli_anything/joplin/tests` �?`112 passed, 2 skipped`+- `python -m pytest -q cli_anything/joplin/tests/test_core.py` �?`91 passed`+- `python -m pytest -q cli_anything/joplin/tests` �?`118 passed, 1 skipped`diff --git a/joplin/agent-harness/cli_anything/joplin/tests/TEST.md b/joplin/agent-harness/cli_anything/joplin/tests/TEST.mdindex ac048da3d..d57c9ee2e 100644--- a/joplin/agent-harness/cli_anything/joplin/tests/TEST.md+++ b/joplin/agent-harness/cli_anything/joplin/tests/TEST.md@@ -8,7 +8,7 @@ The suite has two files:Real-backend classes are skipped automatically when `joplin` is not on `PATH`.-## test_core.py (85 tests, 1 skipped on Windows)+## test_core.py (91 tests)Pure Python tests covering the harness surface. Safe to run anywhere withouta Joplin backend.@@ -24,6 +24,14 @@ Coverage areas:benign Node warning handling (scrubbed copy used only for the non-zero exitdecision; returned `stdout`/`stderr` stay verbatim), mixed warning+real-errorsurfacing, timeout, JSON parse fallback, empty stdout+- Node warning continuation line (`(Use \`node --trace-deprecation …\`)`):+ the hint line Node appends after each deprecation warning is now also dropped+ during scrubbing so warning-only stderr no longer triggers a false+ `RuntimeError`; `run_joplin_json` parses JSON even when warning + hint prefix+ the payload; real errors after warning+hint are still surfaced+- `server_start` timeout: `exit_early=True` uses a finite cap (300 s);+ `exit_early=False` passes `timeout=None` so a long-lived `--wait` server+ process is never killed by a hard deadline- Backend stdout preservation: multi-paragraph note bodies keep internal blanklines; `run_joplin_json` parses JSON when a Node warning prefixes stdout- Error envelope command ID consistency: failures on `config import-file`,diff --git a/joplin/agent-harness/cli_anything/joplin/tests/test_core.py b/joplin/agent-harness/cli_anything/joplin/tests/test_core.pyindex 6f5bcb4b7..3c8c1c827 100644--- a/joplin/agent-harness/cli_anything/joplin/tests/test_core.py+++ b/joplin/agent-harness/cli_anything/joplin/tests/test_core.py@@ -316,6 +316,76 @@ def test_backend_run_command_node_warning_passes(monkeypatch):assert result["stderr"] == _WARNING+def test_backend_run_command_node_warning_with_continuation_passes(monkeypatch):+ """Regression (P1): Node always appends a hint line after each warning:++ (node:…) [DEP0040] DeprecationWarning: …+ (Use `node --trace-deprecation …` to show where the warning was created)++ Before the fix, the continuation line was kept after scrubbing, making+ scrubbed_stderr non-empty, which caused run_joplin_command to raise even+ though the exit was caused only by benign Node noise.+ """+ _WARN = "(node:1234) [DEP0040] DeprecationWarning: The `punycode` module is deprecated."+ _HINT = "(Use `node --trace-deprecation ...` to show where the warning was created)"+ _STDERR = f"{_WARN}\n{_HINT}"++ class Proc:+ returncode = 1+ stdout = ""+ stderr = _STDERR++ monkeypatch.setattr(joplin_backend, "find_joplin", lambda _: "joplin")+ monkeypatch.setattr(joplin_backend.subprocess, "run", lambda *a, **k: Proc())+ cfg = joplin_backend.BackendConfig(binary="joplin", profile=None)+ # Must not raise — both lines are benign warning/hint noise.+ result = joplin_backend.run_joplin_command(["ls"], cfg)+ assert result["returncode"] == 1+ assert result["stderr"] == _STDERR # raw stream still intact+++def test_backend_run_json_parses_despite_warning_and_continuation_prefix(monkeypatch):+ """run_joplin_json must succeed when both the warning AND its hint line+ are emitted to stdout ahead of the JSON payload."""+ _WARN = "(node:7) [DEP0040] DeprecationWarning: The `punycode` module is deprecated."+ _HINT = "(Use `node --trace-deprecation ...` to show where the warning was created)"+ _JSON = '[{"title":"NoteA"}]'++ class Proc:+ returncode = 0+ stdout = f"{_WARN}\n{_HINT}\n{_JSON}"+ stderr = ""++ monkeypatch.setattr(joplin_backend, "find_joplin", lambda _: "joplin")+ monkeypatch.setattr(joplin_backend.subprocess, "run", lambda *a, **k: Proc())+ cfg = joplin_backend.BackendConfig(binary="joplin", profile=None)+ result = joplin_backend.run_joplin_json(["ls", "--format", "json"], cfg)+ assert isinstance(result["data"], list)+ assert result["data"][0]["title"] == "NoteA"+++def test_backend_run_command_real_error_not_masked_by_warning_with_hint(monkeypatch):+ """A real Joplin error must surface even when stderr contains both the+ benign warning AND its continuation hint line before the error text."""++ class Proc:+ returncode = 1+ stdout = ""+ stderr = (+ "(node:1234) [DEP0040] DeprecationWarning: The `punycode` module is deprecated.\n"+ "(Use `node --trace-deprecation ...` to show where the warning was created)\n"+ "Error: Cannot find \"missing-note\"."+ )++ monkeypatch.setattr(joplin_backend, "find_joplin", lambda _: "joplin")+ monkeypatch.setattr(joplin_backend.subprocess, "run", lambda *a, **k: Proc())+ cfg = joplin_backend.BackendConfig(binary="joplin", profile=None)+ with pytest.raises(RuntimeError) as excinfo:+ joplin_backend.run_joplin_command(["cat", "missing-note"], cfg)+ assert "Cannot find" in str(excinfo.value)+ assert "DEP0040" not in str(excinfo.value)++def test_backend_run_command_real_error_alongside_warning_raises(monkeypatch):"""Regression: a real Joplin error must surface even when stderr alsocontains the benign DEP0040 punycode deprecation warning."""@@ -414,6 +484,44 @@ def test_backend_run_command_timeout(monkeypatch):assert "timed out" in str(excinfo.value)+def test_backend_server_start_exit_early_uses_finite_timeout(monkeypatch):+ """P2 regression: server_start(exit_early=True) must pass a finite timeout."""+ captured = {}++ class Proc:+ returncode = 0+ stdout = "Server started"+ stderr = ""++ def fake_run(cmd, *a, **k):+ captured["timeout"] = k.get("timeout")+ return Proc()++ monkeypatch.setattr(backend_core, "find_joplin", lambda _: "joplin")+ monkeypatch.setattr(backend_core, "run_joplin_command",+ lambda args, cfg, timeout=120: captured.update({"timeout": timeout}) or+ {"command": args, "returncode": 0, "stdout": "", "stderr": ""})+ cfg = joplin_backend.BackendConfig()+ backend_core.server_start(cfg, exit_early=True)+ assert captured["timeout"] is not None+ assert captured["timeout"] > 0+++def test_backend_server_start_no_exit_early_uses_no_timeout(monkeypatch):+ """P2 regression: server_start(exit_early=False) must pass timeout=None so+ a long-lived server process is never killed by a hard deadline."""+ captured = {}++ monkeypatch.setattr(backend_core, "run_joplin_command",+ lambda args, cfg, timeout=120: captured.update({"timeout": timeout}) or+ {"command": args, "returncode": 0, "stdout": "", "stderr": ""})+ cfg = joplin_backend.BackendConfig()+ backend_core.server_start(cfg, exit_early=False)+ assert captured["timeout"] is None, (+ f"Expected timeout=None for --wait mode, got {captured['timeout']}"+ )++def test_backend_run_json_parse(monkeypatch):monkeypatch.setattr(joplin_backend,diff --git a/joplin/agent-harness/cli_anything/joplin/utils/joplin_backend.py b/joplin/agent-harness/cli_anything/joplin/utils/joplin_backend.pyindex d9ff5f45c..f5983804c 100644--- a/joplin/agent-harness/cli_anything/joplin/utils/joplin_backend.py+++ b/joplin/agent-harness/cli_anything/joplin/utils/joplin_backend.py@@ -39,15 +39,37 @@ def _line_is_benign_node_warning(line: str) -> bool:return any(all(marker in lowered for marker in markers) for markers in _BENIGN_NODE_WARNING_MARKERS)+def _line_is_node_warning_continuation(line: str) -> bool:+ """Return True for the hint line that Node prints after each deprecation warning.++ Node consistently follows each DeprecationWarning with a one-line hint of+ the form ``(Use `node --trace-deprecation ...` to show where the warning+ was created)``. That line is *not* a warning header, so+ ``_line_is_benign_node_warning`` does not match it. Without this check,+ the continuation line is kept and makes the scrubbed text non-empty,+ causing ``run_joplin_command`` to raise on what are purely benign warnings.+ """+ stripped = line.strip()+ lowered = stripped.lower()+ # The hint always starts with "(use" and references --trace-deprecation.+ return stripped.startswith("(Use ") or (+ lowered.startswith("(use") and "--trace-deprecation" in lowered+ )++def _strip_benign_node_warnings(text: str) -> str:"""Return ``text`` with known-benign Node warning lines removed.- The filter is line-based and only drops the Node warning lines themselves- (and any blank padding emitted around them). Real diagnostic content is- preserved verbatim, including blank lines between paragraphs. Callers- must NOT use the returned value to replace ``stdout`` payloads -- it is- only meant for the success/failure decision, where collapsing trailing- blank padding around dropped warning lines is desirable.+ The filter is line-based and drops:+ - Lines matching ``_line_is_benign_node_warning``+ - The immediately following hint/continuation line if it matches+ ``_line_is_node_warning_continuation`` (e.g. the "Use node+ --trace-deprecation ..." line Node always emits after each warning)+ - Blank padding lines that hug a dropped line++ Real diagnostic content is preserved verbatim, including blank lines+ between paragraphs. Callers must NOT use the returned value to replace+ ``stdout`` payloads -- it is only meant for the success/failure decision."""if not text:return ""@@ -55,19 +77,24 @@ def _strip_benign_node_warnings(text: str) -> str:benign_indices: set[int] = set()for idx, raw_line in enumerate(lines):stripped = raw_line.strip()- if stripped and _line_is_benign_node_warning(stripped):+ if not stripped:+ continue+ if _line_is_benign_node_warning(stripped):benign_indices.add(idx)+ # Also drop the continuation/hint line that Node appends right+ # after each deprecation warning.+ next_idx = idx + 1+ if next_idx < len(lines) and _line_is_node_warning_continuation(lines[next_idx]):+ benign_indices.add(next_idx)if not benign_indices:return text.strip()- # Drop the warning lines themselves and any blank padding that hugs them- # (Node tends to emit a blank line before and after each warning), but- # keep blank lines that are part of legitimate payload structure.+ # Drop the warning/continuation lines and blank padding around them,+ # but keep blank lines that are part of legitimate payload structure.kept: list[str] = []for idx, raw_line in enumerate(lines):if idx in benign_indices:continueif raw_line.strip() == "":- # Drop the blank line only when it is sandwiched against a warningprev_is_warning = (idx - 1) in benign_indicesnext_is_warning = (idx + 1) in benign_indicesif prev_is_warning or next_is_warning:@@ -76,7 +103,7 @@ def _strip_benign_node_warnings(text: str) -> str:return "\n".join(kept).strip()-def run_joplin_command(args: list[str], config: BackendConfig, timeout: int = 120) -> dict:+def run_joplin_command(args: list[str], config: BackendConfig, timeout: Optional[int] = 120) -> dict:binary = find_joplin(config.binary)cmd = [binary]if config.profile:@@ -92,7 +119,7 @@ def run_joplin_command(args: list[str], config: BackendConfig, timeout: int = 12check=False,)except subprocess.TimeoutExpired as e:- raise RuntimeError(f"Joplin command timed out after {timeout}s") from e+ raise RuntimeError(f"Joplin command timed out after {timeout}s") from e # timeout is non-None here# IMPORTANT: stdout is the caller's payload (note bodies, JSON dumps,# config exports, ...). Preserve it verbatim -- collapsing blank lines or@@ -122,7 +149,7 @@ def run_joplin_command(args: list[str], config: BackendConfig, timeout: int = 12return result-def run_joplin_json(args: list[str], config: BackendConfig, timeout: int = 120) -> dict:+def run_joplin_json(args: list[str], config: BackendConfig, timeout: Optional[int] = 120) -> dict:command_args = args if "--format" in args or "-f" in args else args + ["--format", "json"]raw = run_joplin_command(command_args, config, timeout=timeout)text = raw["stdout"]diff --git a/skills/cli-anything-joplin/SKILL.md b/skills/cli-anything-joplin/SKILL.mdindex e31bf58c9..4471ebee1 100644--- a/skills/cli-anything-joplin/SKILL.md+++ b/skills/cli-anything-joplin/SKILL.md@@ -83,7 +83,7 @@ When `--json` is enabled, commands return:- Backend `stdout`/`stderr` in command results are verbatim; do not assumewarnings were stripped from note bodies or exports.- On failure, parse `error` using the same `command` field as success- (`config.import_file`, `e2ee.decrypt_file`, �). Multi-word subcommands use+ (`config.import_file`, `e2ee.decrypt_file`, ?. Multi-word subcommands usea single dot between group and subcommand.## Recommended workflow@@ -98,5 +98,5 @@ When `--json` is enabled, commands return:Current validation baseline (Windows + Joplin CLI 3.6.2):-- `python -m pytest -q cli_anything/joplin/tests/test_core.py` �?`85 passed, 1 skipped`-- `python -m pytest -q cli_anything/joplin/tests` �?`112 passed, 2 skipped`+- `python -m pytest -q cli_anything/joplin/tests/test_core.py` �?`91 passed`+- `python -m pytest -q cli_anything/joplin/tests` �?`118 passed, 1 skipped`