Skip to content

Agent skill that turns natural language, code, Terraform/K8s, SQL, OpenAPI, AsyncAPI, Protobuf and GraphQL sources into editable, tested draw.io architecture diagrams: incremental sync, multi-view projection, drift diff, CI architecture tests, whiteboard derasterize, interactive HTML/PPTX/Mermaid exports.

docs: refresh stale counts on Pages site + comparison docs; add SkillSpector baseline (#88)

Agents365.aiaadd6000b004
diff --git a/.gitignore b/.gitignore
index 1299871..48957d9 100644
--- a/.gitignore
+++ b/.gitignore
@@ -12,3 +12,4 @@ __pycache__/
# Superpowers skill files (local-only)
docs/superpowers
+.pi-subagents/
diff --git a/.skillspector-baseline.json b/.skillspector-baseline.json
new file mode 100644
index 0000000..ce7ada4
--- /dev/null
+++ b/.skillspector-baseline.json
@@ -0,0 +1,270 @@
+{
+ "version": 1,
+ "rules": [],
+ "fingerprints": [
+ {
+ "hash": "sha256:3056deafca0a5370",
+ "rule_id": "AST4",
+ "file": "scripts/autolayout.py",
+ "reason": "Accepted finding (auto-generated baseline)"
+ },
+ {
+ "hash": "sha256:fc4238dba4458e5d",
+ "rule_id": "AST4",
+ "file": "scripts/drawio2pptx.py",
+ "reason": "Accepted finding (auto-generated baseline)"
+ },
+ {
+ "hash": "sha256:e0538884f0fb9343",
+ "rule_id": "AST4",
+ "file": "scripts/drawiohtml.py",
+ "reason": "Accepted finding (auto-generated baseline)"
+ },
+ {
+ "hash": "sha256:c17aedd10330a376",
+ "rule_id": "AST4",
+ "file": "scripts/goimports.py",
+ "reason": "Accepted finding (auto-generated baseline)"
+ },
+ {
+ "hash": "sha256:58b4a143a773720f",
+ "rule_id": "AST4",
+ "file": "scripts/jsimports.py",
+ "reason": "Accepted finding (auto-generated baseline)"
+ },
+ {
+ "hash": "sha256:1fc27d359a49994a",
+ "rule_id": "AST4",
+ "file": "scripts/pyclasses.py",
+ "reason": "Accepted finding (auto-generated baseline)"
+ },
+ {
+ "hash": "sha256:d2b709ed124b6d01",
+ "rule_id": "AST4",
+ "file": "scripts/pyimports.py",
+ "reason": "Accepted finding (auto-generated baseline)"
+ },
+ {
+ "hash": "sha256:3e36e143a9af2b7e",
+ "rule_id": "AST4",
+ "file": "scripts/rustimports.py",
+ "reason": "Accepted finding (auto-generated baseline)"
+ },
+ {
+ "hash": "sha256:3a7dd8b2a0070add",
+ "rule_id": "AST4",
+ "file": "scripts/svgflow.py",
+ "reason": "Accepted finding (auto-generated baseline)"
+ },
+ {
+ "hash": "sha256:427df1f1f4f660c5",
+ "rule_id": "AST4",
+ "file": "scripts/tfimports.py",
+ "reason": "Accepted finding (auto-generated baseline)"
+ },
+ {
+ "hash": "sha256:b637b9487731f3f5",
+ "rule_id": "AST4",
+ "file": "scripts/timelapse.py",
+ "reason": "Accepted finding (auto-generated baseline)"
+ },
+ {
+ "hash": "sha256:f710d1621764a1f2",
+ "rule_id": "AST4",
+ "file": "scripts/timelapse.py",
+ "reason": "Accepted finding (auto-generated baseline)"
+ },
+ {
+ "hash": "sha256:6463d8eea84087e3",
+ "rule_id": "AST4",
+ "file": "scripts/timelapse.py",
+ "reason": "Accepted finding (auto-generated baseline)"
+ },
+ {
+ "hash": "sha256:da5f63b63fcf60c0",
+ "rule_id": "AST4",
+ "file": "scripts/timelapse.py",
+ "reason": "Accepted finding (auto-generated baseline)"
+ },
+ {
+ "hash": "sha256:864c04cfd1ee89e9",
+ "rule_id": "TT4",
+ "file": "scripts/aiicons.py",
+ "reason": "Accepted finding (auto-generated baseline)"
+ },
+ {
+ "hash": "sha256:b45f692df9bbe01b",
+ "rule_id": "TT4",
+ "file": "scripts/aiicons.py",
+ "reason": "Accepted finding (auto-generated baseline)"
+ },
+ {
+ "hash": "sha256:0de16ec428a46dfb",
+ "rule_id": "LP3",
+ "file": "SKILL.md",
+ "reason": "Accepted finding (auto-generated baseline)"
+ },
+ {
+ "hash": "sha256:f8714a46574b30ce",
+ "rule_id": "MP2",
+ "file": "scripts/composeimports.py",
+ "reason": "Accepted finding (auto-generated baseline)"
+ },
+ {
+ "hash": "sha256:b587403f8c061503",
+ "rule_id": "MP2",
+ "file": "scripts/composeimports.py",
+ "reason": "Accepted finding (auto-generated baseline)"
+ },
+ {
+ "hash": "sha256:ece8483b9ec46180",
+ "rule_id": "MP2",
+ "file": "scripts/drawio2pptx.py",
+ "reason": "Accepted finding (auto-generated baseline)"
+ },
+ {
+ "hash": "sha256:1742aa3638be6736",
+ "rule_id": "MP2",
+ "file": "scripts/goimports.py",
+ "reason": "Accepted finding (auto-generated baseline)"
+ },
+ {
+ "hash": "sha256:b4e05ce1903c073e",
+ "rule_id": "MP2",
+ "file": "scripts/heatmap.py",
+ "reason": "Accepted finding (auto-generated baseline)"
+ },
+ {
+ "hash": "sha256:4a621288e287b1fc",
+ "rule_id": "MP2",
+ "file": "scripts/pyclasses.py",
+ "reason": "Accepted finding (auto-generated baseline)"
+ },
+ {
+ "hash": "sha256:e798a280a30640f0",
+ "rule_id": "MP2",
+ "file": "scripts/relabel.py",
+ "reason": "Accepted finding (auto-generated baseline)"
+ },
+ {
+ "hash": "sha256:3f6c38bfe313ea14",
+ "rule_id": "MP2",
+ "file": "scripts/restyle.py",
+ "reason": "Accepted finding (auto-generated baseline)"
+ },
+ {
+ "hash": "sha256:ccea22d7f70c8544",
+ "rule_id": "MP2",
+ "file": "scripts/restyle.py",
+ "reason": "Accepted finding (auto-generated baseline)"
+ },
+ {
+ "hash": "sha256:f8ac72dc206d4f08",
+ "rule_id": "MP2",
+ "file": "scripts/rustimports.py",
+ "reason": "Accepted finding (auto-generated baseline)"
+ },
+ {
+ "hash": "sha256:8f8d6dad7970a22b",
+ "rule_id": "MP2",
+ "file": "scripts/rustimports.py",
+ "reason": "Accepted finding (auto-generated baseline)"
+ },
+ {
+ "hash": "sha256:fcfb65261aee79ae",
+ "rule_id": "MP2",
+ "file": "scripts/shapesearch.py",
+ "reason": "Accepted finding (auto-generated baseline)"
+ },
+ {
+ "hash": "sha256:b1fd63475d232c70",
+ "rule_id": "OH1",
+ "file": "scripts/autolayout.py",
+ "reason": "Accepted finding (auto-generated baseline)"
+ },
+ {
+ "hash": "sha256:3b357839ce175b1a",
+ "rule_id": "OH1",
+ "file": "scripts/goimports.py",
+ "reason": "Accepted finding (auto-generated baseline)"
+ },
+ {
+ "hash": "sha256:d75b218fee1da932",
+ "rule_id": "OH1",
+ "file": "scripts/jsimports.py",
+ "reason": "Accepted finding (auto-generated baseline)"
+ },
+ {
+ "hash": "sha256:778bc3104e33573b",
+ "rule_id": "OH1",
+ "file": "scripts/pyclasses.py",
+ "reason": "Accepted finding (auto-generated baseline)"
+ },
+ {
+ "hash": "sha256:6b07cd921b56d200",
+ "rule_id": "OH1",
+ "file": "scripts/pyimports.py",
+ "reason": "Accepted finding (auto-generated baseline)"
+ },
+ {
+ "hash": "sha256:dae95edd6bbf9b29",
+ "rule_id": "OH1",
+ "file": "scripts/rustimports.py",
+ "reason": "Accepted finding (auto-generated baseline)"
+ },
+ {
+ "hash": "sha256:6118ea5ff28c5978",
+ "rule_id": "OH1",
+ "file": "scripts/svgflow.py",
+ "reason": "Accepted finding (auto-generated baseline)"
+ },
+ {
+ "hash": "sha256:bea4355383fbcf31",
+ "rule_id": "OH1",
+ "file": "scripts/tfimports.py",
+ "reason": "Accepted finding (auto-generated baseline)"
+ },
+ {
+ "hash": "sha256:b41607919a1f83d9",
+ "rule_id": "OH1",
+ "file": "scripts/timelapse.py",
+ "reason": "Accepted finding (auto-generated baseline)"
+ },
+ {
+ "hash": "sha256:492a3e26dc031505",
+ "rule_id": "OH1",
+ "file": "scripts/timelapse.py",
+ "reason": "Accepted finding (auto-generated baseline)"
+ },
+ {
+ "hash": "sha256:f66b3d0819204bd9",
+ "rule_id": "PE3",
+ "file": "SKILL.md",
+ "reason": "Accepted finding (auto-generated baseline)"
+ },
+ {
+ "hash": "sha256:41226ab4ff876ae8",
+ "rule_id": "P2",
+ "file": "references/xml-authoring.md",
+ "reason": "Accepted finding (auto-generated baseline)"
+ },
+ {
+ "hash": "sha256:007eff6759752e34",
+ "rule_id": "P2",
+ "file": "references/xml-authoring.md",
+ "reason": "Accepted finding (auto-generated baseline)"
+ },
+ {
+ "hash": "sha256:4b8f7e0296a72898",
+ "rule_id": "P2",
+ "file": "references/xml-authoring.md",
+ "reason": "Accepted finding (auto-generated baseline)"
+ },
+ {
+ "hash": "sha256:25e30d227f9fd2c4",
+ "rule_id": "TM1",
+ "file": "references/style-presets.md",
+ "reason": "Accepted finding (auto-generated baseline)"
+ }
+ ]
+}
\ No newline at end of file
diff --git a/docs/COMPARISON.md b/docs/COMPARISON.md
index 53537a3..8582cbe 100644
--- a/docs/COMPARISON.md
+++ b/docs/COMPARISON.md
@@ -12,7 +12,7 @@
| Proactive triggers | No — only when explicitly asked | Yes — auto-suggests when 3+ components |
| Layout guidelines | None — varies by run | Complexity-scaled spacing, routing corridors, hub placement |
| Grid alignment | No | Yes — all coordinates snap to 10px multiples |
-| Diagram type presets | No | Yes — 6 presets (ERD, UML, Sequence, Architecture, ML/DL, Flowchart) |
+| Diagram type presets | No | Yes — 11 presets (ERD, UML Class, Sequence, C4, Architecture, ML/Deep Learning, Flowchart, SysML, BPMN, Network Topology, Cross-Functional Swimlane) |
| Visualize a codebase | No | Yes — import graphs (Py/JS/Go/Rust) + class diagrams |
| Auto-layout for large graphs | No — hand-places, overlaps | Yes — Graphviz placement, ortho routing, nested containers |
| Structural validation | No | Yes — deterministic `.drawio` linter |
@@ -37,7 +37,7 @@
| **Self-check** | ✅ 2-round vision-based (reads PNG) | ❌ | ✅ validation + strict mode | ❌ screenshot only |
| **Iterative review** | ✅ 5-round loop | ❌ generate once | ✅ 3 workflows (create/edit/replicate) | ❌ |
| **Layout guidance** | ✅ complexity-scaled + grid snap | ✅ basic spacing | ✅ design-system | ❌ |
-| **Diagram presets** | ✅ 6 types (ERD, UML, Seq, Arch, ML, Flow) | ❌ | ✅ paper-mode classifier (architecture/roadmap/workflow) | ❌ |
+| **Diagram presets** | ✅ 11 types (ERD, UML, Seq, C4, Arch, ML, Flow, SysML, BPMN, Network, Swimlane) | ❌ | ✅ paper-mode classifier (architecture/roadmap/workflow) | ❌ |
| **Animated edges** | ✅ `flowAnimation=1` | ❌ | ❌ | ❌ |
| **ML/DL diagrams** | ✅ tensor shapes, layer colors | ❌ | ❌ | ❌ |
| **Color system** | ✅ 7-color semantic | ❌ | ✅ 6 themes | ❌ |
@@ -56,7 +56,7 @@ _Last audited against competitor READMEs on 2026-07-10. Please open an issue or
## Key advantages
1. **Self-check + iterative loop** — the only pure-SKILL.md solution that reads its own output and auto-fixes before showing the user, then supports multi-round refinement
-2. **6 diagram type presets** — ERD, UML Class, Sequence, Architecture, ML/Deep Learning, Flowchart — each with preset shapes, styles, and layout conventions
+2. **11 diagram type presets** — ERD, UML Class, Sequence, C4, Architecture, ML/Deep Learning, Flowchart, SysML, BPMN, Network Topology, Cross-Functional Swimlane — each with preset shapes, styles, and layout conventions
3. **ML/DL model diagrams** — tensor shape annotations, layer-type color coding, encoder/decoder swimlanes — built for academic papers
4. **Multi-agent, zero-config** — works across 6 platforms with just the `skills/drawio-skill/` directory + draw.io desktop. No MCP server, no Python, no Node.js, no browser
5. **Production-grade layout** — grid-aligned coordinates, complexity-scaled spacing, routing corridors, hub-center strategy, animated connectors
diff --git a/docs/COMPARISON_CN.md b/docs/COMPARISON_CN.md
index ece2c05..21f78da 100644
--- a/docs/COMPARISON_CN.md
+++ b/docs/COMPARISON_CN.md
@@ -12,7 +12,7 @@
| 主动触发 | 否 — 仅在明确要求时 | 是 — 3+ 组件时自动建议画图 |
| 布局规范 | 无 — 每次结果不一致 | 按复杂度分级间距、路由走廊、hub 居中策略 |
| 网格对齐 | 否 | 是 — 所有坐标对齐到 10px 倍数 |
-| 图表类型预设 | 否 | 是 — 6 种预设(ERD、UML、序列图、架构图、ML/DL、流程图) |
+| 图表类型预设 | 否 | 是 — 11 种预设(ERD、UML 类图、序列图、C4、架构图、ML/深度学习、流程图、SysML、BPMN、网络拓扑、跨职能泳道图) |
| 可视化代码库 | 否 | 是 — 导入关系图(Py/JS/Go/Rust)+ 类图 |
| 大图自动布局 | 否 — 手动摆放、易重叠 | 是 — Graphviz 布点、正交路由、嵌套容器 |
| 结构校验 | 否 | 是 — 确定性 `.drawio` linter |
@@ -37,7 +37,7 @@
| **自检** | ✅ 2 轮视觉自检(读取 PNG) | ❌ | ✅ 校验 + 严格模式 | ❌ 仅截图 |
| **迭代审查** | ✅ 5 轮循环 | ❌ 一次生成 | ✅ 3 种工作流(create/edit/replicate) | ❌ |
| **布局指南** | ✅ 按复杂度分级 + 网格对齐 | ✅ 基础间距 | ✅ design-system | ❌ |
-| **图表预设** | ✅ 6 种(ERD、UML、序列、架构、ML、流程) | ❌ | ✅ 论文模式分类(架构/路线图/工作流) | ❌ |
+| **图表预设** | ✅ 11 种(ERD、UML、序列、C4、架构、ML、流程、SysML、BPMN、网络、泳道) | ❌ | ✅ 论文模式分类(架构/路线图/工作流) | ❌ |
| **动画连线** | ✅ `flowAnimation=1` | ❌ | ❌ | ❌ |
| **ML/DL 图** | ✅ 张量标注、层配色 | ❌ | ❌ | ❌ |
| **配色系统** | ✅ 7 色语义 | ❌ | ✅ 6 种主题 | ❌ |
@@ -56,7 +56,7 @@ _最近一次依据各 repo README 核查:2026-07-10。如有出入欢迎提 i
## 核心优势
1. **自检 + 迭代循环** — 唯一纯 SKILL.md 方案中能自动读取输出、修复问题、支持多轮优化的
-2. **6 种图表类型预设** — ERD、UML 类图、序列图、架构图、ML/深度学习、流程图 — 每种都有预设形状、样式和布局规范
+2. **11 种图表类型预设** — ERD、UML 类图、序列图、C4、架构图、ML/深度学习、流程图、SysML、BPMN、网络拓扑、跨职能泳道图 — 每种都有预设形状、样式和布局规范
3. **ML/DL 模型图** — 张量形状标注、层类型配色、编码器/解码器泳道 — 专为学术论文打造
4. **多智能体、零配置** — 跨 6 个平台运行,仅需 `skills/drawio-skill/` 目录 + draw.io 桌面版,无需 MCP、Python、Node.js、浏览器
5. **专业级布局** — 网格对齐坐标、按复杂度分级间距、路由走廊、hub 居中策略、动画连接线
diff --git a/docs/index.html b/docs/index.html
index b4c0029..e8af470 100644
--- a/docs/index.html
+++ b/docs/index.html
@@ -4,13 +4,13 @@
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>drawio-skill — From Text to Professional Diagrams</title>
- <meta name="description" content="Claude Code skill for professional draw.io diagrams from natural language: 6 presets, ML/DL support, codebase visualization, 10,000+ official shapes, 321 AI/LLM brand logos, self-check loop. Exports PNG/SVG/PDF/JPG.">
+ <meta name="description" content="Claude Code skill for professional draw.io diagrams from natural language: 11 presets, ML/DL support, codebase visualization, 10,000+ official shapes, 321 AI/LLM brand logos, self-check loop. Exports PNG/SVG/PDF/JPG.">
<meta name="theme-color" content="#0d1117">
<link rel="canonical" href="https://agents365-ai.github.io/drawio-skill/">
<link rel="alternate" hreflang="zh" href="https://agents365-ai.github.io/drawio-skill/zh.html">
<link rel="alternate" hreflang="en" href="https://agents365-ai.github.io/drawio-skill/">
<meta property="og:title" content="drawio-skill — From Text to Professional Diagrams">
- <meta property="og:description" content="Professional draw.io diagrams from natural language: 6 presets, codebase visualization, 10,000+ official shapes, 321 AI/LLM brand logos, self-check loop.">
+ <meta property="og:description" content="Professional draw.io diagrams from natural language: 11 presets, codebase visualization, 10,000+ official shapes, 321 AI/LLM brand logos, self-check loop.">
<meta property="og:type" content="website">
<meta property="og:url" content="https://agents365-ai.github.io/drawio-skill/">
<meta property="og:image" content="https://raw.githubusercontent.com/Agents365-ai/drawio-skill/main/assets/demo-star.png">
@@ -214,7 +214,7 @@
<!-- Hero -->
<div class="hero">
<div class="container">
- <div class="hero-badge">v1.14.0 &mdash; Codebase Viz, Shape Search, AI &amp; Data Logos</div>
+ <div class="hero-badge">v1.32.0 &mdash; Codebase Viz, Shape Search, AI &amp; Data Logos</div>
<h1>drawio-<span>skill</span></h1>
<p>From text to professional diagrams. Generate draw.io files from natural language &mdash; or turn an existing codebase into a structure diagram &mdash; with self-check, iterative refinement, 10,000+ official shapes, and AI/LLM brand logos.</p>
<div class="hero-install">
@@ -259,8 +259,8 @@
</div>
<div class="feature-card">
<div class="feature-icon">&#x1F4CB;</div>
- <h3>6 Diagram Presets</h3>
- <p>ERD, UML Class, Sequence, Architecture, ML/Deep Learning, Flowchart &mdash; each with preset shapes, styles, and layout conventions.</p>
+ <h3>11 Diagram Presets</h3>
+ <p>ERD, UML Class, Sequence, C4, Architecture, ML/Deep Learning, Flowchart, SysML, BPMN, Network Topology, Cross-Functional Swimlane &mdash; each with preset shapes, styles, and layout conventions.</p>
</div>
<div class="feature-card">
<div class="feature-icon">&#x1F9E0;</div>
@@ -349,7 +349,7 @@
<tbody>
<tr><td>Self-check after export</td><td class="cross">&#x2717;</td><td class="check">&#x2713; 2-round auto-fix</td></tr>
<tr><td>Iterative review loop</td><td class="cross">&#x2717;</td><td class="check">&#x2713; 5-round with targeted edits</td></tr>
- <tr><td>Diagram type presets</td><td class="cross">&#x2717;</td><td class="check">&#x2713; 6 presets (ERD, UML, Seq, Arch, ML, Flow)</td></tr>
+ <tr><td>Diagram type presets</td><td class="cross">&#x2717;</td><td class="check">&#x2713; 11 presets (ERD, UML, Seq, C4, Arch, ML, Flow, SysML, BPMN, Network, Swimlane)</td></tr>
<tr><td>ML model diagrams</td><td class="cross">&#x2717;</td><td class="check">&#x2713; Tensor shapes, layer colors</td></tr>
<tr><td>Animated connectors</td><td class="cross">&#x2717;</td><td class="check">&#x2713; flowAnimation=1</td></tr>
<tr><td>Grid-aligned layout</td><td class="cross">&#x2717;</td><td class="check">&#x2713; 10px snap</td></tr>
diff --git a/docs/zh.html b/docs/zh.html
index dd8a287..e40bf29 100644
--- a/docs/zh.html
+++ b/docs/zh.html
@@ -4,13 +4,13 @@
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>drawio-skill — 从文本到专业图表</title>
- <meta name="description" content="Claude Code skill,通过自然语言生成专业 draw.io 图表:6 种预设、ML/DL 支持、代码库可视化、10,000+ 官方形状、321 个 AI/LLM 品牌图标、自检循环。导出 PNG/SVG/PDF/JPG。">
+ <meta name="description" content="Claude Code skill,通过自然语言生成专业 draw.io 图表:11 种预设、ML/DL 支持、代码库可视化、10,000+ 官方形状、321 个 AI/LLM 品牌图标、自检循环。导出 PNG/SVG/PDF/JPG。">
<meta name="theme-color" content="#0d1117">
<link rel="canonical" href="https://agents365-ai.github.io/drawio-skill/zh.html">
<link rel="alternate" hreflang="zh" href="https://agents365-ai.github.io/drawio-skill/zh.html">
<link rel="alternate" hreflang="en" href="https://agents365-ai.github.io/drawio-skill/">
<meta property="og:title" content="drawio-skill — 从文本到专业图表">
- <meta property="og:description" content="通过自然语言生成专业 draw.io 图表:6 种预设、代码库可视化、10,000+ 官方形状、321 个 AI/LLM 品牌图标、自检循环。">
+ <meta property="og:description" content="通过自然语言生成专业 draw.io 图表:11 种预设、代码库可视化、10,000+ 官方形状、321 个 AI/LLM 品牌图标、自检循环。">
<meta property="og:type" content="website">
<meta property="og:url" content="https://agents365-ai.github.io/drawio-skill/zh.html">
<meta property="og:image" content="https://raw.githubusercontent.com/Agents365-ai/drawio-skill/main/assets/demo-star-cn.png">
@@ -202,7 +202,7 @@
<!-- Hero -->
<div class="hero">
<div class="container">
- <div class="hero-badge">v1.14.0 &mdash; 代码库可视化、形状搜索、AI &amp; 数据图标</div>
+ <div class="hero-badge">v1.32.0 &mdash; 代码库可视化、形状搜索、AI &amp; 数据图标</div>
<h1>drawio-<span>skill</span></h1>
<p>从文本到专业图表。通过自然语言生成 draw.io 文件 &mdash; 也能把现有代码库变成结构图 &mdash; 支持自检、迭代优化、10,000+ 官方形状和 AI/LLM 品牌图标。</p>
<div class="hero-install">
@@ -248,8 +248,8 @@
</div>
<div class="feature-card">
<div class="feature-icon">&#x1F4CB;</div>
- <h3>6 种图表预设</h3>
- <p>ERD、UML 类图、序列图、架构图、ML/深度学习、流程图 &mdash; 每种都有预设形状、样式和布局规范。</p>
+ <h3>11 种图表预设</h3>
+ <p>ERD、UML 类图、序列图、C4、架构图、ML/深度学习、流程图、SysML、BPMN、网络拓扑、跨职能泳道图 &mdash; 每种都有预设形状、样式和布局规范。</p>
</div>
<div class="feature-card">
<div class="feature-icon">&#x1F9E0;</div>
@@ -338,7 +338,7 @@
<tbody>
<tr><td>导出后自检</td><td class="cross">&#x2717;</td><td class="check">&#x2713; 2 轮自动修复</td></tr>
<tr><td>迭代反馈循环</td><td class="cross">&#x2717;</td><td class="check">&#x2713; 5 轮定向编辑</td></tr>
- <tr><td>图表类型预设</td><td class="cross">&#x2717;</td><td class="check">&#x2713; 6 种预设(ERD、UML、序列、架构、ML、流程)</td></tr>
+ <tr><td>图表类型预设</td><td class="cross">&#x2717;</td><td class="check">&#x2713; 11 种预设(ERD、UML、序列、C4、架构、ML、流程、SysML、BPMN、网络、泳道)</td></tr>
<tr><td>ML 模型图</td><td class="cross">&#x2717;</td><td class="check">&#x2713; 张量标注、层配色</td></tr>
<tr><td>动画连接线</td><td class="cross">&#x2717;</td><td class="check">&#x2713; flowAnimation=1</td></tr>
<tr><td>网格对齐布局</td><td class="cross">&#x2717;</td><td class="check">&#x2713; 10px 对齐</td></tr>
diff --git a/skillspector-baseline.txt b/skillspector-baseline.txt
new file mode 100644
index 0000000..da7e9ff
--- /dev/null
+++ b/skillspector-baseline.txt
@@ -0,0 +1,335 @@
+
+╭──────────────────────────────────────────────────────────────────────────────╮
+│ SkillSpector Security Report │
+╰────────────────────────────────── v2.3.11 ───────────────────────────────────╯
+
+Skill: drawio-skill
+Source: /Users/niehu/myagents/myskills/drawio-skill/skills/drawio-skill
+Scanned: 2026-07-13 16:28:47 UTC
+
+
+ Risk Assessment
+ Score 100/100
+ Severity CRITICAL
+ Recommendation DO NOT INSTALL
+
+
+ Components (51)
+┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━┳━━━━━━━┳━━━━━━━━━━━━┓
+┃ File ┃ Type ┃ Lines ┃ Executable ┃
+┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━╇━━━━━━━╇━━━━━━━━━━━━┩
+│ SKILL.md │ markdown │ 338 │ No │
+│ data/SHAPE-INDEX-NOTICE.md │ markdown │ 17 │ No │
+│ data/lobe-icons.json │ json │ 878 │ No │
+│ data/shape-index.json.gz │ other │ 11700 │ No │
+│ references/autolayout.md │ markdown │ 163 │ No │
+│ references/diagram-types.md │ markdown │ 205 │ No │
+│ references/live-infra.md │ markdown │ 71 │ No │
+│ references/mermaid-authoring.md │ markdown │ 56 │ No │
+│ references/shapes.md │ markdown │ 151 │ No │
+│ references/style-extraction.md │ markdown │ 255 │ No │
+│ references/style-presets.md │ markdown │ 115 │ No │
+│ references/toolbox.md │ markdown │ 95 │ No │
+│ references/troubleshooting.md │ markdown │ 63 │ No │
+│ references/xml-authoring.md │ markdown │ 205 │ No │
+│ scripts/aiicons.py │ python │ 204 │ Yes │
+│ ... and 36 more │ │ │ │
+└─────────────────────────────────┴──────────┴───────┴────────────┘
+
+
+Issues (44)
+
+ MEDIUM: AST4 - subprocess module call...
+ Location: scripts/autolayout.py:159–162
+ Confidence: 70%
+ Remediation: Use subprocess.run() with shell=False and an explicit argument
+list. Validate all inputs and avoid passing user-controlled data to commands....
+
+ MEDIUM: AST4 - subprocess module call...
+ Location: scripts/drawio2pptx.py:46–48
+ Confidence: 70%
+ Remediation: Use subprocess.run() with shell=False and an explicit argument
+list. Validate all inputs and avoid passing user-controlled data to commands....
+
+ MEDIUM: AST4 - subprocess module call...
+ Location: scripts/drawiohtml.py:57–58
+ Confidence: 70%
+ Remediation: Use subprocess.run() with shell=False and an explicit argument
+list. Validate all inputs and avoid passing user-controlled data to commands....
+
+ MEDIUM: AST4 - subprocess module call...
+ Location: scripts/goimports.py:82–83
+ Confidence: 70%
+ Remediation: Use subprocess.run() with shell=False and an explicit argument
+list. Validate all inputs and avoid passing user-controlled data to commands....
+
+ MEDIUM: AST4 - subprocess module call...
+ Location: scripts/jsimports.py:96–97
+ Confidence: 70%
+ Remediation: Use subprocess.run() with shell=False and an explicit argument
+list. Validate all inputs and avoid passing user-controlled data to commands....
+
+ MEDIUM: AST4 - subprocess module call...
+ Location: scripts/pyclasses.py:78–79
+ Confidence: 70%
+ Remediation: Use subprocess.run() with shell=False and an explicit argument
+list. Validate all inputs and avoid passing user-controlled data to commands....
+
+ MEDIUM: AST4 - subprocess module call...
+ Location: scripts/pyimports.py:97–98
+ Confidence: 70%
+ Remediation: Use subprocess.run() with shell=False and an explicit argument
+list. Validate all inputs and avoid passing user-controlled data to commands....
+
+ MEDIUM: AST4 - subprocess module call...
+ Location: scripts/rustimports.py:150–151
+ Confidence: 70%
+ Remediation: Use subprocess.run() with shell=False and an explicit argument
+list. Validate all inputs and avoid passing user-controlled data to commands....
+
+ MEDIUM: AST4 - subprocess module call...
+ Location: scripts/svgflow.py:38–39
+ Confidence: 70%
+ Remediation: Use subprocess.run() with shell=False and an explicit argument
+list. Validate all inputs and avoid passing user-controlled data to commands....
+
+ MEDIUM: AST4 - subprocess module call...
+ Location: scripts/tfimports.py:184–185
+ Confidence: 70%
+ Remediation: Use subprocess.run() with shell=False and an explicit argument
+list. Validate all inputs and avoid passing user-controlled data to commands....
+
+ MEDIUM: AST4 - subprocess module call...
+ Location: scripts/timelapse.py:46
+ Confidence: 70%
+ Remediation: Use subprocess.run() with shell=False and an explicit argument
+list. Validate all inputs and avoid passing user-controlled data to commands....
+
+ MEDIUM: AST4 - subprocess module call...
+ Location: scripts/timelapse.py:90–93
+ Confidence: 70%
+ Remediation: Use subprocess.run() with shell=False and an explicit argument
+list. Validate all inputs and avoid passing user-controlled data to commands....
+
+ MEDIUM: AST4 - subprocess module call...
+ Location: scripts/timelapse.py:102–104
+ Confidence: 70%
+ Remediation: Use subprocess.run() with shell=False and an explicit argument
+list. Validate all inputs and avoid passing user-controlled data to commands....
+
+ MEDIUM: AST4 - subprocess module call...
+ Location: scripts/timelapse.py:108–109
+ Confidence: 70%
+ Remediation: Use subprocess.run() with shell=False and an explicit argument
+list. Validate all inputs and avoid passing user-controlled data to commands....
+
+ HIGH: TT4 - Tainted flow: 'url' from open (line 158, file read) → urllib...
+ Location: scripts/aiicons.py:161
+ Confidence: 80%
+ Remediation: Validate and filter file contents before sending over the
+network. Ensure sensitive files (credentials, configs) are never transmitted to
+external end...
+
+ HIGH: TT4 - Tainted flow: 'url' from open (line 158, file read) → urllib...
+ Location: scripts/aiicons.py:183
+ Confidence: 80%
+ Remediation: Validate and filter file contents before sending over the
+network. Ensure sensitive files (credentials, configs) are never transmitted to
+external end...
+
+ MEDIUM: LP3 - Skill has no declared permissions but code capabilities were...
+ Location: SKILL.md:1
+ Confidence: 70%
+ Remediation: Add a 'permissions' field to SKILL.md listing the capabilities
+this skill requires....
+
+ MEDIUM: MP2 - Context Window Stuffing...
+ Location: scripts/composeimports.py:86
+ Confidence: 80%
+ Remediation: Implement context-window management that detects and rejects
+padding or stuffing attempts. Prioritize system instructions over user-injected
+content....
+
+ MEDIUM: MP2 - Context Window Stuffing...
+ Location: scripts/composeimports.py:87
+ Confidence: 80%
+ Remediation: Implement context-window management that detects and rejects
+padding or stuffing attempts. Prioritize system instructions over user-injected
+content....
+
+ MEDIUM: MP2 - Context Window Stuffing...
+ Location: scripts/drawio2pptx.py:89
+ Confidence: 80%
+ Remediation: Implement context-window management that detects and rejects
+padding or stuffing attempts. Prioritize system instructions over user-injected
+content....
+
+ MEDIUM: MP2 - Context Window Stuffing...
+ Location: scripts/goimports.py:18
+ Confidence: 80%
+ Remediation: Implement context-window management that detects and rejects
+padding or stuffing attempts. Prioritize system instructions over user-injected
+content....
+
+ MEDIUM: MP2 - Context Window Stuffing...
+ Location: scripts/heatmap.py:159
+ Confidence: 80%
+ Remediation: Implement context-window management that detects and rejects
+padding or stuffing attempts. Prioritize system instructions over user-injected
+content....
+
+ MEDIUM: MP2 - Context Window Stuffing...
+ Location: scripts/pyclasses.py:19
+ Confidence: 80%
+ Remediation: Implement context-window management that detects and rejects
+padding or stuffing attempts. Prioritize system instructions over user-injected
+content....
+
+ MEDIUM: MP2 - Context Window Stuffing...
+ Location: scripts/relabel.py:59
+ Confidence: 80%
+ Remediation: Implement context-window management that detects and rejects
+padding or stuffing attempts. Prioritize system instructions over user-injected
+content....
+
+ MEDIUM: MP2 - Context Window Stuffing...
+ Location: scripts/restyle.py:64
+ Confidence: 80%
+ Remediation: Implement context-window management that detects and rejects
+padding or stuffing attempts. Prioritize system instructions over user-injected
+content....
+
+ MEDIUM: MP2 - Context Window Stuffing...
+ Location: scripts/restyle.py:153
+ Confidence: 80%
+ Remediation: Implement context-window management that detects and rejects
+padding or stuffing attempts. Prioritize system instructions over user-injected
+content....
+
+ MEDIUM: MP2 - Context Window Stuffing...
+ Location: scripts/rustimports.py:25
+ Confidence: 80%
+ Remediation: Implement context-window management that detects and rejects
+padding or stuffing attempts. Prioritize system instructions over user-injected
+content....
+
+ MEDIUM: MP2 - Context Window Stuffing...
+ Location: scripts/rustimports.py:101
+ Confidence: 80%
+ Remediation: Implement context-window management that detects and rejects
+padding or stuffing attempts. Prioritize system instructions over user-injected
+content....
+
+ MEDIUM: MP2 - Context Window Stuffing...
+ Location: scripts/shapesearch.py:134
+ Confidence: 80%
+ Remediation: Implement context-window management that detects and rejects
+padding or stuffing attempts. Prioritize system instructions over user-injected
+content....
+
+ HIGH: OH1 - Unvalidated Output Injection...
+ Location: scripts/autolayout.py:159
+ Confidence: 95%
+ Remediation: Validate and sanitize all model output before using it in
+downstream contexts. Use parameterized queries for SQL, shell quoting for
+commands, and HTML...
+
+ HIGH: OH1 - Unvalidated Output Injection...
+ Location: scripts/goimports.py:82
+ Confidence: 95%
+ Remediation: Validate and sanitize all model output before using it in
+downstream contexts. Use parameterized queries for SQL, shell quoting for
+commands, and HTML...
+
+ HIGH: OH1 - Unvalidated Output Injection...
+ Location: scripts/jsimports.py:96
+ Confidence: 95%
+ Remediation: Validate and sanitize all model output before using it in
+downstream contexts. Use parameterized queries for SQL, shell quoting for
+commands, and HTML...
+
+ HIGH: OH1 - Unvalidated Output Injection...
+ Location: scripts/pyclasses.py:78
+ Confidence: 95%
+ Remediation: Validate and sanitize all model output before using it in
+downstream contexts. Use parameterized queries for SQL, shell quoting for
+commands, and HTML...
+
+ HIGH: OH1 - Unvalidated Output Injection...
+ Location: scripts/pyimports.py:97
+ Confidence: 95%
+ Remediation: Validate and sanitize all model output before using it in
+downstream contexts. Use parameterized queries for SQL, shell quoting for
+commands, and HTML...
+
+ HIGH: OH1 - Unvalidated Output Injection...
+ Location: scripts/rustimports.py:150
+ Confidence: 95%
+ Remediation: Validate and sanitize all model output before using it in
+downstream contexts. Use parameterized queries for SQL, shell quoting for
+commands, and HTML...
+
+ HIGH: OH1 - Unvalidated Output Injection...
+ Location: scripts/svgflow.py:38
+ Confidence: 95%
+ Remediation: Validate and sanitize all model output before using it in
+downstream contexts. Use parameterized queries for SQL, shell quoting for
+commands, and HTML...
+
+ HIGH: OH1 - Unvalidated Output Injection...
+ Location: scripts/tfimports.py:184
+ Confidence: 95%
+ Remediation: Validate and sanitize all model output before using it in
+downstream contexts. Use parameterized queries for SQL, shell quoting for
+commands, and HTML...
+
+ HIGH: OH1 - Unvalidated Output Injection...
+ Location: scripts/timelapse.py:46
+ Confidence: 95%
+ Remediation: Validate and sanitize all model output before using it in
+downstream contexts. Use parameterized queries for SQL, shell quoting for
+commands, and HTML...
+
+ HIGH: OH1 - Unvalidated Output Injection...
+ Location: scripts/timelapse.py:108
+ Confidence: 95%
+ Remediation: Validate and sanitize all model output before using it in
+downstream contexts. Use parameterized queries for SQL, shell quoting for
+commands, and HTML...
+
+ HIGH: PE3 - Credential Access...
+ Location: SKILL.md:94
+ Confidence: 70%
+ Remediation: Remove references to credential paths. Use environment
+variables or secrets managers. For docs, use placeholder paths (e.g.,
+/path/to/config). Never l...
+
+ HIGH: P2 - Hidden Instructions...
+ Location: references/xml-authoring.md:16
+ Confidence: 21%
+ Remediation: Audit all comments and invisible characters. Remove any
+instructions that direct the agent to perform unauthorized actions. Use plain,
+reviewable cont...
+
+ HIGH: P2 - Hidden Instructions...
+ Location: references/xml-authoring.md:54
+ Confidence: 21%
+ Remediation: Audit all comments and invisible characters. Remove any
+instructions that direct the agent to perform unauthorized actions. Use plain,
+reviewable cont...
+
+ HIGH: P2 - Hidden Instructions...
+ Location: references/xml-authoring.md:108
+ Confidence: 21%
+ Remediation: Audit all comments and invisible characters. Remove any
+instructions that direct the agent to perform unauthorized actions. Use plain,
+reviewable cont...
+
+ HIGH: TM1 - Tool Parameter Abuse...
+ Location: references/style-presets.md:101
+ Confidence: 26%
+ Remediation: Validate all tool parameters against an allowlist. Reject
+dangerous parameter values (shell=True, --force, -rf /) and use safe
+defaults....
+
+Executable scripts: Yes