AI turns documents or topics into real, native PowerPoint decks—with native shapes, transitions and animations, data-backed charts and tables on demand, audio narration from speaker notes, and support for your own .pptx templates. · by Hugo He
fix(skill): make skills/ppt-master self-contained for standalone install
hugohe3df9c1bc480ce
diff --git a/.env.example b/.env.exampleindex 8795934d..dac130da 100644--- a/.env.example+++ b/.env.example@@ -6,6 +6,15 @@# Current process environment variables take precedence over this file.# 当前文件是 image_gen.py 的可选 fallback 配置来源。# 当前进程环境变量优先于这个文件。+#+# Resolution order (only the FIRST existing file is read; keys are NOT merged across files):+# 1. ./.env in your current working directory+# 2. <repo-root>/.env (when running from a clone)+# 3. ~/.ppt-master/.env (user-level config)+# 查找顺序(只读第一个存在的文件,多个 .env 之间不合并):+# 1. 当前工作目录下的 ./.env+# 2. 仓库根目录下的 .env(仅在 clone 模式下)+# 3. ~/.ppt-master/.env(用户级配置)# Active backend (required) / 当前启用后端(必需)# Recommended core backends: openai / gemini / qwen / zhipu / volcenginediff --git a/README.md b/README.mdindex 90863c36..2a2369b8 100644--- a/README.md+++ b/README.md@@ -38,7 +38,7 @@ English | [中文](./README_CN.md)Drop in a PDF, DOCX, URL, or Markdown — get back a **natively editable PowerPoint** with real shapes, real text boxes, and real charts. Not images. Click anything and edit it.-> **Animations** — exported decks support **page transitions** and **per-element entrance animations** as real OOXML, not embedded video. Click-by-click cascade in PowerPoint and Keynote, no extra tooling. See [Animations & Transitions →](./docs/animations.md).+> **Animations** — exported decks support **page transitions** and **per-element entrance animations** as real OOXML, not embedded video. Click-by-click cascade in PowerPoint and Keynote, no extra tooling. See [Animations & Transitions →](./skills/ppt-master/references/animations.md).> **How it works** — PPT Master is a workflow (a "skill") that works inside AI IDEs like Claude Code, Cursor, VS Code + Copilot, or Codebuddy. You chat with the AI — "make a deck from this PDF" — and it follows the workflow to produce a real editable `.pptx` on your computer. No coding on your side; the IDE is just where the conversation happens.>@@ -238,7 +238,7 @@ Multiple backends are supported across Core / Extended / Experimental tiers. Run| 📖 | [SKILL.md](./skills/ppt-master/SKILL.md) | Core workflow and rules || 🎨 | [Create a Custom Template](./skills/ppt-master/workflows/create-template.md) | Standalone workflow for building your own brand or industry template || 📐 | [Canvas Formats](./skills/ppt-master/references/canvas-formats.md) | PPT 16:9, Xiaohongshu, WeChat, and 10+ formats |-| 🎬 | [Animations & Transitions](./docs/animations.md) | Page transitions and per-element entrance animations |+| 🎬 | [Animations & Transitions](./skills/ppt-master/references/animations.md) | Page transitions and per-element entrance animations || 🛠️ | [Scripts & Tools](./skills/ppt-master/scripts/README.md) | All scripts and commands || 💼 | [Examples](./examples/README.md) | 22 projects, 309 pages || 🏗️ | [Technical Design](./docs/technical-design.md) | Architecture, design philosophy, why SVG |diff --git a/docs/faq.md b/docs/faq.mdindex 8d20e0c0..f6c441c3 100644--- a/docs/faq.md+++ b/docs/faq.md@@ -66,7 +66,7 @@ python3 skills/ppt-master/scripts/svg_to_pptx.py <project> --animation mixed #python3 skills/ppt-master/scripts/svg_to_pptx.py <project> --animation fade --animation-trigger after-previous # cascade without clicks```-Full effect list, anchor logic (top-level `<g id="...">`), fallback behavior, and limitations: see [Animations & Transitions](./animations.md).+Full effect list, anchor logic (top-level `<g id="...">`), fallback behavior, and limitations: see [Animations & Transitions](../skills/ppt-master/references/animations.md).## Q: Which AI model works best?diff --git a/requirements.txt b/requirements.txtindex 7268947f..4346dde9 100644--- a/requirements.txt+++ b/requirements.txt@@ -1,99 +1,11 @@# PPT Master Dependencies / PPT Master 依赖# =============================================#-# Most tools use only the Python standard library. Below are optional dependencies.-# 大部分工具仅使用 Python 标准库,以下为可选依赖。+# Full list lives inside the skill so installing the skill alone gives full capability.+# 完整依赖列表已内置于 skill 内部,单独安装 skill 即可获得完整能力。## Install / 安装方式:-# pip install -r requirements.txt--# ─────────────────────────────────────────────────────────────-# SVG to PPTX tool / SVG 转 PPTX 工具 (skills/ppt-master/scripts/svg_to_pptx.py)-# ─────────────────────────────────────────────────────────────-# Batch-convert SVG files to PowerPoint presentations.-# 用于将 SVG 文件批量转换为 PowerPoint 演示文稿-# Uses Office-compatible mode (PNG + SVG dual format) by default, supports all Office versions.-# 默认使用 Office 兼容模式(PNG + SVG 双格式),支持所有 Office 版本-python-pptx>=0.6.21--# Office compatibility dependencies (choose one, CairoSVG preferred)-# Office 兼容模式依赖(二选一,优先使用 cairosvg)-# Converts SVG to PNG fallback images for Office LTSC 2021 etc.-# 用于将 SVG 转换为 PNG 后备图片,确保 Office LTSC 2021 等版本正常显示+# pip install -r requirements.txt # from repo root / 仓库根目录+# pip install -r skills/ppt-master/requirements.txt # from anywhere / 任意位置#-# Option A / 方案 A: CairoSVG (recommended / 推荐, ~25MB, full gradient/filter support)-# pip install cairosvg-# macOS: brew install cairo-#-# Option B / 方案 B: svglib (lightweight / 轻量, ~5MB, some gradients may be lost)-svglib>=1.5.0-reportlab>=4.0.0--# ─────────────────────────────────────────────────────────────-# PDF to Markdown tool / PDF 转 Markdown 工具 (skills/ppt-master/scripts/source_to_md/pdf_to_md.py)-# ─────────────────────────────────────────────────────────────-# Converts PDF to Markdown with text, image, and table extraction.-# 用于将 PDF 文件转换为 Markdown 格式,支持文本、图片、表格提取-PyMuPDF>=1.23.0--# ─────────────────────────────────────────────────────────────-# Document to Markdown tool / 文档转 Markdown 工具 (skills/ppt-master/scripts/source_to_md/doc_to_md.py)-# ─────────────────────────────────────────────────────────────-# Native (pure-Python) paths — no external binary required:-# 原生路径(纯 Python,无需外部程序):-# .docx → mammoth-# .html → markdownify (+ beautifulsoup4, listed below)-# .epub → ebooklib (+ markdownify)-# .ipynb → nbconvert-mammoth>=1.6.0-markdownify>=0.11.6-ebooklib>=0.18-nbconvert>=7.0.0--# ─────────────────────────────────────────────────────────────-# Excel to Markdown tool / Excel 转 Markdown 工具 (skills/ppt-master/scripts/source_to_md/excel_to_md.py)-# ─────────────────────────────────────────────────────────────-# Converts .xlsx/.xlsm workbooks to Markdown while preserving sheet structure.-# 用于将 .xlsx/.xlsm 工作簿转换为 Markdown,并保留工作表结构。-openpyxl>=3.1.0-#-# Fallback path — only needed for less common formats-# (.doc .odt .rtf .tex/.latex .rst .org .typ).-# Not required if you only convert the four native formats above.-# 备用路径 —— 仅在需要处理以下小众格式时才用到-# (.doc .odt .rtf .tex/.latex .rst .org .typ)。-# 如果只处理上述四种原生格式,无需安装。-# macOS: brew install pandoc-# Ubuntu: sudo apt install pandoc-# Windows: https://pandoc.org/installing.html--# ─────────────────────────────────────────────────────────────-# Image processing tools / 图片处理工具-# ─────────────────────────────────────────────────────────────-# fix_image_aspect.py - Fix image aspect ratio (prevent stretching during PPT shape conversion)-# fix_image_aspect.py - 修复图片宽高比(防止 PPT 转形状时拉伸)-# gemini_watermark_remover.py - Remove watermarks from Gemini-generated images-# gemini_watermark_remover.py - 去除 Gemini 生成图片的水印-Pillow>=9.0.0-numpy>=1.20.0--# ─────────────────────────────────────────────────────────────-# Web to Markdown tool / 网页转 Markdown 工具 (skills/ppt-master/scripts/source_to_md/web_to_md.py)-# ─────────────────────────────────────────────────────────────-requests>=2.31.0-beautifulsoup4>=4.12.0-# Optional — TLS fingerprint impersonation for sites that block Python's-# default TLS fingerprint (e.g., WeChat mp.weixin.qq.com). If installed,-# web_to_md.py uses it automatically; otherwise falls back to requests.-# Install this to avoid needing Node.js for WeChat / portal pages.-# 可选 —— 用于绕过 TLS 指纹屏蔽(例如微信公众号等)。装了之后 web_to_md.py-# 会自动启用;不装则回退到 requests。装了它就不必再装 Node.js。-curl_cffi>=0.7.0--# ─────────────────────────────────────────────────────────────-# AI image generation tool / AI 图片生成工具 (skills/ppt-master/scripts/image_gen.py)-# ─────────────────────────────────────────────────────────────-# Gemini backend / Gemini 后端 (IMAGE_BACKEND=gemini)-google-genai>=1.0.0-# OpenAI-compatible backend / OpenAI 兼容后端 (IMAGE_BACKEND=openai)-openai>=1.0.0+-r skills/ppt-master/requirements.txtdiff --git a/skills/ppt-master/SKILL.md b/skills/ppt-master/SKILL.mdindex 49d33209..a9b779ea 100644--- a/skills/ppt-master/SKILL.md+++ b/skills/ppt-master/SKILL.md@@ -311,7 +311,7 @@ python3 ${SKILL_DIR}/scripts/svg_to_pptx.py <project_path> -s final- `--animation-trigger {on-click,with-previous,after-previous}` — Start mode (matches PowerPoint's animation-pane Start dropdown). Default `on-click`. Use `after-previous` (with `--animation-stagger`) for click-free cascade, or `with-previous` for all-at-once.- `--auto-advance <seconds>` — kiosk-style auto-play.-Full effect list, anchor logic, and limits: [`docs/animations.md`](../../docs/animations.md).+Full effect list, anchor logic, and limits: [`references/animations.md`](references/animations.md).> ❌ **NEVER** substitute `cp` for `finalize_svg.py` — finalize performs multiple critical processing steps> ❌ **NEVER** export from `svg_output/` — MUST use `-s final` (exports from `svg_final/`)diff --git a/docs/animations.md b/skills/ppt-master/references/animations.mdsimilarity index 98%rename from docs/animations.mdrename to skills/ppt-master/references/animations.mdindex 9d627a02..13de8264 100644--- a/docs/animations.md+++ b/skills/ppt-master/references/animations.md@@ -108,4 +108,4 @@ Executors should wrap logical sections in `<g id>` regardless of whether you pla| Slower per-element reveal | `--animation-duration 0.5` || Wider gap in after-previous | `--animation-stagger 0.8` |-See also: [`scripts/docs/svg-pipeline.md`](../skills/ppt-master/scripts/docs/svg-pipeline.md) for the full `svg_to_pptx.py` reference.+See also: [`scripts/docs/svg-pipeline.md`](../scripts/docs/svg-pipeline.md) for the full `svg_to_pptx.py` reference.diff --git a/skills/ppt-master/references/shared-standards.md b/skills/ppt-master/references/shared-standards.mdindex 997a0d42..bc2f43a8 100644--- a/skills/ppt-master/references/shared-standards.md+++ b/skills/ppt-master/references/shared-standards.md@@ -314,7 +314,7 @@ python3 scripts/svg_to_pptx.py <project_path> -s final- `--animation-trigger {on-click,with-previous,after-previous}` — Start mode matching PowerPoint's animation-pane Start dropdown. Default `on-click`; `after-previous` cascades on slide entry (pace via `--animation-stagger <seconds>`); `with-previous` plays all groups together.- `--auto-advance <seconds>` — kiosk-style auto-play-Full reference: [`docs/animations.md`](../../../docs/animations.md).+Full reference: [`animations.md`](animations.md).**Prohibited**:- NEVER use `cp` as a substitute for `finalize_svg.py`diff --git a/skills/ppt-master/requirements.txt b/skills/ppt-master/requirements.txtnew file mode 100644index 00000000..7268947f--- /dev/null+++ b/skills/ppt-master/requirements.txt@@ -0,0 +1,99 @@+# PPT Master Dependencies / PPT Master 依赖+# =============================================+#+# Most tools use only the Python standard library. Below are optional dependencies.+# 大部分工具仅使用 Python 标准库,以下为可选依赖。+#+# Install / 安装方式:+# pip install -r requirements.txt++# ─────────────────────────────────────────────────────────────+# SVG to PPTX tool / SVG 转 PPTX 工具 (skills/ppt-master/scripts/svg_to_pptx.py)+# ─────────────────────────────────────────────────────────────+# Batch-convert SVG files to PowerPoint presentations.+# 用于将 SVG 文件批量转换为 PowerPoint 演示文稿+# Uses Office-compatible mode (PNG + SVG dual format) by default, supports all Office versions.+# 默认使用 Office 兼容模式(PNG + SVG 双格式),支持所有 Office 版本+python-pptx>=0.6.21++# Office compatibility dependencies (choose one, CairoSVG preferred)+# Office 兼容模式依赖(二选一,优先使用 cairosvg)+# Converts SVG to PNG fallback images for Office LTSC 2021 etc.+# 用于将 SVG 转换为 PNG 后备图片,确保 Office LTSC 2021 等版本正常显示+#+# Option A / 方案 A: CairoSVG (recommended / 推荐, ~25MB, full gradient/filter support)+# pip install cairosvg+# macOS: brew install cairo+#+# Option B / 方案 B: svglib (lightweight / 轻量, ~5MB, some gradients may be lost)+svglib>=1.5.0+reportlab>=4.0.0++# ─────────────────────────────────────────────────────────────+# PDF to Markdown tool / PDF 转 Markdown 工具 (skills/ppt-master/scripts/source_to_md/pdf_to_md.py)+# ─────────────────────────────────────────────────────────────+# Converts PDF to Markdown with text, image, and table extraction.+# 用于将 PDF 文件转换为 Markdown 格式,支持文本、图片、表格提取+PyMuPDF>=1.23.0++# ─────────────────────────────────────────────────────────────+# Document to Markdown tool / 文档转 Markdown 工具 (skills/ppt-master/scripts/source_to_md/doc_to_md.py)+# ─────────────────────────────────────────────────────────────+# Native (pure-Python) paths — no external binary required:+# 原生路径(纯 Python,无需外部程序):+# .docx → mammoth+# .html → markdownify (+ beautifulsoup4, listed below)+# .epub → ebooklib (+ markdownify)+# .ipynb → nbconvert+mammoth>=1.6.0+markdownify>=0.11.6+ebooklib>=0.18+nbconvert>=7.0.0++# ─────────────────────────────────────────────────────────────+# Excel to Markdown tool / Excel 转 Markdown 工具 (skills/ppt-master/scripts/source_to_md/excel_to_md.py)+# ─────────────────────────────────────────────────────────────+# Converts .xlsx/.xlsm workbooks to Markdown while preserving sheet structure.+# 用于将 .xlsx/.xlsm 工作簿转换为 Markdown,并保留工作表结构。+openpyxl>=3.1.0+#+# Fallback path — only needed for less common formats+# (.doc .odt .rtf .tex/.latex .rst .org .typ).+# Not required if you only convert the four native formats above.+# 备用路径 —— 仅在需要处理以下小众格式时才用到+# (.doc .odt .rtf .tex/.latex .rst .org .typ)。+# 如果只处理上述四种原生格式,无需安装。+# macOS: brew install pandoc+# Ubuntu: sudo apt install pandoc+# Windows: https://pandoc.org/installing.html++# ─────────────────────────────────────────────────────────────+# Image processing tools / 图片处理工具+# ─────────────────────────────────────────────────────────────+# fix_image_aspect.py - Fix image aspect ratio (prevent stretching during PPT shape conversion)+# fix_image_aspect.py - 修复图片宽高比(防止 PPT 转形状时拉伸)+# gemini_watermark_remover.py - Remove watermarks from Gemini-generated images+# gemini_watermark_remover.py - 去除 Gemini 生成图片的水印+Pillow>=9.0.0+numpy>=1.20.0++# ─────────────────────────────────────────────────────────────+# Web to Markdown tool / 网页转 Markdown 工具 (skills/ppt-master/scripts/source_to_md/web_to_md.py)+# ─────────────────────────────────────────────────────────────+requests>=2.31.0+beautifulsoup4>=4.12.0+# Optional — TLS fingerprint impersonation for sites that block Python's+# default TLS fingerprint (e.g., WeChat mp.weixin.qq.com). If installed,+# web_to_md.py uses it automatically; otherwise falls back to requests.+# Install this to avoid needing Node.js for WeChat / portal pages.+# 可选 —— 用于绕过 TLS 指纹屏蔽(例如微信公众号等)。装了之后 web_to_md.py+# 会自动启用;不装则回退到 requests。装了它就不必再装 Node.js。+curl_cffi>=0.7.0++# ─────────────────────────────────────────────────────────────+# AI image generation tool / AI 图片生成工具 (skills/ppt-master/scripts/image_gen.py)+# ─────────────────────────────────────────────────────────────+# Gemini backend / Gemini 后端 (IMAGE_BACKEND=gemini)+google-genai>=1.0.0+# OpenAI-compatible backend / OpenAI 兼容后端 (IMAGE_BACKEND=openai)+openai>=1.0.0diff --git a/skills/ppt-master/scripts/README.md b/skills/ppt-master/scripts/README.mdindex 2cd1d23e..855f7e8e 100644--- a/skills/ppt-master/scripts/README.md+++ b/skills/ppt-master/scripts/README.md@@ -110,6 +110,6 @@ python3 scripts/update_repo.py --skip-pip- [SVG Pipeline Tools](./docs/svg-pipeline.md)- [Image Tools](./docs/image.md)- [Troubleshooting](./docs/troubleshooting.md)-- [AGENTS Guide](../../../AGENTS.md)+- [Skill Entry](../SKILL.md)_Last updated: 2026-04-09_diff --git a/skills/ppt-master/scripts/image_backends/backend_bfl.py b/skills/ppt-master/scripts/image_backends/backend_bfl.pyindex 9f979c44..be168505 100644--- a/skills/ppt-master/scripts/image_backends/backend_bfl.py+++ b/skills/ppt-master/scripts/image_backends/backend_bfl.py@@ -145,7 +145,7 @@ def generate(prompt: str, negative_prompt: str = None,"""Generate an image with retries using the BFL backend."""api_key = require_api_key("BFL_API_KEY",- message="No API key found. Set BFL_API_KEY in the current environment or the project-root .env.",+ message="No API key found. Set BFL_API_KEY in the current environment or a .env file.",)base_url = os.environ.get("BFL_BASE_URL") or DEFAULT_BASE_URLresolved_model = model or os.environ.get("BFL_MODEL") or DEFAULT_MODELdiff --git a/skills/ppt-master/scripts/image_backends/backend_fal.py b/skills/ppt-master/scripts/image_backends/backend_fal.pyindex 790d24ac..726461ba 100644--- a/skills/ppt-master/scripts/image_backends/backend_fal.py+++ b/skills/ppt-master/scripts/image_backends/backend_fal.py@@ -95,7 +95,7 @@ def generate(prompt: str, negative_prompt: str = None,api_key = require_api_key("FAL_KEY","FAL_API_KEY",- message="No API key found. Set FAL_KEY or FAL_API_KEY in the current environment or the project-root .env.",+ message="No API key found. Set FAL_KEY or FAL_API_KEY in the current environment or a .env file.",)base_url = os.environ.get("FAL_BASE_URL") or DEFAULT_ENDPOINTresolved_model = model or os.environ.get("FAL_MODEL") or DEFAULT_MODELdiff --git a/skills/ppt-master/scripts/image_backends/backend_gemini.py b/skills/ppt-master/scripts/image_backends/backend_gemini.pyindex 962ce41d..9a3990a4 100644--- a/skills/ppt-master/scripts/image_backends/backend_gemini.py+++ b/skills/ppt-master/scripts/image_backends/backend_gemini.py@@ -163,7 +163,7 @@ def generate(prompt: str, negative_prompt: str = None,"""Gemini image generation with automatic retry.- Reads credentials from the current process environment or the project-root `.env`:+ Reads credentials from the current process environment or a `.env` file:GEMINI_API_KEYGEMINI_BASE_URLGEMINI_MODEL (optional override)@@ -186,7 +186,7 @@ def generate(prompt: str, negative_prompt: str = None,if not api_key:raise ValueError(- "No API key found. Set GEMINI_API_KEY in the current environment or the project-root .env."+ "No API key found. Set GEMINI_API_KEY in the current environment or a .env file.")if model is None:diff --git a/skills/ppt-master/scripts/image_backends/backend_ideogram.py b/skills/ppt-master/scripts/image_backends/backend_ideogram.pyindex e96176bd..7c1d4d66 100644--- a/skills/ppt-master/scripts/image_backends/backend_ideogram.py+++ b/skills/ppt-master/scripts/image_backends/backend_ideogram.py@@ -120,7 +120,7 @@ def generate(prompt: str, negative_prompt: str = None,"""Generate an image with retries using the Ideogram backend."""api_key = require_api_key("IDEOGRAM_API_KEY",- message="No API key found. Set IDEOGRAM_API_KEY in the current environment or the project-root .env.",+ message="No API key found. Set IDEOGRAM_API_KEY in the current environment or a .env file.",)base_url = os.environ.get("IDEOGRAM_BASE_URL") or DEFAULT_BASE_URLresolved_model = model or os.environ.get("IDEOGRAM_MODEL") or DEFAULT_MODELdiff --git a/skills/ppt-master/scripts/image_backends/backend_minimax.py b/skills/ppt-master/scripts/image_backends/backend_minimax.pyindex d8e4cd6e..87146fe7 100644--- a/skills/ppt-master/scripts/image_backends/backend_minimax.py+++ b/skills/ppt-master/scripts/image_backends/backend_minimax.py@@ -174,7 +174,7 @@ def generate(prompt: str, negative_prompt: str = None,"""Generate an image with retries using the MiniMax backend."""api_key = require_api_key("MINIMAX_API_KEY",- message="No API key found. Set MINIMAX_API_KEY in the current environment or the project-root .env.",+ message="No API key found. Set MINIMAX_API_KEY in the current environment or a .env file.",)base_url = os.environ.get("MINIMAX_BASE_URL") or DEFAULT_ENDPOINTresolved_model = model or os.environ.get("MINIMAX_MODEL") or DEFAULT_MODELdiff --git a/skills/ppt-master/scripts/image_backends/backend_openai.py b/skills/ppt-master/scripts/image_backends/backend_openai.pyindex 57d8a84f..a1fc0d8f 100644--- a/skills/ppt-master/scripts/image_backends/backend_openai.py+++ b/skills/ppt-master/scripts/image_backends/backend_openai.py@@ -252,7 +252,7 @@ def generate(prompt: str, negative_prompt: str = None,"""OpenAI-compatible image generation with automatic retry.- Reads credentials from the current process environment or the project-root `.env`:+ Reads credentials from the current process environment or a `.env` file:OPENAI_API_KEYOPENAI_BASE_URLOPENAI_MODEL (optional override)@@ -275,7 +275,7 @@ def generate(prompt: str, negative_prompt: str = None,if not api_key:raise ValueError(- "No API key found. Set OPENAI_API_KEY in the current environment or the project-root .env."+ "No API key found. Set OPENAI_API_KEY in the current environment or a .env file.")if model is None:diff --git a/skills/ppt-master/scripts/image_backends/backend_openrouter.py b/skills/ppt-master/scripts/image_backends/backend_openrouter.pyindex 875bb037..0ba27978 100644--- a/skills/ppt-master/scripts/image_backends/backend_openrouter.py+++ b/skills/ppt-master/scripts/image_backends/backend_openrouter.py@@ -135,7 +135,7 @@ def generate(prompt: str, negative_prompt: str = None,"""OpenRouter image generation with automatic retry.- Reads credentials from the current process environment or the project-root `.env`:+ Reads credentials from the current process environment or a `.env` file:OPENROUTER_API_KEYOPENROUTER_BASE_URLOPENROUTER_MODEL (optional override)@@ -145,7 +145,7 @@ def generate(prompt: str, negative_prompt: str = None,if not api_key:raise ValueError(- "No API key found. Set OPENROUTER_API_KEY in the current environment or the project-root .env."+ "No API key found. Set OPENROUTER_API_KEY in the current environment or a .env file.")if model is None:diff --git a/skills/ppt-master/scripts/image_backends/backend_qwen.py b/skills/ppt-master/scripts/image_backends/backend_qwen.pyindex 5b0e135a..550bb477 100644--- a/skills/ppt-master/scripts/image_backends/backend_qwen.py+++ b/skills/ppt-master/scripts/image_backends/backend_qwen.py@@ -165,7 +165,7 @@ def generate(prompt: str, negative_prompt: str = None,api_key = require_api_key("QWEN_API_KEY","DASHSCOPE_API_KEY",- message="No API key found. Set QWEN_API_KEY or DASHSCOPE_API_KEY in the current environment or the project-root .env.",+ message="No API key found. Set QWEN_API_KEY or DASHSCOPE_API_KEY in the current environment or a .env file.",)base_url = os.environ.get("QWEN_BASE_URL") or DEFAULT_ENDPOINTresolved_model = model or os.environ.get("QWEN_MODEL") or DEFAULT_MODELdiff --git a/skills/ppt-master/scripts/image_backends/backend_replicate.py b/skills/ppt-master/scripts/image_backends/backend_replicate.pyindex 76c39320..70dd4076 100644--- a/skills/ppt-master/scripts/image_backends/backend_replicate.py+++ b/skills/ppt-master/scripts/image_backends/backend_replicate.py@@ -139,7 +139,7 @@ def generate(prompt: str, negative_prompt: str = None,api_key = require_api_key("REPLICATE_API_KEY","REPLICATE_API_TOKEN",- message="No API key found. Set REPLICATE_API_KEY or REPLICATE_API_TOKEN in the current environment or the project-root .env.",+ message="No API key found. Set REPLICATE_API_KEY or REPLICATE_API_TOKEN in the current environment or a .env file.",)base_url = os.environ.get("REPLICATE_BASE_URL") or DEFAULT_BASE_URLresolved_model = model or os.environ.get("REPLICATE_MODEL") or DEFAULT_MODELdiff --git a/skills/ppt-master/scripts/image_backends/backend_siliconflow.py b/skills/ppt-master/scripts/image_backends/backend_siliconflow.pyindex bdf87abf..a8ae0b0f 100644--- a/skills/ppt-master/scripts/image_backends/backend_siliconflow.py+++ b/skills/ppt-master/scripts/image_backends/backend_siliconflow.py@@ -148,7 +148,7 @@ def generate(prompt: str, negative_prompt: str = None,"""Generate an image with retries using the SiliconFlow backend."""api_key = require_api_key("SILICONFLOW_API_KEY",- message="No API key found. Set SILICONFLOW_API_KEY in the current environment or the project-root .env.",+ message="No API key found. Set SILICONFLOW_API_KEY in the current environment or a .env file.",)base_url = os.environ.get("SILICONFLOW_BASE_URL") or DEFAULT_ENDPOINTresolved_model = model or os.environ.get("SILICONFLOW_MODEL") or DEFAULT_MODELdiff --git a/skills/ppt-master/scripts/image_backends/backend_stability.py b/skills/ppt-master/scripts/image_backends/backend_stability.pyindex d6b82941..ecba2505 100644--- a/skills/ppt-master/scripts/image_backends/backend_stability.py+++ b/skills/ppt-master/scripts/image_backends/backend_stability.py@@ -111,7 +111,7 @@ def generate(prompt: str, negative_prompt: str = None,"""Generate an image with retries using the Stability backend."""api_key = require_api_key("STABILITY_API_KEY",- message="No API key found. Set STABILITY_API_KEY in the current environment or the project-root .env.",+ message="No API key found. Set STABILITY_API_KEY in the current environment or a .env file.",)base_url = os.environ.get("STABILITY_BASE_URL") or DEFAULT_BASE_URLresolved_model = model or os.environ.get("STABILITY_MODEL") or DEFAULT_MODELdiff --git a/skills/ppt-master/scripts/image_backends/backend_volcengine.py b/skills/ppt-master/scripts/image_backends/backend_volcengine.pyindex 692f1e98..3bc20f66 100644--- a/skills/ppt-master/scripts/image_backends/backend_volcengine.py+++ b/skills/ppt-master/scripts/image_backends/backend_volcengine.py@@ -155,7 +155,7 @@ def generate(prompt: str, negative_prompt: str = None,api_key = require_api_key("VOLCENGINE_API_KEY","ARK_API_KEY",- message="No API key found. Set VOLCENGINE_API_KEY or ARK_API_KEY in the current environment or the project-root .env.",+ message="No API key found. Set VOLCENGINE_API_KEY or ARK_API_KEY in the current environment or a .env file.",)base_url = os.environ.get("VOLCENGINE_BASE_URL") or DEFAULT_ENDPOINTresolved_model = model or os.environ.get("VOLCENGINE_MODEL") or DEFAULT_MODELdiff --git a/skills/ppt-master/scripts/image_backends/backend_zhipu.py b/skills/ppt-master/scripts/image_backends/backend_zhipu.pyindex dd4c84d1..ac5c3943 100644--- a/skills/ppt-master/scripts/image_backends/backend_zhipu.py+++ b/skills/ppt-master/scripts/image_backends/backend_zhipu.py@@ -156,7 +156,7 @@ def generate(prompt: str, negative_prompt: str = None,api_key = require_api_key("ZHIPU_API_KEY","BIGMODEL_API_KEY",- message="No API key found. Set ZHIPU_API_KEY or BIGMODEL_API_KEY in the current environment or the project-root .env.",+ message="No API key found. Set ZHIPU_API_KEY or BIGMODEL_API_KEY in the current environment or a .env file.",)base_url = os.environ.get("ZHIPU_BASE_URL") or DEFAULT_ENDPOINTresolved_model = model or os.environ.get("ZHIPU_MODEL") or DEFAULT_MODELdiff --git a/skills/ppt-master/scripts/image_gen.py b/skills/ppt-master/scripts/image_gen.pyindex 3dd7966a..21e7be86 100644--- a/skills/ppt-master/scripts/image_gen.py+++ b/skills/ppt-master/scripts/image_gen.py@@ -19,9 +19,12 @@ Backend selection (`IMAGE_BACKEND` in `.env` or the current process environment)IMAGE_BACKEND=replicate -> Replicate backendIMAGE_BACKEND=openrouter -> OpenRouter backend-Configuration source:+Configuration source (process env wins, `.env` is the fallback layer):1. Current process environment variables- 2. Project-root `.env` as a fallback layer+ 2. The first `.env` found among:+ - Current working directory+ - Repo root (when running from a clone)+ - `~/.ppt-master/.env` (user-level config)Supported keys:IMAGE_BACKEND (required) backend name@@ -42,7 +45,25 @@ import sysimport argparsefrom pathlib import Path-ENV_PATH = Path(__file__).resolve().parents[3] / ".env"+def _resolve_env_path() -> Path:+ """+ Locate a `.env` file across the deploy modes PPT Master supports.++ Returns the first existing candidate; if none exist, returns the CWD path+ (used purely as a non-existent fallback so `_load_image_env_file` no-ops).+ """+ candidates = [+ Path.cwd() / ".env", # working directory (skill mode)+ Path(__file__).resolve().parents[3] / ".env", # repo root (clone mode)+ Path.home() / ".ppt-master" / ".env", # user-level config+ ]+ for candidate in candidates:+ if candidate.exists():+ return candidate+ return candidates[0]+++ENV_PATH = _resolve_env_path()IMAGE_ENV_PREFIXES = ("IMAGE_","GEMINI_",@@ -200,7 +221,7 @@ def _strip_env_quotes(value: str) -> str:def _load_image_env_file() -> None:"""- Load image generation config from the project-root `.env` as a fallback layer.+ Load image generation config from the resolved `.env` as a fallback layer.Existing process environment variables win over `.env`."""