文档转换
- 作者仓库星标 1,187
- 叉子 185
- 作者更新于 2026年6月14日 10:01
- 作者仓库 claude-code-skills
- 领域
- 设计与多媒体
- 兼容 Agent
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- 信任分
- 88 / 100 · 社区维护
- 作者 / 版本 / 许可
- @daymade · 未声明 license
- Token 消耗评级
- 低消耗
- 接入复杂程度
- 需简单配置
- 是否需要外部 API Key
- 不需要
- 兼容的系统
- Windows · WSL
- 底层运行要求
- Python
- 文件与系统权限
-
- 只读
- 允许写入 / 修改
- Shell 执行
- 网络行为
- 仅限本地
- 安装命令数
- 26 条
档案由构建时根据 SKILL.md 与安装命令自动衍生,可能与作者实际意图存在差异。
需要注意: 未限定 allowed-tools,默认拥有全部工具权限。
---
name: doc-to-markdown
description: Converts DOCX/PDF/PPTX to high-quality Markdown with automatic post-processing. Fixes pandoc gri…
category: 设计与多媒体
runtime: Python
---
# doc-to-markdown 输出预览
## PART A: 任务判断
- 适用问题:视觉内容、演示材料、信息图或设计交付。
- 输入要求:目标材料、限制条件、期望输出和验收方式。
- 证据边界:围绕“Quick Start / Dual Mode / Tool Selection”读取原文规则,不把推断写成作者承诺。
## PART B: 执行结果
- **01** 任务判断:确认你的需求是否属于视觉内容、演示材料、信息图或设计交付,并标出输入、限制和预期结果。
- **02** 执行计划:优先按“Quick Start / Dual Mode / Tool Selection”拆成步骤,说明每一步会读取什么、修改什么、产出什么。
- **03** 交付结果:给出可复制的命令、文件改动、检查清单或内容草稿,并说明如何继续迭代。
- **04** 风险边界:结合 读取文件、写入/修改文件、执行终端命令、主要在本地完成、通常不需要额外 API Key 给出执行前确认项。
## Running Rules
- 读取文件、写入/修改文件、执行终端命令;主要在本地完成;通常不需要额外 API Key。
- 先小样例验证,再放大到真实任务。
- 交付时同时给结果、检查口径和下一步迭代建议。 原文出现了 `/mnt`、`/daymade-docs`、`/fact-checker` 这类斜杠命令;如果你的 Agent 支持命令触发,优先用命令开场,再补充目标和边界。
告诉 Agent 目标文件或材料、期望结果、不可改范围、是否允许联网或执行命令。本 Skill 的权限画像是:读取文件、写入/修改文件、执行终端命令。
先用一个小任务确认它会围绕“Quick Start / Dual Mode / Tool Selection”工作;涉及文件或命令时,先看 diff、日志、预览或测试结果。
检查最终产物是否包含明确结果、必要证据和下一步动作;如果输出泛泛而谈,就补充输入、边界和验收标准后重跑。
---
name: doc-to-markdown
description: Converts DOCX/PDF/PPTX to high-quality Markdown with automatic post-processing. Fixes pandoc gri…
category: 设计与多媒体
source: daymade/claude-code-skills
---
# doc-to-markdown
## 什么时候使用
- doc-to-markdown 是设计与多媒体方向的技能,让 Agent 直接产出图、卡、视觉素材 适合处理界面、视觉、封面、信息图或演示材料交付,核心价值是把输入、判断、执行、验证和交付边界固定下来,避免 Agent 泛泛回答。 把任…
- 面向视觉内容、演示材料、信息图或设计交付,优先处理能明确输入、步骤和验收标准的工作。
## 需要提供什么
- 目标材料、目录范围、期望结果和不可改动内容。
- 是否允许联网、执行命令、读写文件或调用外部服务。
## 执行规则
- 围绕「Quick Start / Dual Mode / Tool Selection」组织步骤,不把推断写成作者事实。
- 读取文件、写入/修改文件、执行终端命令;主要在本地完成;通常不需要额外 API Key。
- 先跑小样例,确认结果可检查后再扩大任务范围。
## 输出要求
- 给出最终产物、关键证据、验证方式和下一步动作。
- 信息不足时标记 unknown,不编造命令、平台或依赖。 作者原文负责流程事实;仓库文件负责来源和命令;流狐只补充适用场景、限制和质量判断。
skill "doc-to-markdown" {
输入层 -> 用户目标 + 目标文件 + 禁止范围 + 验收标准
上下文层 -> Quick Start / Dual Mode / Tool Selection
规则层 -> SKILL.md 触发条件 / 执行顺序 / 输出格式
运行层 -> Python | 读取文件、写入/修改文件、执行终端命令 | 主要在本地完成
安全层 -> 通常不需要额外 API Key + 小任务验证 + diff / 日志复核
输出层 -> 可复制结果 + 检查清单 + 下一步迭代
} Doc to Markdown
Convert documents to high-quality markdown with intelligent multi-tool orchestration and automatic DOCX post-processing.
Architecture: Pandoc (best-in-class extraction) + 8 post-processing fixes (our value-add).
Quick Start
# DOCX → Markdown (one command, zero manual fixes)
uv run --with pymupdf4llm --with markitdown scripts/convert.py document.docx -o output.md --assets-dir ./media
# PDF → Markdown
uv run --with pymupdf4llm --with markitdown scripts/convert.py document.pdf -o output.md
# Run tests
uv run --with pytest pytest scripts/test_convert.py -v
Dual Mode
| Mode | Speed | Quality | Use Case |
|---|---|---|---|
| Quick (default) | Fast | Good | Drafts, simple documents |
| Heavy | Slower | Best | Final documents, complex layouts |
Tool Selection
| Format | Quick Mode | Heavy Mode |
|---|---|---|
| pymupdf4llm | pymupdf4llm + markitdown | |
| DOCX | pandoc + post-processing | pandoc + markitdown |
| PPTX | markitdown | markitdown + pandoc |
| XLSX | markitdown | markitdown |
DOCX Post-Processing (automatic)
When converting DOCX via pandoc, 8 cleanups are applied automatically:
| Problem | Fix | Test coverage |
|---|---|---|
Grid tables (+:---+) |
Single-column → blockquote, multi-column → pipe table | TestPostprocessPipeline |
Simple tables ( ---- ----) |
Multi-column images → pipe table with captions | TestSimpleTable |
Image path nesting (media/media/) |
Flatten to media/, absolute → relative |
test_stats_tracking |
Pandoc attributes ({width="..."}) |
Removed | test_pandoc_attributes_removed |
CJK bold spacing (**粗体**中文) |
Add space around ** for CJK bold spans |
TestCjkBoldSpacing (15 cases) |
| Indented dashed code blocks | → fenced ``` with language detection | test_code_block_with_language |
Escaped brackets (\[...\]) |
→ [...] |
test_escaped_brackets_fixed |
Double-bracket links ([[text]](url)) |
→ [text](url) |
test_double_bracket_links_fixed |
CJK Bold Spacing — why and how
DOCX uses run-level styling (no spaces between bold/normal runs in CJK text). Markdown renderers need whitespace around ** to recognize bold boundaries.
Rule: if a **content** span contains any CJK character, ensure both sides have a space — unless already spaced or at line boundary. This handles CJK punctuation, emoji adjacency, and mixed content.
Before: 打开**飞书**,就可以 → some renderers fail to bold
After: 打开 **飞书** ,就可以 → universally renders correctly
Heavy Mode Workflow
Heavy Mode runs multiple tools in parallel and selects the best segments:
- Parallel Execution: Run all applicable tools simultaneously
- Segment Analysis: Parse each output into segments (tables, headings, images, paragraphs)
- Quality Scoring: Score each segment based on completeness and structure
- Intelligent Merge: Select best version of each segment across tools
Merge Criteria
| Segment Type | Selection Criteria |
|---|---|
| Tables | More rows/columns, proper header separator |
| Images | Alt text present, local paths preferred |
| Headings | Proper hierarchy, appropriate length |
| Lists | More items, nested structure preserved |
| Paragraphs | Content completeness |
Image Extraction
# Extract images with metadata
uv run --with pymupdf scripts/extract_pdf_images.py document.pdf -o ./extracted-images
# Generate markdown references file
uv run --with pymupdf scripts/extract_pdf_images.py document.pdf --markdown refs.md
Output:
- Images:
extracted-images/img_page1_1.png,extracted-images/img_page2_1.jpg - Metadata:
extracted-images/images_metadata.json(page, position, dimensions)
Quality Validation
# Validate conversion quality
uv run --with pymupdf scripts/validate_output.py document.pdf output.md
# Generate HTML report
uv run --with pymupdf scripts/validate_output.py document.pdf output.md --report report.html
Quality Metrics
| Metric | Pass | Warn | Fail |
|---|---|---|---|
| Text Retention | >95% | 85-95% | <85% |
| Table Retention | 100% | 90-99% | <90% |
| Image Retention | 100% | 80-99% | <80% |
Merge Outputs Manually
# Merge multiple markdown files
python scripts/merge_outputs.py output1.md output2.md -o merged.md
# Show segment attribution
python scripts/merge_outputs.py output1.md output2.md -o merged.md --verbose
Path Conversion (Windows/WSL)
# Windows to WSL conversion
python scripts/convert_path.py "C:\Users\<windows-user>\Documents\file.pdf"
# Output: /mnt/c/Users/<windows-user>/Documents/file.pdf
Common Issues
"No conversion tools available"
# Install all tools
pip install pymupdf4llm
uv tool install "markitdown[pdf]"
brew install pandoc
FontBBox warnings during PDF conversion
- Harmless font parsing warnings, output is still correct
Images missing from output
- Use Heavy Mode for better image preservation
- Or extract separately with
scripts/extract_pdf_images.py
Tables broken in output
- Use Heavy Mode - it selects the most complete table version
- Or validate with
scripts/validate_output.py
Bundled Scripts
| Script | Purpose |
|---|---|
convert.py |
Main orchestrator with Quick/Heavy mode + DOCX post-processing |
test_convert.py |
31 tests covering all post-processing functions |
merge_outputs.py |
Merge multiple markdown outputs |
validate_output.py |
Quality validation with HTML report |
extract_pdf_images.py |
PDF image extraction with metadata |
convert_path.py |
Windows to WSL path converter |
References
references/benchmark-2026-03-22.md- 5-tool benchmark (Docling/MarkItDown/Pandoc/Mammoth/ours)references/heavy-mode-guide.md- Detailed Heavy Mode documentationreferences/tool-comparison.md- Tool capabilities comparisonreferences/conversion-examples.md- Batch operation examples
Next Step: Clean Up Converted Content
After converting documents to markdown, suggest cleanup:
Conversion complete: [N] files converted to markdown.
Options:
A) Clean up docs — run /daymade-docs:docs-cleaner to consolidate redundant content (Recommended if multiple files)
B) Check facts — run /fact-checker to verify claims in the converted content
C) No thanks — the markdown conversion is sufficient
先判断是否适合
作者设计意图
作者的方法与取舍
边界和复核