Document Parse

by Youchu-lawhub

Document Parse is an Automation skill for Claude Code, published by Youchu-lawhub in cn-litigation-toolkit.

19 stars2 forkson Youchu-lawhub/cn-litigation-toolkitAdded 2026/08/11+12% in starsRepository updated 2026/07/11

View source on GitHub Download repo ZIP

agent-skillschinese-lawcivil-proceduredocxelement-analysislegallegal-techlitigationmcprequest-right-basis

Install in seconds

Install Document Parse

Copy Document Parse into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/Youchu-lawhub/cn-litigation-toolkit/tree/main/skills/document-parse ~/.claude/skills/document-parse

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/Youchu-lawhub/cn-litigation-toolkit.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: skills/document-parse/SKILL.md in Youchu-lawhub/cn-litigation-toolkit
Installs to: ~/.claude/skills/document-parse
Collection: One of 23 skills cataloged from this repository
Category: Automation — 1523 skills

What Document Parse does

Parse PDFs, images, Word, and PPT files into structured Markdown for downstream legal analysis. Supports multi-backend parsing with fallback chains; used as the unified input layer for the cn-litigation-toolkit suite.

Document Parse is cataloged under Automation on DirSkills. Document Parse comes from a repository tagged agent-skills, chinese-law, civil-procedure, docx and element-analysis.

Documentation

README

Excerpt

文档解析（document-parse）· 输入侧解析入口

本技能是本套件读取上传文件的统一前门。任何需要把用户提供的 PDF/图片/Word/PPT 转成可分析文本的技能，在拿到上传文件后、进入分析或起草之前，先经本技能解析为 Markdown，再把结构化文本交回原技能。

与 /legal-verification（输出侧必过闸门）对称：/legal-verification 守"出"，/document-parse 守"入"。

本技能只负责"把文件变成可读的 md"，不做法律分析、不做内容删改、不臆造文档内容。

0 | 两种调用模式

模式一：自动入口（其他技能调用，默认）

收到上传文件 → 【document-parse入口】→ 选定后端 → 解析为 Markdown
   ├─ 成功 → 把 md（含表格/公式/正文）交回原技能继续分析/起草
   └─ 失败 → 按降级链逐级回退；全部失败则停下报告，不静默兜底

入口为默认、不可静默跳过（与 profile.md「共享护栏 #3」「标准管线」一致）。

模式二：独立解析（用户直接调用）

用户给出文件路径或上传文件并要求"解析/转 Markdown/提取内容"，执行完整解析流程并返回结果，不进入后续法律分析。

This is the opening of the README. Read the full README on GitHub.

Commands Document Parse provides

Slash commands named in this skill’s SKILL.md, listed in the order they first appear.

/legal-verification
/document-parse

Frequently asked about Document Parse

What else does Youchu-lawhub publish alongside Document Parse?
Document Parse is one of 23 skills that DirSkills catalogs from Youchu-lawhub/cn-litigation-toolkit, the repository it ships in. Its siblings there include Agency Opinion, Asset Discovery and Case Facts. Each one is a separate skill with its own page in this directory, installs the same way Document Parse does, and is maintained by Youchu-lawhub in that same repository. The rest of the collection is listed on the Youchu-lawhub/cn-litigation-toolkit page.
How does Document Parse compare to other Automation skills?
Document Parse ranks #1494 by stars among the 1523 Automation skills in this catalog. The most-starred ones next to it are Autonomous Loops, Autonomous Agent Harness and Automation Audit Ops. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Document Parse against them. Open each page to compare what they document and how they install.