📄
DataPython

Antinet Doc Parse

by anbeime

Antinet Doc Parse is a Data skill for Claude Code, published by anbeime in skill.

5.3K stars519 forkson anbeime/skillAdded 2026/08/16+3% in starsRepository updated 2026/08/16
claude-skillsfinance-skillgemini-skillshermes-skilloffice-skillopenclaw-skillsskillskill-mdskills
Install in seconds
Install Antinet Doc Parse
Copy Antinet Doc 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/anbeime/skill/tree/main/skills/antinet-doc-parse ~/.claude/skills/antinet-doc-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/anbeime/skill.git

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

In this catalog

Source file
skills/antinet-doc-parse/SKILL.md in anbeime/skill
Installs to
~/.claude/skills/antinet-doc-parse
Collection
One of 23 skills cataloged from this repository
Category
Data668 skills

What Antinet Doc Parse does

Antinet Doc Parse converts PDF, PPT, Excel, and Word files into structured Markdown with metadata and confidence scores. Use it as a data foundation for RAG pipelines and knowledge-card generation.

Antinet Doc Parse is cataloged under Data on DirSkills. Antinet Doc Parse comes from a repository tagged claude-skills, finance-skill, gemini-skills, hermes-skill and office-skill.

Documentation

README

多格式文档解析 Skill(密卷房)

使用方式

  • 由密卷房 Worker 在收到已通过安全扫描的文件时调用。
  • 三级 fallback 依次尝试,输出最终结构化结果与置信度。

输入(Input)

  • file_path:已通过 security-scan 的本地文件路径
  • formats:(可选)期望支持的格式白名单,默认全格式

输出(Output)

  • markdown:结构化 Markdown 正文
  • metadata:标题、页数、表格数、作者等元数据
  • confidence:0–1 解析置信度
  • fallback_used:最终生效的解析器名称

依赖(Dependencies)

  • MinerU(首选,强排版还原)
  • PyMuPDF(次选,PDF 快速解析)
  • pdfplumber(兜底,表格/文本抽取)
  • python-magic(类型探测)

失败处理(Failure Handling)

  • 主解析器失败 → 自动降级到下一档,直到全部尝试。
  • 三级全部失败 → 标记 人工介入,不输出残缺结果,回传 BLOCKED 给军机处。
  • 单页超大文件 → 分块解析后拼接,避免内存溢出;块级失败仅标记该块低置信度。

复用价值(Reuse Value)

  • 通用解析底座:RAG 索引、企业知识库、合同结构化均可直接复用。
  • 置信度透明:下游(通政司四色卡片)可据此决定是否需要人工复核,降低幻觉风险。

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

Frequently asked about Antinet Doc Parse

  • What else does anbeime publish alongside Antinet Doc Parse?

    Antinet Doc Parse is one of 23 skills that DirSkills catalogs from anbeime/skill, the repository it ships in. Its siblings there include Agent Team, AgentKit Multimedia Shopping and Antinet Four Color Cards. Each one is a separate skill with its own page in this directory, installs the same way Antinet Doc Parse does, and is maintained by anbeime in that same repository. The rest of the collection is listed on the anbeime/skill page.

  • How does Antinet Doc Parse compare to other Data skills?

    Antinet Doc Parse ranks #173 by stars among the 668 Data skills in this catalog. The most-starred ones next to it are Benchmark Methodology, Jupyter Notebook and Solana. 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 Antinet Doc Parse against them. Open each page to compare what they document and how they install.

More from anbeime/skill

Antinet Doc Parse is one of 23 skills cataloged on DirSkills from anbeime/skill.

See all 23 skills
👥
2w ago

Agent Team

Agent Team provides a framework for managing and combining multiple AI agent roles into task-oriented teams with real-time communication and shared memory. Use it when coordinating multiple agents for meetings, system building, or complex projects.
AI Engineering
5.3K519
🎬
2w ago

AgentKit Multimedia Shopping

AgentKit Multimedia Shopping generates digital human shopping guide videos by orchestrating AI image, voice, music, and video generation into a 9:16 vertical workflow. Use it to produce e-commerce digital human shopping guide videos with ByteDance agentkit multimedia samples.
Automation
5.3K519
🃏
2w ago

Antinet Four Color Cards

Antinet Four Color Cards generates four structured analysis cards—blue facts, green explanations, yellow risks, and red actions—from parsed documents and user intent, with source traceability. Used for research, finance, and legal document analysis.
Data
5.3K519
🧾
2w ago

Antinet Provenance

Antinet Provenance collects full-chain operational logs and generates traceable evidence chains and vector indexes for multi-agent system observability and security auditing. Use it to record key operation events, query audit trails by trace ID or time window, and support rollback and compliance.
AI Engineering
5.3K519
🛡️
2w ago

Antinet Security Scan

Antinet Security Scan performs security and compliance checks on incoming files or URLs and returns a pass/reject verdict together with a scan report. Use it as a mandatory front-line gate before any document processing.
Quality
5.3K519
🖼️
2w ago

Article Illustrator

Article Illustrator analyzes article content and generates illustrations at positions where visual aids help, such as abstract concepts, processes, or comparisons. It is used when a user asks to add images or illustrations to an article.
AI Engineering
5.3K519