Skip to content
cccskills
FreePublished on GitHub

antinet-doc-parse

Convert PDF, Word, and Excel documents into structured Markdown for search and knowledge bases. The skill tries three parsers in sequence when needed and returns metadata, a confidence score, and the parser used.

OriginalShow the original description

软件开发工程师与数据科学家在构建RAG系统时,当需处理PDF/Word/Excel等多格式复杂文档,用此技能可自动触发三级解析降级,一键输出高置信度结构化Markdown与元数据,免去繁琐清洗,直接夯实企业知识库数据底座!

Works withExcel
See how to install

Good for

  • Prepare documents for retrieval-augmented generation
  • Structure documents for an internal knowledge base
  • Extract structured text from contracts
  • Identify parsing results that need human review

Files included (3)

  • SKILL.md2.2 KB
  • LICENSE3.0 KB
  • scripts/run_doc_parse.py2.2 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

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。

复赛代码包执行(runnable package)

  • 真实入口:scripts/run_doc_parse.py
  • 执行等价于 core.runtime.AgentSession.run_stage("doc-parse"),调用 archive.mijuanfang.MiJuanFangAgent(三级解析 fallback,纯 Python 可离线)。
  • 运行:python skills/doc-parse/scripts/run_doc_parse.py
  • 产物:examples/snse_survey/skill_outputs/doc_parse.json(解析结果 + 置信度 + fallback 信息)。

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

agent-team

FreeSummary

Organize AI agents into execution, management, and review roles for complex projects. Choose preset or custom teams, share project context and decisions, and combine their discussions and work into meeting records, feasibility reports, or implementation outputs.

  • Reviewing a technical architecture from several perspectives
  • Discussing product pricing across market and cost considerations
  • Assessing a new product's feasibility
anbeime/skill8.3KUpdated Oct 18, 2026

Generate character images, backgrounds, synthetic speech, and music for product videos featuring 小省导购员, a digital shopping presenter. Coordinate these assets with InfiniteTalk to produce a 25-second vertical video made from five scenes.

  • Producing a 25-second vertical product presentation video
  • Generating reference images for the 小省导购员 character
  • Creating business setting backgrounds for a video
anbeime/skill8.3KUpdated Oct 18, 2026

Organize parsed documents into four color-coded cards covering facts, explanations, risks, and actions. Preserve source references and generation details so readers can review evidence, identify uncertainty, and consider next steps in research, financial, or legal analysis.

  • Separating facts from interpretations in financial reports
  • Organizing evidence and risks in legal documents
  • Turning research documents into evidence-linked analysis cards
anbeime/skill8.3KUpdated Oct 18, 2026

Record operations across multiple AI agents and connect events into a traceable history. Search records by tracking ID, time window, or responsible component to support audits and investigations, with local storage available when the vector database fails.

  • Trace task dispatch and execution across agents
  • Search audit records by time or responsible component
  • Keep recording events during vector database failures
anbeime/skill8.3KUpdated Oct 18, 2026

Screen documents and external URLs before they enter a processing workflow. Check blocked domains and document permissions, then produce a pass or reject decision, a risk report, and a tracking ID for later review.

  • Screening documents before adding them to a knowledge base
  • Checking external URLs against a domain blocklist
  • Reviewing document permissions before processing
anbeime/skill8.3KUpdated Oct 18, 2026

archify

FreeSummary

Turn plain-language descriptions or Mermaid diagrams into interactive, standalone HTML diagrams of systems, workflows, API exchanges, data flows, and state changes. Validate layouts, explore relationships, switch themes, and export diagrams as images or video.

  • Explain system components and their relationships
  • Visualize workflows and approval steps
  • Map API calls and data pipelines
anbeime/skill8.3KUpdated Oct 18, 2026

See all skills by anbeime

Report a problem with this skill