antinet-doc-parse – Documents & Office skill for AI agents
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!
Install the antinet-doc-parse skill with one command
Pick the tool you use, copy the command and paste it in your terminal. The skill lands in that tool's skills folder and is ready in your next session.
Claude Code
mkdir -p ~/.claude/skills && curl -fsSL https://skill.dn1nguoi.com/z/antinet-doc-parse-026e1.tgz | tar xz -C ~/.claude/skills
Call it in Claude Code: /antinet-doc-parse – then describe the task you want done.
Codex
mkdir -p ~/.codex/skills && curl -fsSL https://skill.dn1nguoi.com/z/antinet-doc-parse-026e1.tgz | tar xz -C ~/.codex/skills
Call it in Codex: $antinet-doc-parse – then describe the task you want done.
Hermes Agent
mkdir -p ~/.hermes/skills && curl -fsSL https://skill.dn1nguoi.com/z/antinet-doc-parse-026e1.tgz | tar xz -C ~/.hermes/skills
Call it in Hermes Agent: /antinet-doc-parse – then describe the task you want done.
DeepSeek
mkdir -p ~/.deepcode/skills && curl -fsSL https://skill.dn1nguoi.com/z/antinet-doc-parse-026e1.tgz | tar xz -C ~/.deepcode/skills
Call it in DeepSeek: /antinet-doc-parse – then describe the task you want done.
SKILL.md content
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)。
Related skills
- baoyu-danger-x-to-markdown – Converts X (Twitter) tweets and articles to markdown with YAML front matter. Uses…
- baoyu-format-markdown – Formats plain text or markdown files with frontmatter, titles, summaries, headings…
- law-to-markdown – 律师助理与法律助手在处理繁杂法条时,当需要将 PDF/Word/TXT 格式的法律规范文件转为结构化 Markdown 时适用。自动完成 OCR…
- documentation-and-adrs – Records decisions and documentation. Use when you need to document an architecture…
- baoyu-markdown-to-html – Converts Markdown to styled HTML with WeChat-compatible themes. Supports code…
- paperjsx – Generate PPTX presentations, DOCX documents, XLSX spreadsheets, and PDF reports from…
- akf-trust-metadata – The AI native file format. EXIF for AI — stamps every file with trust scores, source…
- board-prep – Board meeting preparation for the adversarial scenario, not the friendly one. Forces…