将 PDF/PPT/Excel/Word 等多格式文档解析为结构化 Markdown,并输出元数据与解析置信度,作为 RAG 与四色卡片的数据底座。
Scanned 9/2/2026
Install to Claude Code
npx -y skills add anbeime/skill --skill doc-parse --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Doc Parse?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/anbeime-doc-parse)More formats (shields.io, HTML) on the badges page.
---
name: doc-parse
description: 将 PDF/PPT/Excel/Word 等多格式文档解析为结构化 Markdown,并输出元数据与解析置信度,作为 RAG 与四色卡片的数据底座。
assign_when: 该 Worker 负责把任意格式的原始文档转成机器可读的结构化文本,是下游信息抽取与检索的通用解析入口。
---
# 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)。
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.