Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

doc-parse (Multi-format Document Parser)

Turns PDF/PPT/Excel/Word files into structured Markdown with metadata and a parsing confidence score.

Docs & OfficeIntermediate★ 6,083⑂ 585AI score 8/10Last updated: Sep 2, 2026

What it does

  • Takes a local file path and converts PDF/PPT/Excel/Word into structured Markdown.
  • Returns metadata (title, page count, table count, author) plus a 0–1 confidence score.
  • Uses a three-tier parser fallback: MinerU (best layout fidelity) → PyMuPDF (fast PDF read) → pdfplumber (table/text last resort), and reports which parser actually produced the output (fallback_used).
  • If all three tiers fail it refuses to emit partial output, flags manual intervention and returns BLOCKED. Oversized files are parsed in chunks to avoid OOM; only failing chunks get a low confidence flag.

Who it's for

  • Teams building RAG pipelines or internal knowledge bases that must normalize mixed-format documents.
  • Anyone extracting table-heavy contracts or reports while preserving structure.
  • Data/AI engineers who want confidence scores to route only risky docs to human review.

Examples

  1. Feed a 100-page business plan PDF → get Markdown with intact tables plus table-count metadata, ready for RAG chunking.
  2. Feed a poorly scanned PPT → MinerU fails, it falls back to pdfplumber, confidence is 0.4, so the doc goes to the manual review queue.
  3. Run python skills/doc-parse/scripts/run_doc_parse.py to produce examples/snse_survey/skill_outputs/doc_parse.json for the next pipeline stage.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/anbeime/skill/HEAD/antinet-agentteams/skills/doc-parse/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the antinet-agentteams/skills/doc-parse folder from the GitHub repo anbeime/skill into my ~/.claude/skills/doc-parse/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/anbeime/skill.git && mkdir -p ~/.claude/skills && cp -r skill/antinet-agentteams/skills/doc-parse ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal and clone the repo: git clone https://github.com/anbeime/skill.git
  2. Create the skills folder: mkdir -p ~/.claude/skills
  3. Copy just this skill: cp -r skill/antinet-agentteams/skills/doc-parse ~/.claude/skills/
  4. Install parsing dependencies: pip install pymupdf pdfplumber python-magic (add MinerU separately if you need high-fidelity layout recovery).
  5. Restart Claude Code and try a prompt like "parse this PDF into Markdown" to confirm the skill loads.
  6. To use the bundled script, run python skills/doc-parse/scripts/run_doc_parse.py from the cloned repo root first to verify the paths resolve.
View source on GitHub ↗