aliceisjustplaying

Claude Skill PDF To Markdown — Documentation skill for Claude Code

Documentation community

Convert PDF documents to clean, structured Markdown with table and image extraction.

How to install Claude Skill PDF To Markdown

This entry records only its repository, not the path inside it, so there is no exact command to give. Open aliceisjustplaying/claude-skill-pdf-to-markdown and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Claude Skill PDF To Markdown does

Convert PDF documents to clean, structured Markdown with table and image extraction.

Alternatives in Documentation

  • PDF — Extract text, create PDFs, merge/split documents, and handle forms 94.1k ★
  • Notion Knowledge Capture — Convert conversations into structured, searchable Notion wiki entries 14.6k ★
  • Repo Recap — Generate a structured recap of the repository state: open PRs, open issues, recent releases, and executive sum 11.9k ★

README

PDF to Markdown Converter

Convert PDF documents to clean, structured Markdown with table and image extraction.

Features

  • Text extraction with formatting preservation (headers, bold, italic, lists)
  • Table extraction with two modes:
    • Fast mode: PyMuPDF (good for simple tables)
    • Accurate mode: IBM Docling AI (better for complex/borderless tables)
  • Image extraction to cache directory with paths in output
  • Aggressive caching - extract once, reuse forever

Installation

cd ~/.claude/skills/pdf-to-markdown
uv venv .venv

# For fast mode (default):
uv pip install --python .venv/bin/python pymupdf pymupdf4llm

# For --docling mode (high-accuracy tables):
uv pip install --python .venv/bin/python pymupdf docling docling-core

Usage

# Basic conversion (outputs to document.md)
.venv/bin/python scripts/pdf_to_md.py document.pdf

# High-accuracy tables (slower)
.venv/bin/python scripts/pdf_to_md.py document.pdf --docling

# Custom output path
.venv/bin/python scripts/pdf_to_md.py document.pdf output.md

Options

Option Description
--docling Use Docling AI for high-accuracy tables
--no-progress Disable progress indicator
--clear-cache Clear cache for this PDF and re-extract
--clear-all-cache Clear entire cache
--cache-stats Show cache statistics

Project Structure

scripts/
  pdf_to_md.py    # Main CLI tool
  extractor.py    # PDF extraction library (fast + accurate modes)

Cache

PDFs are cached in `~/.cache/pdf-to-markdown/`. Cache is invalidated when:

  • Source PDF is modified
  • Extractor version changes
  • Explicitly cleared with --clear-cache

License

MIT