Converts PDF files to Markdown format using PyMuPDF, extracting text content and embedded images. Fast and lightweight. Automatically fixes LaTeX umlauts (¨a â ä, etc.) and converts à to ss (Swiss German). Use when converting PDFs to Markdown, extracting document content, or processing PDF files for text analysis. Generates one .md file and 0..n .png files for images.
Install
npx skills add talent-factory/dotfiles --skill pdf-to-markdown-converternpx skills add talent-factory/dotfiles --skill pdf-to-markdown-converter -a claude-code -gnpx skills add talent-factory/dotfiles --skill pdf-to-markdown-converter -a codex -ggemini skills install https://github.com/talent-factory/dotfiles.git --path agents/claude/skills/pdf-to-markdown-convertergh skill install talent-factory/dotfiles pdf-to-markdown-convertergit clone --depth 1 https://github.com/talent-factory/dotfiles /tmp/talent-factory__dotfiles
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/talent-factory__dotfiles/agents/claude/skills/pdf-to-markdown-converter ~/.claude/skills/pdf-to-markdown-converter # Claude Code
cp -R /tmp/talent-factory__dotfiles/agents/claude/skills/pdf-to-markdown-converter ~/.agents/skills/pdf-to-markdown-converter # Codex, Cursor, Gemini CLI, Copilot, OpenCode