# PDF To Markdown > Convert a PDF file to Markdown (with referenced images) in the current directory using docling. Use when the user wants to turn a PDF into markdown or extract a PDF's text/content. Takes the PDF path as the single argument. Use when this capability is needed. - Skill: `tomevault-io/pdf-to-markdown` (Agent Skill, multi-file: 2 files) - Install (CLI): `npx skillmds@latest add tomevault-io/pdf-to-markdown` - Raw SKILL.md: https://api.skillmd.com/api/skills/tomevault-io/pdf-to-markdown/raw - Safety review: pending (external: skill-scanner PASS, skillspector PASS) - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: Docs & Writing - Author: tomevault-io (https://skillmd.com/u/tomevault-io) - Updated: 2026-09-17 - Page: https://skillmd.com/skills/tomevault-io/pdf-to-markdown --- ## /pdf-to-markdown Convert the PDF at `$pdf` to Markdown in the **current working directory** using docling, by running the bundled script: ```bash bash "$HOME/.claude/skills/pdf-to-markdown/convert.sh" "$pdf" ``` What to expect: - Output is written to the current directory: a `.md` file plus a folder of referenced images (image export mode is `referenced`). - docling uses the locally cached models at `~/.cache/docling/models`, so a local PDF needs no network access. - Conversion runs model inference and can take a while on large or scanned PDFs — let it finish. After it completes: - Report the generated Markdown file path and the images directory (if created). - If docling errors, surface its output verbatim rather than guessing. --- > Source: [insanum/dotfiles](https://github.com/insanum/dotfiles) — distributed by [TomeVault](https://tomevault.io).