pdf-to-markdown — Claude Code skill: turn PDFs into Markdown
Turns a PDF into structured Markdown with headings, tables, lists and reading order intact. Handy when an agent needs the text of a document to work with.
npx skills add PSPDFKit-labs/nutrient-skills --skill pdf-to-markdown -a claude-codeWhat pdf-to-markdown does
This skill converts PDFs to Markdown and keeps the structure: headings, tables, lists, reading order. Two modes. Standard handles PDFs where text can be selected, and it costs nothing. Vision is meant for scans, photos, handwriting, formulas and messy layouts.
The wrapper at $SKILL_DIR/bin/pdf-to-markdown pulls the CLI from Nutrient's CDN on the first run into ~/.local/share/nutrient/cli/, then looks for updates every six hours. One file goes through with an input and an output path. Two or more files go through as an input directory and an output directory, and the CLI converts them in parallel. Add --enable-image-export to drop images into {output}_resources/ and link them from the Markdown.
Vision will not run without a Nutrient account, an API key or a CLI license key. For unattended jobs set NUTRIENT_API_KEY in the environment rather than passing it on the command line. Once Vision has connected it keeps working offline for one hour and handles up to 100 pages; a document that crosses that line still finishes. Standard keeps going even when Nutrient is unreachable. Convert each PDF once and search the saved file — running it again just burns time.
What it helps with
- pull text out of a PDF for an agent to analyse
- read a scan or an image-only PDF
- get Markdown with tables and lists out of a report
- batch-convert a folder of PDFs in one run
- extract images alongside the text
Example prompts for the agent
- Convert
report.pdfto Markdown and tell me where you saved it - This contract is a scan — run it through Vision
- Convert every PDF in
invoices/to Markdown with image export
How to install pdf-to-markdown
1Skills CLI (Vercel)
npx skills add PSPDFKit-labs/nutrient-skills --skill pdf-to-markdown -a claude-code2Manually: put the files in place
~/.claude/skills/pdf-to-markdown/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/pdf-to-markdown/
1Skills CLI (Vercel)
npx skills add PSPDFKit-labs/nutrient-skills --skill pdf-to-markdown -a codex2Manually: put the files in place
.agents/skills/pdf-to-markdown/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add PSPDFKit-labs/nutrient-skills --skill pdf-to-markdown -a cursor2Manually: put the files in place
.cursor/skills/pdf-to-markdown/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install PSPDFKit-labs/nutrient-skills pdf-to-markdown2Manually: put the files in place
.github/skills/pdf-to-markdown/SKILL.md1Skills CLI (Vercel)
npx skills add PSPDFKit-labs/nutrient-skills --skill pdf-to-markdown -a gemini-cli2Platform CLI
gemini skills install https://github.com/PSPDFKit-labs/nutrient-skills --path plugins/pdf-to-markdown/skills/pdf-to-markdownManually: put the files in place
.devin/skills/pdf-to-markdown/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add PSPDFKit-labs/nutrient-skills --skill pdf-to-markdown -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about pdf-to-markdown
How do I install pdf-to-markdown in Claude Code?
Run npx skills add PSPDFKit-labs/nutrient-skills --skill pdf-to-markdown -a claude-code. The skill file lands at ~/.claude/skills/pdf-to-markdown/SKILL.md.
What does pdf-to-markdown do?
It converts PDFs to Markdown while keeping headings, tables, lists and reading order. Standard covers selectable text; Vision covers scans and complex layouts.
What do I need for Vision mode?
A Nutrient account, an API key or a CLI license key. With an account or an API key, every input page draws one Vision page from the monthly allowance.
