pdf-to-markdown · lttr — Claude Code skill: what it does, how to install
pdf-to-markdown transcribes scanned and image-based PDFs into formatted Markdown files saved in the same directory as the source document.
no license 5 installs ★ 4 updated 2026-10-22
npx skills add lttr/dotfiles --skill pdf-to-markdown -a claude-codeWhat pdf-to-markdown does
This skill relies on vision capabilities to read pages directly instead of calling separate OCR APIs. It first inspects page totals with pdfinfo. When a document spans 10 or more pages, it splits the file into 4-page batches with qpdf and handles them simultaneously through Task agents.
The resulting .md file retains headings, lists, original diacritics, and handwritten notes in italics. Strikethrough syntax marks crossed-out phrases. Once merging finishes, temporary files are cleaned up automatically.
Without qpdf installed on your machine, processing documents with 10 or more pages will fail during the chunking phase.
What it helps with
- extract text from scanned or image-based PDF files
- convert multi-page documents in parallel 4-page batches
- preserve handwritten edits and crossed-out notes in markdown
- format raw scanned pages into clean heading and list structures
Example prompts for the agent
- Transcribe
scanned_contract.pdfinto a markdown file - Convert the image document
history_archive.pdfto markdown - Extract text from
records.pdfwhile preserving handwritten annotations
How to install pdf-to-markdown
1Skills CLI (Vercel)
npx skills add lttr/dotfiles --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 lttr/dotfiles --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 lttr/dotfiles --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 lttr/dotfiles claude/skills/pdf-to-markdown2Manually: put the files in place
.github/skills/pdf-to-markdown/SKILL.md1Skills CLI (Vercel)
npx skills add lttr/dotfiles --skill pdf-to-markdown -a gemini-cli2Platform CLI
gemini skills install https://github.com/lttr/dotfiles --path claude/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 lttr/dotfiles --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 to install pdf-to-markdown in Claude Code?
Run npx skills add lttr/dotfiles --skill pdf-to-markdown -a claude-code in your terminal.
What does pdf-to-markdown do?
It reads PDF pages visually via assistant tools, transcribes the content, and outputs a formatted .md file right next to the source.
Which dependencies are required?
You need pdfinfo to count pages and qpdf to break down documents that contain 10 or more pages.
Similar skills
All skills for Writing and docs →pdf-to-markdown by other authors comes first.