Pdf To Markdown

Converts PDFs to Markdown by checking if they have native text or need OCR, though OCR isn't implemented yet. Runs with just Node.js using npx to pull @opendocsg/pdf2md on first use, no installation required. Works well for text-based PDFs like documentation or reports, handles basic tables, but complex multi-column layouts won't survive perfectly. The auto-detect mode is smart enough to tell you when a PDF is scanned and can't be processed. Outputs clean JSON with page counts and paths. If you're building documentation pipelines or need to extract content from standard PDFs without dealing with system dependencies, this does the job without fuss.

skills.sh installs: 293
GitHub stars: 6
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add andreadellacorte/groove --skill pdf-to-markdown --agent claude-code

Installs into .claude/skills of the current project.

Files

[IMPORTANT] Use TaskCreate to break ALL work into small tasks BEFORE starting — including tasks for each file read. This prevents context loss from long files. For simple tasks, AI MUST ask user whether to skip.

Quick Summary

Goal: Convert PDF files to well-formatted Markdown with auto-detection of native text vs scanned documents. Only native-text conversion is implemented; OCR is planned.

Workflow:

Auto-Detect — Determine if PDF has native text or needs OCR
Convert — Run scripts/convert.cjs with input path and optional mode/output flags
Output — Returns JSON with success status, page count, and output path

Key Rules: