This skill plugs Claude Code into MinerU for document conversion and OCR. You can ask for a PDF, image, or Office file to be turned into structured text formats, and Claude will use `mineru-open-api` behind the scenes. It supports quick reads with `flash-extract` and larger jobs with `extract`.
Builders who want Claude Code to read and convert documents into usable text formats.
You can turn PDFs and office files into the format you need without manually extracting or reformatting them.
Converts PDFs, images, and Office documents into Markdown, Word, HTML, LaTeX, JSON, or plain text.
Reads scanned documents instead of only working with selectable text.
Uses `flash-extract` for quick, no-auth reads and `extract` for larger, higher-fidelity jobs.
Lets you ask Claude directly for actions like converting a report to Word or extracting tables from a PDF.
npx skills add tanis90/pdf-converter-mineru
A Claude Code skill for converting PDFs and documents using MinerU.
Converts PDF, images, and Office documents to Markdown, Word, HTML, LaTeX, or plain text. Also handles OCR for scanned documents and supports 80+ languages.
npx skills add tanis90/pdf-converter-mineru
Just talk to Claude naturally:
Claude will automatically use mineru-open-api to extract the document and help you with what you need.
| Mode | When to use | Limits |
|---|---|---|
flash-extract | Quick reads, no auth needed | 10 MB / 20 pages |
extract | Full fidelity, images, batch | 200 MB / 600 pages |
flash-extract is used by default. Run mineru-open-api auth to unlock extract mode.
md, docx, html, latex, json — specify with -f md,docx
MinerU Open API by OpenDataLab (Shanghai AI Lab)
Sign in to join the discussion.
No comments yet. Be the first to say what this is good for.
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
Topic in, narrated explainer video out. A Claude Code / Codex skill that turns any topic into a black-canvas motion-graphics explainer video with TTS voiceover, subtitles and a chapter progress bar. Chinese or English; every frame drawn in code with Remotion.
Public repository for Agent Skills
Open-source AI job search: scan job portals, evaluate listings into a structured A-H report with a global 1-5 score, tailor your CV, track applications — runs locally in your AI coding CLI (Claude Code, Codex, OpenCode, Antigravity…)
Agent skill for beautiful, verifiable architecture, workflow, sequence, data-flow, and lifecycle diagrams—self-contained HTML with motion and crisp export.
A skill to stop your coding agent from burying the answer. ADHD-friendly output.