# mineru

This skill uses MinerU to read, parse, search, OCR, and cite local documents. It fits PDFs, scans, tables, and long files.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 1500 installs · ★ 82436
- Author: opendatalab
- License: LicenseRef-Unknown · policy=link-only · description only; the file stays with the author
- Source: https://github.com/opendatalab/MinerU/tree/HEAD/skills/mineru/SKILL.md
- Updated: 2026-10-25
- HTML: https://affpapa.org/en/nevibecode/skills/mineru

## What it does

The skill directs the agent to the `mineru` command-line tool for local document work. MinerU parses PDFs, images, Word, PowerPoint, and Excel files, plus RTF, OpenDocument, EPUB, OFD, HTML, MHTML, CSV, and TSV. The agent can read results in parts, search processed documents, and retrieve page or block images.

MinerU returns stable page and block locators for follow-up reads and citations. The skill covers OCR, tables, formulas, and complex page layouts; it is not a RAG framework or vector database. It requires the MinerU CLI at version `>=4.0,<5` and Python `>=3.10,<3.15`. Without a compatible CLI version, the skill's commands cannot run.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add opendatalab/MinerU --skill mineru -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/mineru/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/mineru/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add opendatalab/MinerU --skill mineru -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/mineru/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add opendatalab/MinerU --skill mineru -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/mineru/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install opendatalab/MinerU mineru
```

2. **Manually: put the files in place**
- File: `.github/skills/mineru/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add opendatalab/MinerU --skill mineru -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/opendatalab/MinerU --path skills/mineru
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/mineru/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add opendatalab/MinerU --skill mineru -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/opendatalab/MinerU/tree/HEAD/skills/mineru/SKILL.md

## When to use it
- read a local PDF and answer questions about it
- OCR scanned pages or document images
- extract tables and formulas from a file
- continue through a long document from a page locator
- search documents that MinerU has already processed

## Example prompts
- Read `contract.pdf` and list its termination conditions.
- OCR `report.jpg`, then find every mention of amounts and dates.
- Continue from the returned document locator and cite the relevant page.

## Similar
- [pptx](https://affpapa.org/en/nevibecode/skills/pptx.md) — skill · 241433 installs
- [pdf](https://affpapa.org/en/nevibecode/skills/pdf.md) — skill · 216041 installs
- [docx](https://affpapa.org/en/nevibecode/skills/docx.md) — skill · 206304 installs
- [xlsx](https://affpapa.org/en/nevibecode/skills/xlsx.md) — skill · 187223 installs
- [brand-guidelines](https://affpapa.org/en/nevibecode/skills/brand-guidelines.md) — skill · 109043 installs
- [theme-factory](https://affpapa.org/en/nevibecode/skills/theme-factory.md) — skill · 94921 installs

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md