mcpField
M
mineru-pdf

mineru-pdf

github.com/kesslerioDocuments7126 installsUpdated 15w ago
Repository

About mineru-pdf

A skill that parses PDFs locally with MinerU on CPU, producing Markdown and JSON by default. It can include tables or images when requested and processes a single PDF by default.

Key features

  1. 01Parse PDFs locally using CPU
  2. 02Produce Markdown and JSON by default
  3. 03Optionally include tables and images
  4. 04Allow JSON output format

Use cases

  1. 01Extract content from a PDF locally
  2. 02Convert a single PDF to Markdown and JSON
  3. 03Extract tables or images when needed

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/kesslerio/mineru-pdf-parser-openclaw-skill --skill mineru-pdf

After installing, type/mineru-pdfin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

README.md
LICENSE
VERSION
.gitignore
CHANGELOG.md
references/
mineru-cli.md
scripts/
mineru_parse.sh

Details

From the project README

MinerU PDF

Overview

Parse a PDF locally with MinerU (CPU). Default output is Markdown + JSON. Use tables/images only when requested.

Quick start (single PDF)

# Run from the skill directory
./scripts/mineru_parse.sh /path/to/file.pdf

Optional examples:

./scripts/mineru_parse.sh /path/to/file.pdf --format json
./scripts/mineru_parse.sh /path/to/file.pdf --tables --images

When to read references

If flags differ from your wrapper or you need advanced defaults (backend/method/device/threads/format mapping), read:

  • references/mineru-cli.md

Output conventions

  • Output root defaults to ./mineru-output/.
  • MinerU creates the per-document subfolder under the output root (e.g., ./mineru-output/<basename>/...).

Batching

Default is single-PDF parsing. Only implement batch folder parsing if explicitly requested.

Comments

Markdown supported