Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
kesslerio avatar

Mineru Pdf

  • 20 installs
  • 8 repo stars
  • Updated July 14, 2026
  • kesslerio/mineru-pdf-parser-openclaw-skill

Parse PDFs locally into Markdown and JSON using MinerU with optional table and image extraction.

About

CPU-based PDF parser that converts documents to structured text with layout preservation and metadata extraction. Supports batch processing with configurable output formats.

  • Creates per-document output folders with Markdown and JSON formats and optional image/table extraction
  • Outputs include layout data (~50KB+) with better structure preservation than simple text extraction

Mineru Pdf by the numbers

  • 20 all-time installs (skills.sh)
  • Ranked #1,268 of 2,064 Data Science & ML skills by installs in the Skillselion catalog
  • Data as of Jul 25, 2026 (Skillselion catalog sync)
npx skills add https://github.com/kesslerio/mineru-pdf-parser-openclaw-skill --skill mineru-pdf

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs20
repo stars8
Last updatedJuly 14, 2026
Repositorykesslerio/mineru-pdf-parser-openclaw-skill

What it does

Parse PDFs locally into Markdown and JSON using MinerU with optional table and image extraction.

Files

SKILL.mdMarkdownGitHub ↗

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.

Related skills

Data Science & MLpipelinesetl

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.