MinerU Document Extractor

Trust Score 85/100

CLI-driven document extraction skill: convert PDFs, images, Word/PPT/Excel, and web pages to Markdown/HTML/LaTeX/DOCX with OCR, table and formula recognition.

triggers:document extractionpdf to markdownocrmineruflash-extractextract

GitHub SKILL.md

What it does

MinerU provides a CLI skill to convert a wide range of documents (PDFs, scanned images, Word, PPT, Excel, web pages) into clean Markdown or other formats. It includes two modes: a zero-config 'flash-extract' for quick Markdown output (no token) and a precision 'extract' mode (token) for multi-format output, VLM layout parsing, batch processing, OCR, table and formula recognition.

When to use it

Use MinerU when you need fast, reliable conversion of messy or scanned documents into editable text (research papers, reports, slides, scans), to extract tables/formulas accurately, or to batch-process large numbers of files. Choose 'flash-extract' for quick one-off conversions and 'extract' for higher accuracy and larger files.

What's included

Scripts: CLI integration (mineru-open-api) — installable via npm or Go.
References: CLI docs and repo README.
Instructions: usage examples for flash-extract, extract, crawl, auth, flags for output format, model selection, OCR, and batching.

Compatible agents

Best used by agents or tools that can invoke system CLIs and stream/process stdout/stderr (automation agents, developer assistants, research pipelines).

Audit Summary

MinerU document extraction skill — converts PDFs, images, Office docs, and web pages to Markdown/HTML/LaTeX/DOCX via the mineru-open-api CLI. Well-documented with two extraction modes (flash-extract for quick no-token use, extract for full-featured), comprehensive format tables, and clear agent rules. No bundled scripts; relies on external CLI binary. Privacy metadata discloses that document content is sent to mineru.net for processing.

Watch Out

Document content is transmitted to mineru.net API for server-side extraction
Flash-extract mode has 10MB/20-page limits per file
Full extract mode requires MINERU_TOKEN setup

Notes

Clean skill, no security concerns beyond the inherent external API dependency which is clearly documented in privacy metadata. Well-structured SKILL.md with thorough documentation and agent rules.

Information

Repository: mineru-ecosystem
Stars: 112

Trust Score

Overall85

Security88

Code Quality85

Architecture78

Usefulness85

Related Skills

NGINX Integration

Integrate with NGINX via the Membrane CLI to query, manage, and proxy requests to NGINX for configuration, logs, and runtime operations.

Retriever (Membrane CLI)

Integrate Retriever search and discovery via the Membrane CLI — manage connections and run queries across Retriever data sources.

Run Execute

Orchestrates execution of work items across modes (autopilot, confirm, validate) with scripted init/complete tooling, plan/test/report artifacts and strict gati

BluOS CLI (blu)

Control Bluesound and NAD speakers: discover devices, play/stop, group/ungroup, and set volume from the CLI.

OpenDAL Oli CLI Playbooks

Command playbooks and safe-operation patterns for the OpenDAL 'oli' CLI — listing, copying, moving, editing, and benchmarking data across local and remote profi

Caveman Compress

Compress natural-language memory files into a compact 'caveman' format to save LLM tokens while preserving code, links, and structure.

Markdrop

Convert PDFs to structured Markdown or interactive HTML and generate AI-powered descriptions for images and tables using multiple LLM providers.

Uloop: Execute Dynamic Code

Run small C# snippets in the Unity Editor via the uloop CLI for editor automation tasks like prefab wiring, AddComponent flows, and scene edits—without writing

Back to Skills