A local, CPU-based PDF parser that transforms complex documents into AI-ready Markdown and JSON formats.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install mineru-pdf-parser-clawdbot-skill
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install mineru-pdf-parser-clawdbot-skill using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is MinerU PDF Parser?
The MinerU PDF parser provides a robust solution for developers needing to extract high-fidelity content from PDF documents locally. By utilizing the MinerU engine, this skill ensures that layouts, tables, and images are accurately captured without the need for cloud-based processing. Integrating this tool into your Openclaw Skills library allows for secure, offline document analysis and data preparation for LLMs.
MinerU PDF Parser Use Cases
- Local conversion of technical documentation for internal knowledge bases.
- Automated extraction of tables from financial PDF reports.
- Preparing unstructured PDF data for vector embeddings within Openclaw Skills.
- Offline archival of PDF content into human-readable Markdown.
How MinerU PDF Parser Works
- Initiate the parsing process by passing a PDF file path to the local script.
- The system executes the MinerU CLI using the local CPU backend.
- Content is analyzed and segmented into text, tables, and visual elements.
- Structured Markdown or JSON files are saved to the designated output folder.
- Users can leverage the extracted data for further automation using Openclaw Skills.
MinerU PDF Parser Setup
To begin using the skill, run the parse script from the directory:
./scripts/mineru_parse.sh /path/to/file.pdf
For advanced JSON output with images and tables enabled:
./scripts/mineru_parse.sh /path/to/file.pdf --format json --tables --images
MinerU PDF Parser Data Schema & Taxonomy
The skill organizes extracted data into a structured directory pattern:
| Path | Purpose |
|---|---|
./mineru-output/ |
The default root for all parsed outputs. |
./mineru-output/<basename>/ |
Per-document folder containing all specific extracts. |
<basename>.md |
The primary Markdown representation of the PDF. |
<basename>.json |
Structured data containing metadata and content objects. |
images/ |
Directory containing extracted visual assets if requested. |
MinerU PDF Parser Advanced Features
- Configurable format mapping between Markdown and JSON.
- Support for detailed table and image extraction flags.
- Local-first processing architecture ensuring data privacy.
- Ability to handle multi-column layouts and complex formatting.
- Compatible with batch processing requests when integrated with other Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
lobster-jobs
A specialized migration tool for converting OpenClaw cron jobs into deterministic Lobster workflows featuring approval gates and resumable execution.
Klutch Programmable Finance
An advanced financial integration that enables AI agents and developers to interact with Klutch programmable credit cards through a secure GraphQL API.
Stealth Browser
An advanced browser automation skill designed to bypass aggressive anti-bot protections like Cloudflare and Datadome using stealth-patched browsers.
ImageMagick Moltbot Skill
A comprehensive suite of ImageMagick operations designed to automate complex image manipulation, format conversion, and background removal within AI agent workflows.
Coding Agent Skill
A robust orchestration layer for running interactive AI coding agents like Codex, Claude Code, and Gemini via a controlled terminal environment.
Oura Analytics
A comprehensive integration for Oura Ring that automates health data retrieval, trend analysis, and recovery alerting.
Featured*
