A lightning-fast local tool for converting PDF documents into Markdown and JSON formats with support for image and table extraction.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install pymupdf-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 pymupdf-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 PyMuPDF PDF Parsing?
The PyMuPDF PDF parsing skill provides a high-performance, local solution for extracting text and assets from PDF files. Designed to integrate perfectly into the ecosystem of Openclaw Skills, this tool leverages the fitz library to deliver rapid results without the overhead of heavy OCR engines or cloud-based dependencies. It is the ideal choice for developers who prioritize execution speed and want to transform static PDF content into AI-ready Markdown or JSON data structures.
By focusing on local processing, this skill ensures that document data remains private and accessible even in offline environments. While it excels at fast text extraction, it also offers utility for capturing images and basic tabular data, making it a versatile component for any automated pipeline involving Openclaw Skills. Whether you are processing a single report or batch-converting an entire library, this skill provides a reliable and efficient foundation for document analysis.
PyMuPDF PDF Parsing Use Cases
- Rapidly converting large batches of PDF documents into Markdown for LLM ingestion.
- Extracting embedded images from technical manuals for use in digital asset management.
- Generating structured JSON metadata from PDF reports for data analytics pipelines.
- Providing a lightweight and fast local parsing fallback within complex Openclaw Skills automation workflows.
How PyMuPDF PDF Parsing Works
- The user executes the script by pointing to a local PDF file and defining the desired output format (Markdown or JSON).
- The skill utilizes the PyMuPDF (fitz) engine to parse the document's internal structure and extract text layers.
- If specific flags are enabled, the tool identifies and extracts images and basic table structures into separate files.
- A dedicated directory is automatically generated using the document's base name to ensure clean data organization.
- The final parsed content is saved to the output root, ready for immediate use by other Openclaw Skills or downstream applications.
PyMuPDF PDF Parsing Setup
To get started with this skill, ensure that PyMuPDF is available in your environment. You can initiate a parse by running the script from your terminal:
# Basic Markdown parsing
./scripts/pymupdf_parse.py /path/to/document.pdf --format md --outroot ./pymupdf-output
# Comprehensive extraction including images and tables
./scripts/pymupdf_parse.py /path/to/document.pdf --format both --images --tables
PyMuPDF PDF Parsing Data Schema & Taxonomy
This skill follows a standardized output directory structure to help Openclaw Skills manage extracted data efficiently.
| File/Folder | Purpose |
|---|---|
output.md |
The primary text content of the PDF in Markdown format. |
output.json |
A structured JSON file containing the text and metadata like language hints. |
images/ |
A subdirectory containing all images extracted from the PDF. |
tables.json |
A line-based JSON representation of tabular data found in the document. |
PyMuPDF PDF Parsing Advanced Features
- Support for multi-format output, allowing simultaneous generation of Markdown and JSON files.
- Language hinting via the
--langflag to improve the accuracy of downstream NLP tasks. - Specialized image extraction capability for visual content processing.
- Configurable output roots to facilitate seamless integration with enterprise Openclaw Skills file storage.
- Local-first architecture that prioritizes speed and security over resource-intensive OCR processing.
SKILL.md
Loading
Related Openclaw Skills
Oura Analytics
A comprehensive integration for Oura Ring that automates health data retrieval, trend analysis, and recovery alerting.
Coding Agent Skill
A robust orchestration layer for running interactive AI coding agents like Codex, Claude Code, and Gemini via a controlled terminal environment.
MinerU PDF Parser
A local, CPU-based PDF parser that transforms complex documents into AI-ready Markdown and JSON formats.
lobster-jobs
A specialized migration tool for converting OpenClaw cron jobs into deterministic Lobster workflows featuring approval gates and resumable execution.
Shorten
A streamlined URL shortening skill that leverages is.gd to provide permanent short links without the need for authentication.
SoulCraft
SoulCraft is a specialized framework for designing, refining, and evolving the internal character and external identity of AI agents.
Featured*
