A comprehensive document processing engine for creating, editing, merging, and extracting structured data from PDF files using Python-based tools.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install pdf-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 pdf-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 PDF Skill?
The PDF skill is a robust solution for developers needing to programmatically handle complex document workflows within Openclaw Skills. It leverages industry-standard libraries like pypdf, pdfplumber, and weasyprint to provide a full suite of capabilities including text and table extraction, form filling, and metadata management.
Beyond basic manipulation, this Openclaw Skills extension supports advanced requirements such as OCR for scanned documents via Tesseract and professional-grade PDF generation from HTML/CSS templates. Whether you are automating invoice processing or generating dynamic monthly reports, this skill provides the necessary hooks and API references to streamline your document automation pipeline.
PDF Skill Use Cases
- Automating the extraction of tabular data from financial statements into Excel or CSV formats.
- Generating dynamic, styled PDF reports from HTML templates for business intelligence.
- Batch merging or splitting documents for organized digital archiving.
- Redacting or watermarking sensitive documents with confidential stamps.
- Converting scanned image-based PDFs into searchable text using OCR.
How PDF Skill Works
- The skill initializes by loading the target PDF file into a reader object using pypdf or pdfplumber.
- For extraction tasks, it parses the document's internal structure to identify text blocks, table boundaries, or form fields.
- For creation tasks, it renders HTML and CSS into a PDF canvas using the WeasyPrint engine for high-fidelity layouts.
- For modification tasks (like merging or rotating), it utilizes a writer object to stage changes before committing them to a new file.
- The skill outputs the processed data as a new PDF file, a JSON object, or a structured data frame depending on the requested operation.
PDF Skill Setup
To get started with this skill, install the primary dependencies:
pip install pypdf pdfplumber weasyprint
For advanced features like OCR and image conversion, install the optional system requirements:
# For image conversion
brew install poppler
pip install pdf2image
# For OCR
brew install tesseract
pip install pytesseract
PDF Skill Data Schema & Taxonomy
The PDF skill organizes metadata and extracted content into structured formats for easy integration with other Openclaw Skills.
| Data Type | format | Description |
|---|---|---|
| Metadata | Dictionary | Contains Title, Author, Subject, Creator, and Creation Date. |
| Extracted Text | String/JSON | Clean text content mapped by page number. |
| Tables | List of Lists | Raw table data extracted via pdfplumber, compatible with Pandas DataFrames. |
| Form Data | Key-Value Pair | Dictionary of field names and their corresponding string values. |
PDF Skill Advanced Features
- Multi-engine OCR support for converting scanned images into machine-readable text.
- CSS-based PDF styling allowing for headers, footers, and page numbering via WeasyPrint.
- Document security features including password encryption and decryption.
- Programmatic form filling for automating the completion of standardized PDF templates.
- Rotation and page-level manipulation for correcting document orientation at scale.
SKILL.md
Loading
Related Openclaw Skills
Indie App Marketing Pipeline
A zero-LLM daily marketing system for indie developers that generates and schedules a full week of multi-platform social content from a pre-defined content bank.
CPS Monetization Pro
A systematic framework for executing high-conversion Cost-Per-Sale (CPS) affiliate marketing campaigns across multiple platforms.
Durable Workflow Patterns
A comprehensive set of patterns and scripts for building AI agent workflows that maintain state and survive external failures.
DELULU AI Dating Agent
DELULU is an intelligent AI dating agent that automates friend matching, smart conversations, and social interactions for the OpenClaw and Claude Code platforms.
XLSX Skill
A professional-grade Excel automation engine for creating, reading, and analyzing spreadsheets with full formula and formatting support.
Cross-border E-commerce Strategy
A systematic framework designed to achieve positive cash flow and scalable operations in international markets within 90 days.
Featured*
