A versatile utility for extracting text, metadata, and converting various document formats including PDF, Word, and Excel.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install document-handler
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install document-handler using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
The Document Handler is a comprehensive technical skill designed for AI agents to interact with a wide array of document formats. It provides the necessary tools to read content from PDFs, Microsoft Office files, EPUBs, and OpenDocument formats, making it an essential component for any automated data processing workflow within the Openclaw Skills ecosystem.
By leveraging standard CLI utilities and custom shell scripts, this skill enables seamless extraction of text and metadata, as well as high-quality format conversion. Whether you need to scrape data from a complex spreadsheet or summarize an academic PDF report, this skill ensures your AI agent has direct access to the underlying information without requiring heavy external software suites.
To integrate this capability into your Openclaw Skills environment, ensure you have the required CLI utilities installed. On macOS, these can be managed via Homebrew.
# Install PDF utilities (pdftotext, pdfinfo, pdftoppm)
brew install poppler
# Install lynx for EPUB text rendering
brew install lynx
Execute the provided scripts directly for bulk processing:
# Extract text and metadata from any supported file
./scripts/extract_document.sh <file_path>
# Convert PDF pages to PNG images for visual processing
./scripts/pdf_to_images.sh <pdf_path> <output_directory> [dpi]
The Document Handler processes various input files and generates structured text or image outputs. Metadata is often returned as JSON-formatted comments for easy parsing.
| Document Component | Extraction Method | Primary Output |
|---|---|---|
| Text Content | pdftotext, sed, textutil | Plain Text |
| File Metadata | pdfinfo, unzip | JSON / Key-Value |
| Page Visuals | pdftoppm | PNG / JPEG Images |
| Spreadsheet Data | unzip + xml parsing | Normalized Text |
Loading
A comprehensive audio processing toolkit for AI agents to analyze, convert, and manipulate media files using industry-standard CLI tools.

A professional-grade portrait segmentation skill for AI agents to perform automatic image matting and contour recognition.

A professional-grade face fusion skill that seamlessly merges user faces with template images using high-performance Tencent Cloud AI.

A professional AI image generation skill leveraging the Tencent Cloud HunYuan large model for high-quality text-to-image and image-to-image synthesis.

A comprehensive utility for reading, analyzing, and manipulating a wide variety of image formats using native macOS tools and ffmpeg.

A powerful automation utility that transforms REST APIs into fully documented Openclaw Skills using OpenAPI specifications.








































