Setup & Installation
openclaw skills install @iyeque/iyeque-pdf-reader
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
npx clawhub install iyeque-pdf-reader
Version History
v1.1.0Feb 17, 2026 - Version note by skill developer:
Fixed SKILL.md to match actual PyMuPDF implementation. Corrected API documentation.
What This Skill Does
Extracts text and metadata from PDF files using PyMuPDF. Supports page-limited extraction and returns structured metadata including title, author, and creation date. Handles large, encrypted, and malformed PDFs.
PyMuPDF is one of the fastest PDF processing libraries available, making it practical for large files where tools like pdfminer are noticeably slow.
When to use it
- Extract text from a scanned research paper
- Check author and creation date of a contract PDF
- Pull first 5 pages from a lengthy report for quick review
- Verify if a PDF is encrypted before processing
- Batch-read metadata from a folder of archived documents
Example Workflow
Here's how your AI assistant might use this skill in practice.
INPUT
User asks: extract the text from the first 3 pages of report.pdf
AGENT
- 1Receives file path and page limit from user
- 2Calls extract command with --max_pages 3 on report.pdf
- 3PyMuPDF opens the file and reads up to page 3
- 4Returns plain text content from those pages
OUTPUT
Plain text from the first 3 pages of report.pdf