القائمة
PDF reader skill using PyMuPDF (fitz) for text extraction and metadata retrieval. Supports encrypted PDFs and handles large documents efficiently.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Main orchestration workflow for systematic literature research - search, evaluate, traverse, synthesize via the rp_* tools pipeline (Scopus + OpenAlex)
Collaboratively build and refine paper screening rubrics through brainstorming, test-driven development, and iterative feedback
Safely remove intermediate files from completed research sessions while preserving important data
Perform advanced search on CNKI with field filters like author, title, journal, date range, source category (SCI/EI/CSSCI/北大核心). Use when user needs precise filtered search beyond simple keywords.
Download a paper PDF/CAJ from CNKI. Requires user to be logged in. Use when user wants to download a specific paper.
Export paper from CNKI and push to Zotero, or save as RIS file. Use when user wants to save a paper to Zotero or export citation data.
| name | iyeque-pdf-reader |
| description | PDF reader skill using PyMuPDF (fitz) for text extraction and metadata retrieval. Supports encrypted PDFs and handles large documents efficiently. |
| tags | ["pdf","reader","text-extraction","metadata","pymupdf"] |
| version | 1.0.0 |
| author | iyeque |
| source | https://clawhub.ai/iyeque/iyeque-pdf-reader |
| requirements | ["PyMuPDF (fitz)"] |
| install | pip install pymupdf |
PDF reader skill for text extraction and metadata retrieval using PyMuPDF.
pip install pymupdf
The skill provides two commands:
Extracts plain text from the specified PDF file.
Parameters:
| Parameter | Type | Required | Description |
|---|---|---|---|
file_path | string | ✅ | Path to the PDF file |
--max_pages | integer | ❌ | Maximum number of pages to extract |
Usage:
# Extract all text
python3 skills/pdf-reader/reader.py extract /path/to/document.pdf
# Extract first 5 pages only
python3 skills/pdf-reader/reader.py extract /path/to/document.pdf --max_pages 5
Output: Plain text content from the PDF.
Retrieve metadata about the document.
Parameters:
| Parameter | Type | Required | Description |
|---|---|---|---|
file_path | string | ✅ | Path to the PDF file |
Usage:
python3 skills/pdf-reader/reader.py metadata /path/to/document.pdf
Output: Structured JSON with document metadata.
| Field | Description |
|---|---|
title | Document title |
author | Document author |
subject | Document subject |
creator | Software that created the PDF |
producer | PDF producer software |
creationDate | Creation date |
modDate | Modification date |
format | PDF format version |
encryption | Encryption info (if any) |
Plain text content from the PDF...
{
"title": "Annual Report 2024",
"author": "John Doe",
"creationDate": "D:20240115120000Z",
"creator": "Microsoft Word",
"producer": "Adobe PDF Library",
"format": "PDF 1.7"
}
--max_pages for large documentsYou can also use PyMuPDF directly in Python:
import fitz # PyMuPDF
# Open PDF
doc = fitz.open("document.pdf")
# Get metadata
print(doc.metadata)
# Extract text from all pages
for page in doc:
text = page.get_text()
print(text)
# Extract from specific page
page = doc[0] # First page (0-indexed)
text = page.get_text()
fitz) for fast, reliable PDF processing--max_pages option| Error | Cause | Solution |
|---|---|---|
| File not found | Invalid path | Check file path |
| Not a valid PDF | Corrupted file | Verify file integrity |
| Encrypted PDF | Password protected | Provide password if required |