Skip to content
TakoAPI
Back to skills

iyeque-pdf-reader

by iyeque

Coding Agents & IDEs
785Downloads reported by clawskills.sh
4Stars
0Views
0 likesSign in to like this skill
—Not yet rated
Your rating

Brief

Extract text, search inside PDFs, and produce summaries.

Description

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

INPUT

User asks: extract the text from the first 3 pages of report.pdf

AGENT
  1. 1

    Receives file path and page limit from user

  2. 2

    Calls extract command with --max_pages 3 on report.pdf

  3. 3

    PyMuPDF opens the file and reads up to page 3

  4. 4

    Returns plain text content from those pages

OUTPUT

Plain text from the first 3 pages of report.pdf

Installation

clawhub install iyeque/iyeque-pdf-reader

Run the CLI command, or paste the prompt into Claude Code, Cursor, Codex or whichever coding agent you use.

Links