Pdfreader

What this skill does

The documentation describes reading PDF pages, extracting text, and optionally writing JSON; its path-check claims may be affected by symlinks. Process only authorized files in a trusted working directory and avoid untrusted symlinks to prevent unintended reads or overwrites. Requires Python with PyMuPDF; use a virtual environment with a pinned version. The documented inputs are PDF files and JSON outputs in the working directory, but symlinks can bypass that boundary. Do not rely on it until path handling rejects or safely resolves symlinks.

Profile published 2026-10-27

Example prompts

Generated from the skill’s documentation as examples; not results of actual runs.

Monthly Trend

SKILL.md (original)

The author’s original file, shown as plain text without edits or review by AlphaMoat. Links are not clickable; check commands before running them. Fetched 2026-10-23.

# PDF Reader Skill for OpenClaw

Extract and read text from PDF files using PyMuPDF.

## Installation

```powershell
pip install pymupdf
```

## Usage

```powershell
# Extract text (first 10 pages by default)
python pdf_reader.py "path/to/file.pdf" 10

# Output to JSON file (for reading)
python pdf_reader.py "path/to/file.pdf" 10 --output=extracted.json

# Read specific number of pages
python pdf_reader.py "path/to/file.pdf" 5
```

## Features

- Extracts text from any PDF
- Supports large files
- Outputs JSON for AI reading
- Handles encoding issues
- Shows metadata (title, author, etc.)

## Security Restrictions

For safety, the script enforces:
- **Input files:** Must be `.pdf` files within the current working directory
- **Output files:** Must be `.json` files within the current working directory
- No path traversal (`../`) allowed
- Files can only be read/written in the directory where the script runs

## Files

- `pdf_reader.py` - Main Python script
- `SKILL.md` - This documentation

Popular in Office