# Pdf Reader

> Extract text content from PDF files. Use when: user asks to read, extract, or analyze content from a PDF document. Supports multi-page extraction, page ranges, and metadata. NOT for: scanned/image PDFs (OCR), PDF editing, or creating PDFs.

- **Type:** Skill
- **Install:** `agentstack add skill-ericwang915-pythonclaw-pdf-reader`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [ericwang915](https://agentstack.voostack.com/s/ericwang915)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [ericwang915](https://github.com/ericwang915)
- **Source:** https://github.com/ericwang915/PythonClaw/tree/main/pythonclaw/templates/skills/data/pdf_reader
- **Website:** https://github.com/ericwang915/PythonClaw

## Install

```sh
agentstack add skill-ericwang915-pythonclaw-pdf-reader
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# PDF Reader Skill

Extract text and metadata from PDF files using PyPDF2.

## When to Use

✅ **USE this skill when:**
- "Read this PDF"
- "Extract pages 2-4 from report.pdf"
- "What's in this PDF?"
- "Get PDF metadata"
- User wants to read or summarize content from a PDF

## When NOT to Use

❌ **DON'T use this skill when:**
- Scanned/image PDFs (no embedded text) → use OCR tools
- PDF editing or creating → use PDF manipulation libraries
- Extracting images or embedded media → use specialized PDF tools

## Usage/Commands

```bash
python {skill_path}/read_pdf.py PATH_TO_PDF [options]
```

Options:
- `--pages 1-5` — extract only specific pages (1-indexed, supports ranges)
- `--metadata` — include PDF metadata (author, title, creation date)
- `--format json` — output as JSON
- `--summary` — show page count and character count overview only

### Examples

- "Read this PDF" → `python {skill_path}/read_pdf.py document.pdf`
- "Extract pages 2-4 from report.pdf" → `python {skill_path}/read_pdf.py report.pdf --pages 2-4`
- "What's in this PDF?" → `python {skill_path}/read_pdf.py file.pdf --summary`
- "Get PDF metadata" → `python {skill_path}/read_pdf.py file.pdf --metadata`

## Notes

- Install dependency: `pip install PyPDF2`
- Works best with PDFs that have embedded text (not scanned images)

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [ericwang915](https://github.com/ericwang915)
- **Source:** [ericwang915/PythonClaw](https://github.com/ericwang915/PythonClaw)
- **License:** MIT
- **Homepage:** https://github.com/ericwang915/PythonClaw

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-ericwang915-pythonclaw-pdf-reader
- Seller: https://agentstack.voostack.com/s/ericwang915
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.