PDF Reader
Extract text, tables, and metadata from PDF files. Supports OCR for scanned documents, page selection, and structured data extraction.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add pdf-reader npx -- -y @trustedskills/pdf-reader
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"pdf-reader": {
"command": "npx",
"args": [
"-y",
"@trustedskills/pdf-reader"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
Extracts text, tables, and metadata from PDF files. It supports optical character recognition (OCR) for scanned documents, allows users to select specific pages, and can extract structured data such as form fields or tables.
When to use it
- To convert a scanned document into editable text
- When you need to extract specific pages from a multi-page PDF
- For pulling out table data from reports or research papers
Key capabilities
- Text extraction from PDFs
- Table and structured data extraction
- OCR support for scanned documents
- Page selection for targeted content retrieval
Example prompts
- "Extract the text from page 3 of this PDF."
- "Perform OCR on this scanned document and return the text."
- "Pull out all tables from the attached report."
Tips & gotchas
Ensure that the PDF is not password protected before using this skill. For best results with OCR, use high-quality scans with clear text.
TrustedSkills Verification
Unlike other registries that point to live repositories, TrustedSkills pins every skill to a verified commit hash. This protects you from malicious updates — what you install today is exactly what was reviewed and verified.
Security Audits
| Gen Agent Trust Hub | Pass |
| Socket | Pass |
| Snyk | Pass |
Details
- Version
- v1.0.5
- License
- Apache-2.0
- Author
- community
- Installs
- 780
- Updated
- Feb 15, 2026
- Published
- Jan 5, 2026
🌐 Community
Passed automated security scans.