smithery.ai

gemini-pdf-analyzer

Analyzes PDFs and images using Gemini 2.5 Flash via OpenRouter. Use when asked to extract info, ask questions about, or analyze large PDFs or images agentically.

First seen Apr 13, 2026

Installation

$ npx skills add https://smithery.ai

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

Also in this package

Other skills from smithery.ai · top by installs.

npx skills add https://smithery.ai

Browse all from smithery.ai

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 1,470 B
  • docs SUMMARY.md 188 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 1 installs

SKILL.md

Gemini PDF Analyzer

Analyze PDFs and images using Google's Gemini 3 Flash model via OpenRouter API.

Usage

Run the analyzer script with a prompt and one or more PDF/image files:

bun run .agents/skills/gemini-pdf-analyzer/scripts/analyze.ts "Your question here" path/to/file1.pdf path/to/file2.png

Environment

Requires OPENROUTERAPIKEY environment variable.

Capabilities

  • Extract text and tables from PDFs
  • Answer questions about document content
  • Analyze images and diagrams
  • Compare multiple documents
  • Process large PDFs by sending them directly to Gemini's vision capabilities

Examples

Ask about a PDF:

bun run .agents/skills/gemini-pdf-analyzer/scripts/analyze.ts "What are the main findings in this report?" report.pdf

Analyze multiple files:

bun run .agents/skills/gemini-pdf-analyzer/scripts/analyze.ts "Compare these two documents" doc1.pdf doc2.pdf

Extract structured data:

bun run .agents/skills/gemini-pdf-analyzer/scripts/analyze.ts "Extract all tables as JSON" data.pdf

Agentic Workflow

For complex multi-page PDFs, use iteratively:

  1. First ask for a summary/overview
  2. Then drill down into specific sections
  3. Extract structured data as needed