Provides PDF table extraction with automatic detection and structured output in four formats: Markdown, CSV, JSON, and HTML. Uses pdfplumber for native PDFs with text layers, with optional Table Transformer and OCR backends for scanned documents and images. Offers two tools -- extract_tables for full extraction with page selection and format control, and list_tables for quick previews of table dimensions and headers. Lightweight ~33MB install with no model downloads or API keys required.
Cognium trust score
87%
Tier
Verified
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
Last scanned 2026-09-19.
Returns 7 tools: search_skills, get_skill, list_leaderboard, get_trust_breakdown, resolve_composition, plus the ChatGPT-connector search and fetch. Every tool is annotated read-only.
Resolve this skill directly via MCP tools/call get_skill.