Provides PDF reading, rendering, and search capabilities using PyMuPDF and PyMuPDF4LLM. Offers tools for metadata extraction, table of contents retrieval, text extraction in multiple formats (JSON, text, markdown, HTML), page rendering as PNG images, and case-insensitive full-text search. Designed for processing datasheets and technical documents containing diagrams and tables.
Cognium trust score
91%
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 2026-09-28.
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.