Provides access to Google Gemini models directly from Claude Code or any compatible client. Supports asking questions, analyzing code, multi-turn conversations with full history, and listing available models. Includes retry with exponential backoff, per-call model override, and graceful error reporting.
Cognium trust score
65%
Tier
Scanned
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 2026-09-02.
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.