Sends AI personas through web applications using Claude vision models to simulate real user behavior. Personas are defined with backgrounds, goals, and frustrations in YAML, and the engine takes screenshots, makes decisions, and executes actions via Playwright. Supports web, macOS native, and iOS Simulator testing.
Cognium trust score
0%
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.