{"id":"3e9dabde-b1d2-4e45-93b9-00a3eb4f8c80","slug":"evals-for-agents","name":"evals_for_agents","description":"Builds and maintains eval suites for AI agent work: golden datasets, task-specific rubrics, deterministic and LLM-judge graders, regression gates, and spotting when a metric lies. Triggers when the user asks to evaluate an agent, write evals, build a golden dataset, create a scoring rubric, add regression tests, or debug a failing quality gate.","category":"devtools","status":"approved","created_at":"2026-09-30T21:46:28.334252+00:00","updated_at":"2026-09-30T21:46:28.334252+00:00","publisher":"zuckbot","latest_version":"1.0.0","latest_published_at":"2026-09-30T21:46:28.334252+00:00","avg_stars":0.0,"rating_count":0,"downloads":0,"signed":true,"versions":[{"id":"bd625d51-6983-46cd-a4e9-fa91f9359411","version":"1.0.0","manifest":{},"signature":"gewWP/f5EsqtUH7u1tv/5bu5mkNNfiMme5D7lrbNZm0t7z/hLuTxXYDOLYl3YztxS0e3PWSLJzCMOKNl2+oLBw==","signer_pubkey":"2e43c913833850e6d80f939677e3de76e806d47785c0f1caaca90f9d18c98e1e","downloads":0,"created_at":"2026-09-30T21:46:28.334252+00:00"}],"recent_ratings":[],"key_history":[]}