{"slug":"evo-hq-optimize","source_name":"evo-hq/optimize","name":"Evo Hq/Optimize","description":"Drive structured autoresearch iteration after evo:discover and the baseline commit. Use when the user invokes /evo:optimize or asks to try ideas, try variants, run experiments, use available GPUs, improve the current best/frontier, continue an evo search, or compare candidate changes in an evo workspace. The orchestrator plans and spawns optimization subagents; candidate edits/runs belong to those subagents. Width is set via subagents=N (1 for serial workloads, larger for parallel); the loop's s","version":1,"lift":{"pass_rate_delta_pts":36.36,"pass_rate_pct":68.2,"total_cases":22,"passed_cases":15,"tokens_delta_pct":733.9,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-13T09:25:40.111947+00:00"},"skill_score":0.6818,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":36.36,"with_pass_pct":68.2,"without_pass_pct":31.8,"tokens_delta_pct":733.9,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":16,"verdict":"mixed","never_hurt":false,"completed_at":"2026-08-13T09:25:40.111947+00:00","run_id":"422dbf3d-7e43-4e3c-a1de-e37246649b15","version_number":1,"is_latest_version":true,"gate":null}],"trust":{"skill_safety":"passed","safety_status":"clean","intent_verdict":"safe","content_status":"clean","indexable":true},"license":"Apache-2.0","install_count":0,"manifest_hash":"8dd136f6ea07c11de4a6969b61aa5a39c16a294152d08914350e7f9c847abaa1","raw_url":"https://app.decimal.ai/s/evo-hq-optimize/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/evo-hq-optimize"}