{"slug":"brycewang-stanford-aamas-experiments","source_name":"brycewang-stanford/aamas-experiments","name":"Brycewang Stanford/Aamas Experiments","description":"Use when designing or auditing AAMAS experiments - self-play and population-based training, opponent selection, equilibrium and regret metrics, game-theoretic simulations, ablations, seeds, hyperparameters, compute, and claim-to-evidence fit - with emphasis on experiments that probe the interaction rather than chase a single-agent leaderboard.","version":1,"lift":{"pass_rate_delta_pts":18.18,"pass_rate_pct":86.4,"total_cases":22,"passed_cases":19,"tokens_delta_pct":-13.8,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-15T03:06:54.875313+00:00"},"skill_score":0.8636,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":18.18,"with_pass_pct":86.4,"without_pass_pct":68.2,"tokens_delta_pct":-13.8,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":22,"verdict":"mixed","never_hurt":false,"completed_at":"2026-08-15T03:06:54.875313+00:00","run_id":"dd7cfb9f-9c72-48af-bc4a-44a49f5f1fa8","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":"MIT","install_count":0,"manifest_hash":"c5b0fa42abb264b924fb090e9ade2f08d1212e00b7525d40497cfec2c21635a3","raw_url":"https://app.decimal.ai/s/brycewang-stanford-aamas-experiments/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/brycewang-stanford-aamas-experiments"}