{"slug":"brycewang-stanford-aamas-reproducibility","source_name":"brycewang-stanford/aamas-reproducibility","name":"Brycewang Stanford/Aamas Reproducibility","description":"Use when strengthening AAMAS reproducibility evidence for interaction claims, including proofs and game definitions, opponent and population sets, self-play protocols, random seeds, compute, uncertainty on strategic outcomes, baselines, and consistency between what the paper claims about agents and what the artifact can actually show.","version":1,"lift":{"pass_rate_delta_pts":13.64,"pass_rate_pct":81.8,"total_cases":22,"passed_cases":18,"tokens_delta_pct":3.9,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-15T03:08:12.859271+00:00"},"skill_score":0.8182,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":13.64,"with_pass_pct":81.8,"without_pass_pct":68.2,"tokens_delta_pct":3.9,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":22,"verdict":"mixed","never_hurt":false,"completed_at":"2026-08-15T03:08:12.859271+00:00","run_id":"564b75e8-eea5-4eb0-87d8-c075405062aa","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":"64b08f866685a2ea3e94cf701b79f8b56af42efe45ff7a7341d2163b5a756674","raw_url":"https://app.decimal.ai/s/brycewang-stanford-aamas-reproducibility/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/brycewang-stanford-aamas-reproducibility"}