{"slug":"brycewang-stanford-autoresearch","source_name":"brycewang-stanford/autoresearch","name":"Brycewang Stanford/Autoresearch","description":"Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports continuous agent operation via Claude Code /loop and OpenClaw heartbeat, and produces research presentations and papers. Use when starting a research project, running autonomous experimen","version":1,"lift":{"pass_rate_delta_pts":31.82,"pass_rate_pct":59.1,"total_cases":22,"passed_cases":13,"tokens_delta_pct":287.4,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-07T02:02:18.455061+00:00"},"skill_score":0.5909,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":31.82,"with_pass_pct":59.1,"without_pass_pct":27.3,"tokens_delta_pct":287.4,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":20,"verdict":"mixed","never_hurt":false,"completed_at":"2026-08-07T02:02:18.455061+00:00","run_id":"f1066423-eaea-4246-84d6-36bcce6b68c8","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":"5582a55f3a0aac8fd81f4a8432418e0b615674c627ec096c34c8da4a0cb8762d","raw_url":"https://app.decimal.ai/s/brycewang-stanford-autoresearch/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/brycewang-stanford-autoresearch"}