{"slug":"brycewang-stanford-run-experiment","source_name":"brycewang-stanford/run-experiment","name":"Brycewang Stanford/Run Experiment","description":"Deploy and run ML experiments on local or remote GPU servers. Use when user says \"run experiment\", \"deploy to server\", \"跑实验\", or needs to launch training jobs.","version":2,"lift":{"pass_rate_delta_pts":47.83,"pass_rate_pct":87,"total_cases":23,"passed_cases":20,"tokens_delta_pct":46.1,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-11T14:58:24.285743+00:00"},"skill_score":0.8696,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":47.83,"with_pass_pct":87,"without_pass_pct":39.1,"tokens_delta_pct":46.1,"turns_delta_pct":0,"total_cases":23,"cases_aggregated":20,"verdict":"mixed","never_hurt":true,"completed_at":"2026-08-11T14:58:24.285743+00:00","run_id":"e5bfd98f-2ec3-4b38-84eb-5d3428841abc","latest_attempt":{"id":"e5bfd98f-2ec3-4b38-84eb-5d3428841abc","runner_model":"gemini-3.6-flash","overall_verdict":"mixed","completed_at":"2026-08-11T14:58:24.285743+00:00","gate":null},"version_number":2,"is_latest_version":true,"gate":null}],"trust":{"skill_safety":"passed","safety_status":"clean","intent_verdict":"safe","content_status":"clean","indexable":true},"license":"NOASSERTION","install_count":0,"total_uses":0,"total_users":0,"manifest_hash":"046ffe0e64df6f9e588bdf4e790ac4aa43239b40bd956d232381e3a1dc51aab3","install_name":"brycewang-stanford-run-experiment","version_id":"73ad232f-4bed-4598-a8e6-c722029a5f11","body_sha256":"046ffe0e64df6f9e588bdf4e790ac4aa43239b40bd956d232381e3a1dc51aab3","render_hash":"f5b211d3afe658eedbb72186a43d924fcd0973864f552f8f3747f9b1ae5d3a5e","raw_url":"https://app.decimal.ai/s/brycewang-stanford-run-experiment/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/brycewang-stanford-run-experiment"}