{"slug":"fcakyon-compare","source_name":"fcakyon/compare","name":"Fcakyon/Compare","description":"Same-epoch comparison of training runs across wandb, neptune, tensorboard, or mlflow. Aligns runs at the student's current step (never current-vs-final-of-baseline) and separates proxy metrics from downstream targets. Use when the user asks to compare runs, check if a run is improving, track lag against a baseline, rank experiments, or evaluate run-vs-run performance.","version":1,"lift":{"pass_rate_delta_pts":30.43,"pass_rate_pct":87,"total_cases":23,"passed_cases":20,"tokens_delta_pct":32.3,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-21T04:42:04.097863+00:00"},"skill_score":0.8696,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":30.43,"with_pass_pct":87,"without_pass_pct":56.5,"tokens_delta_pct":32.3,"turns_delta_pct":0,"total_cases":23,"cases_aggregated":23,"verdict":"mixed","never_hurt":false,"completed_at":"2026-08-21T04:42:04.097863+00:00","run_id":"fb2efffd-5bfd-4c4b-a286-c29a863d4dd5","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":"ab593b8db451876731fc47cb92c810006d8645b4a690b9aa3d37a9b0ffedf6a5","raw_url":"https://app.decimal.ai/s/fcakyon-compare/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/fcakyon-compare"}