{"slug":"terminalskills-braintrust","source_name":"terminalskills/braintrust","name":"Terminalskills/Braintrust","description":"You are an expert in Braintrust, the evaluation and observability platform for AI applications. You help developers run systematic evaluations, compare model versions, track experiments, log production traces, and measure quality metrics — with a focus on making AI development as rigorous as traditional software testing.","version":1,"lift":{"pass_rate_delta_pts":13.64,"pass_rate_pct":86.4,"total_cases":22,"passed_cases":19,"tokens_delta_pct":10.7,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-04T04:31:28.489057+00:00"},"skill_score":0.8636,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":13.64,"with_pass_pct":86.4,"without_pass_pct":72.7,"tokens_delta_pct":10.7,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":22,"verdict":"mixed","never_hurt":false,"completed_at":"2026-08-04T04:31:28.489057+00:00","run_id":"8a7e5839-8360-4f41-8ea0-6b4cb05a3f3a","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":"Apache-2.0","install_count":0,"manifest_hash":"090a5c267e2abe61071f197db7c4ad7921df7d9763b0f8b2b6f2f35223dd184d","raw_url":"https://app.decimal.ai/s/terminalskills-braintrust/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/terminalskills-braintrust"}