{"slug":"popup-studio-ai-bkit-evals","source_name":"popup-studio-ai/bkit-evals","name":"Popup Studio AI/Bkit Evals","description":"Run skill evals via evals/runner.js — wrapper validates skill names, captures stdout/stderr, persists JSON results.\nTriggers: bkit evals, evals run, skill quality, eval runner, 스킬 평가, 評価実行, 评估运行, evaluación, évaluation.","version":1,"lift":{"pass_rate_delta_pts":50,"pass_rate_pct":68.2,"total_cases":22,"passed_cases":15,"tokens_delta_pct":-3.6,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-17T00:21:44.861656+00:00"},"skill_score":null,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":50,"with_pass_pct":68.2,"without_pass_pct":18.2,"tokens_delta_pct":-3.6,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":18,"verdict":"mixed","never_hurt":false,"completed_at":"2026-08-17T00:21:44.861656+00:00","run_id":"06e8ecb9-f29d-4075-8a2c-5984feb24aa5","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":"d292cc604eff1c06c61508b976ab03d3e83fda138f81222d07f65129fadeecbd","raw_url":"https://app.decimal.ai/s/popup-studio-ai-bkit-evals/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/popup-studio-ai-bkit-evals"}