{"slug":"agentscope-ai-prompt-regression","source_name":"agentscope-ai/prompt-regression","name":"Agentscope AI/Prompt Regression","description":"Use when the user has changed a prompt (system prompt, RAG template, agent instruction, etc.) and wants to know whether the candidate is better or worse than the baseline. Also use when the user mentions prompt A/B testing, prompt comparison, prompt optimization validation, \"did my prompt change help,\" or prompt regression testing. Outputs per-dimension win rates with statistical significance using OpenJudge PairwiseAnalyzer.","version":1,"lift":{"pass_rate_delta_pts":27.27,"pass_rate_pct":90.9,"total_cases":22,"passed_cases":20,"tokens_delta_pct":104,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-14T18:48:13.733919+00:00"},"skill_score":0.9091,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":27.27,"with_pass_pct":90.9,"without_pass_pct":63.6,"tokens_delta_pct":104,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":22,"verdict":"mixed","never_hurt":false,"completed_at":"2026-08-14T18:48:13.733919+00:00","run_id":"c7b24328-4270-4efc-8bdf-5e8f1b215490","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":"40a2abb00dd41a38b0fb2429d189e8989ad695446a90e1b1e1f01db09d713138","raw_url":"https://app.decimal.ai/s/agentscope-ai-prompt-regression/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/agentscope-ai-prompt-regression"}