{"slug":"mohitagw15856-prompt-regression-suite","source_name":"mohitagw15856/prompt-regression-suite","name":"Mohitagw15856/Prompt Regression Suite","description":"Design a regression test suite that catches an LLM feature getting worse when the prompt, model, or context changes. Use when asked to stop prompt changes breaking production, set up golden tests or CI gates for an LLM feature, or test a model/prompt upgrade before shipping it. Produces a golden case set, per-case pass criteria, CI gate thresholds, and a triage protocol for failures. For designing first-time evaluation of a new feature use ai-eval-plan instead.","version":1,"lift":{"pass_rate_delta_pts":22.73,"pass_rate_pct":90.9,"total_cases":22,"passed_cases":20,"tokens_delta_pct":12.6,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-31T14:21:38.283376+00:00"},"skill_score":0.9091,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":22.73,"with_pass_pct":90.9,"without_pass_pct":68.2,"tokens_delta_pct":12.6,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":22,"verdict":"mixed","never_hurt":true,"completed_at":"2026-08-31T14:21:38.283376+00:00","run_id":"da9bb4f5-94de-4620-8823-a38a852e1360","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":"980f9a06b0e1210c79671f1355f3eea5cae8f3ed84a59d6d034663ef74f340fb","raw_url":"https://app.decimal.ai/s/mohitagw15856-prompt-regression-suite/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/mohitagw15856-prompt-regression-suite"}