{"slug":"nousresearch-adversarial-ux-test","source_name":"nousresearch/adversarial-ux-test","name":"Nousresearch/Adversarial UX Test","description":"Roleplay a hostile user to find and triage UX pain points.","version":1,"lift":{"pass_rate_delta_pts":40.91,"pass_rate_pct":81.8,"total_cases":22,"passed_cases":18,"tokens_delta_pct":54.9,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-08T12:11:00.413086+00:00"},"skill_score":0.8182,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":40.91,"with_pass_pct":81.8,"without_pass_pct":40.9,"tokens_delta_pct":54.9,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":22,"verdict":"mixed","never_hurt":false,"completed_at":"2026-08-08T12:11:00.413086+00:00","run_id":"826b87b3-3a63-45c1-8468-bcae5a8128f4","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":"2e4b81b2656f1bd15cec8325ab07cd2b17a6f42c01210dc6b5777ea97dd138bf","raw_url":"https://app.decimal.ai/s/nousresearch-adversarial-ux-test/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/nousresearch-adversarial-ux-test"}