{"slug":"tech-leads-club-harness-eval","source_name":"tech-leads-club/harness-eval","name":"Tech Leads Club/Harness Eval","description":"Evaluate a repo agent harness (AGENTS.md, rules, skills, skill refs) for broken paths/commands, redundant instructions, and usefulness using a stack-agnostic dual-judge protocol with planted traps. HIGH PRIORITY questionnaires at top: Q1 optional docs, Q2 B/C budget before Track A (certainty/tokens). A always runs after Q2; B/C opt-in. ADRs/RFCs excluded from T2. Mixed apply uses 11-mixed-apply.md (KEEP/CUT). Use when the user says harness eval, harness-eval, harness debug, audit AGENTS.md, audi","version":1,"lift":{"pass_rate_delta_pts":34.78,"pass_rate_pct":65.2,"total_cases":23,"passed_cases":15,"tokens_delta_pct":155.7,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-29T00:40:40.513159+00:00"},"skill_score":0.6522,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":34.78,"with_pass_pct":65.2,"without_pass_pct":30.4,"tokens_delta_pct":155.7,"turns_delta_pct":0,"total_cases":23,"cases_aggregated":19,"verdict":"mixed","never_hurt":false,"completed_at":"2026-08-29T00:40:40.513159+00:00","run_id":"3c78cc07-254e-4138-9e2e-af590817f871","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":"CC-BY-4.0","install_count":0,"manifest_hash":"6a0e1e5bd2d3e018464354610932957da42c7c8e3c32b6139f9927f4ed39ba64","raw_url":"https://app.decimal.ai/s/tech-leads-club-harness-eval/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/tech-leads-club-harness-eval"}