{"slug":"brenbuilds1-memory-audit","source_name":"brenbuilds1/memory-audit","name":"Brenbuilds1/Memory Audit","description":"Fact-check an agent's persistent memory against the repo it describes. Use when an agent acts on outdated notes, when inheriting a project with existing CLAUDE.md / AGENTS.md / rules files, after a large refactor, or periodically on any long-lived project. Inventories every memory and instruction file the agent loads, splits them into atomic claims, verifies each claim against the current codebase and git history, and reports a per-line verdict table (confirmed, stale, wrong, contradiction, pref","version":1,"lift":{"pass_rate_delta_pts":9.09,"pass_rate_pct":50,"total_cases":22,"passed_cases":11,"tokens_delta_pct":23.2,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-04T12:50:06.175352+00:00"},"skill_score":0.5,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":9.09,"with_pass_pct":50,"without_pass_pct":40.9,"tokens_delta_pct":23.2,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":15,"verdict":"mixed","never_hurt":false,"completed_at":"2026-08-04T12:50:06.175352+00:00","run_id":"0d8f7143-6ea1-4962-8c0e-4d88894a4609","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":"a77eef2012cd9fd89840cb7a3eb607ab34dd112ff8c03f0a7ef6b4dd04f997f1","raw_url":"https://app.decimal.ai/s/brenbuilds1-memory-audit/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/brenbuilds1-memory-audit"}