[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-sourcegraph-audit":3,"mdc-11nhws-key":31,"related-org-sourcegraph-audit":425,"related-repo-sourcegraph-audit":541},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":21,"repoUrl":22,"updatedAt":23,"license":24,"forks":25,"topics":26,"repo":27,"sourceUrl":29,"mdContent":30},"audit","audit repository health and benchmark integrity","Run repo health checks, validate benchmark tasks, and audit run integrity.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"sourcegraph","Sourcegraph","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fsourcegraph.png",[12,16,19],{"name":13,"slug":14,"type":15},"Benchmarking","benchmarking","tag",{"name":17,"slug":18,"type":15},"QA","qa",{"name":20,"slug":4,"type":15},"Audit",31,"https:\u002F\u002Fgithub.com\u002Fsourcegraph\u002FCodeScaleBench","2026-07-17T06:07:07.220218",null,4,[],{"repoUrl":22,"stars":21,"forks":25,"topics":28,"description":24},[],"https:\u002F\u002Fgithub.com\u002Fsourcegraph\u002FCodeScaleBench\u002Ftree\u002FHEAD\u002Fskills\u002Faudit","---\nname: audit\ndescription: Run repo health checks, validate benchmark tasks, and audit run integrity.\n---\n\n# Skill: Audit & Validation\n\n## Scope\n\nUse this skill when the user asks to:\n- Run pre-commit\u002Fpush repo health gates\n- Validate task definitions and structure\n- Audit benchmark run integrity and completeness\n- Check documentation consistency\n- Verify contract compliance (task.toml, tests, oracles)\n\n## Canonical Commands\n\n```bash\n# Full repo health gate\npython3 scripts\u002Fmaintenance\u002Frepo_health.py\n\n# Quick health (docs + selection file only)\npython3 scripts\u002Fmaintenance\u002Frepo_health.py --quick\n\n# Validate all tasks\npython3 scripts\u002Fauthoring\u002Fvalidate_tasks_preflight.py --all\n\n# Validate specific task\npython3 scripts\u002Fauthoring\u002Fvalidate_tasks_preflight.py --task benchmarks\u002Fcsb\u002Fdebug\u002Ftask-name\n\n# Post-run task validation\npython3 scripts\u002Fauthoring\u002Fvalidate_task_run.py runs\u002Fstaging\u002Frun_dir\u002Ftask_id\n\n# Audit canonical evaluation contract\npython3 scripts\u002Fevaluation\u002Faudit_canonical_evaluation_contract.py\n```\n\n## Health Gate Checks\n\n- **Docs consistency** — CLAUDE.md, AGENTS.md, script index drift\n- **Task preflight** — instruction length, test.sh present, no placeholders\n- **Selection file** — configs\u002Fselected_benchmark_tasks.json valid JSON\n- **Launch policy** — configs\u002F*.sh use _common.sh, no raw harbor run\n\n## Task Validation\n\n- Task metadata in task.toml (language, difficulty, time_limit_sec)\n- test.sh and oracle_checks.py present and executable\n- Instruction.md length and format compliance\n- Verifier contract (test, artifact, verification modes)\n\n## Related Skills\n\n- `\u002Frun` — execute benchmarks that will be audited\n- `\u002Freport` — compile audit findings into reports\n",{"data":32,"body":33},{"name":4,"description":6},{"type":34,"children":35},"root",[36,45,52,58,88,94,309,315,359,365,388,394,419],{"type":37,"tag":38,"props":39,"children":41},"element","h1",{"id":40},"skill-audit-validation",[42],{"type":43,"value":44},"text","Skill: Audit & Validation",{"type":37,"tag":46,"props":47,"children":49},"h2",{"id":48},"scope",[50],{"type":43,"value":51},"Scope",{"type":37,"tag":53,"props":54,"children":55},"p",{},[56],{"type":43,"value":57},"Use this skill when the user asks to:",{"type":37,"tag":59,"props":60,"children":61},"ul",{},[62,68,73,78,83],{"type":37,"tag":63,"props":64,"children":65},"li",{},[66],{"type":43,"value":67},"Run pre-commit\u002Fpush repo health gates",{"type":37,"tag":63,"props":69,"children":70},{},[71],{"type":43,"value":72},"Validate task definitions and structure",{"type":37,"tag":63,"props":74,"children":75},{},[76],{"type":43,"value":77},"Audit benchmark run integrity and completeness",{"type":37,"tag":63,"props":79,"children":80},{},[81],{"type":43,"value":82},"Check documentation consistency",{"type":37,"tag":63,"props":84,"children":85},{},[86],{"type":43,"value":87},"Verify contract compliance (task.toml, tests, oracles)",{"type":37,"tag":46,"props":89,"children":91},{"id":90},"canonical-commands",[92],{"type":43,"value":93},"Canonical Commands",{"type":37,"tag":95,"props":96,"children":101},"pre",{"className":97,"code":98,"language":99,"meta":100,"style":100},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","# Full repo health gate\npython3 scripts\u002Fmaintenance\u002Frepo_health.py\n\n# Quick health (docs + selection file only)\npython3 scripts\u002Fmaintenance\u002Frepo_health.py --quick\n\n# Validate all tasks\npython3 scripts\u002Fauthoring\u002Fvalidate_tasks_preflight.py --all\n\n# Validate specific task\npython3 scripts\u002Fauthoring\u002Fvalidate_tasks_preflight.py --task benchmarks\u002Fcsb\u002Fdebug\u002Ftask-name\n\n# Post-run task validation\npython3 scripts\u002Fauthoring\u002Fvalidate_task_run.py runs\u002Fstaging\u002Frun_dir\u002Ftask_id\n\n# Audit canonical evaluation contract\npython3 scripts\u002Fevaluation\u002Faudit_canonical_evaluation_contract.py\n","bash","",[102],{"type":37,"tag":103,"props":104,"children":105},"code",{"__ignoreMap":100},[106,118,134,144,152,170,178,187,205,213,222,244,252,261,279,287,296],{"type":37,"tag":107,"props":108,"children":111},"span",{"class":109,"line":110},"line",1,[112],{"type":37,"tag":107,"props":113,"children":115},{"style":114},"--shiki-light:#90A4AE;--shiki-light-font-style:italic;--shiki-default:#546E7A;--shiki-default-font-style:italic;--shiki-dark:#676E95;--shiki-dark-font-style:italic",[116],{"type":43,"value":117},"# Full repo health gate\n",{"type":37,"tag":107,"props":119,"children":121},{"class":109,"line":120},2,[122,128],{"type":37,"tag":107,"props":123,"children":125},{"style":124},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[126],{"type":43,"value":127},"python3",{"type":37,"tag":107,"props":129,"children":131},{"style":130},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[132],{"type":43,"value":133}," scripts\u002Fmaintenance\u002Frepo_health.py\n",{"type":37,"tag":107,"props":135,"children":137},{"class":109,"line":136},3,[138],{"type":37,"tag":107,"props":139,"children":141},{"emptyLinePlaceholder":140},true,[142],{"type":43,"value":143},"\n",{"type":37,"tag":107,"props":145,"children":146},{"class":109,"line":25},[147],{"type":37,"tag":107,"props":148,"children":149},{"style":114},[150],{"type":43,"value":151},"# Quick health (docs + selection file only)\n",{"type":37,"tag":107,"props":153,"children":155},{"class":109,"line":154},5,[156,160,165],{"type":37,"tag":107,"props":157,"children":158},{"style":124},[159],{"type":43,"value":127},{"type":37,"tag":107,"props":161,"children":162},{"style":130},[163],{"type":43,"value":164}," scripts\u002Fmaintenance\u002Frepo_health.py",{"type":37,"tag":107,"props":166,"children":167},{"style":130},[168],{"type":43,"value":169}," --quick\n",{"type":37,"tag":107,"props":171,"children":173},{"class":109,"line":172},6,[174],{"type":37,"tag":107,"props":175,"children":176},{"emptyLinePlaceholder":140},[177],{"type":43,"value":143},{"type":37,"tag":107,"props":179,"children":181},{"class":109,"line":180},7,[182],{"type":37,"tag":107,"props":183,"children":184},{"style":114},[185],{"type":43,"value":186},"# Validate all tasks\n",{"type":37,"tag":107,"props":188,"children":190},{"class":109,"line":189},8,[191,195,200],{"type":37,"tag":107,"props":192,"children":193},{"style":124},[194],{"type":43,"value":127},{"type":37,"tag":107,"props":196,"children":197},{"style":130},[198],{"type":43,"value":199}," scripts\u002Fauthoring\u002Fvalidate_tasks_preflight.py",{"type":37,"tag":107,"props":201,"children":202},{"style":130},[203],{"type":43,"value":204}," --all\n",{"type":37,"tag":107,"props":206,"children":208},{"class":109,"line":207},9,[209],{"type":37,"tag":107,"props":210,"children":211},{"emptyLinePlaceholder":140},[212],{"type":43,"value":143},{"type":37,"tag":107,"props":214,"children":216},{"class":109,"line":215},10,[217],{"type":37,"tag":107,"props":218,"children":219},{"style":114},[220],{"type":43,"value":221},"# Validate specific task\n",{"type":37,"tag":107,"props":223,"children":225},{"class":109,"line":224},11,[226,230,234,239],{"type":37,"tag":107,"props":227,"children":228},{"style":124},[229],{"type":43,"value":127},{"type":37,"tag":107,"props":231,"children":232},{"style":130},[233],{"type":43,"value":199},{"type":37,"tag":107,"props":235,"children":236},{"style":130},[237],{"type":43,"value":238}," --task",{"type":37,"tag":107,"props":240,"children":241},{"style":130},[242],{"type":43,"value":243}," benchmarks\u002Fcsb\u002Fdebug\u002Ftask-name\n",{"type":37,"tag":107,"props":245,"children":247},{"class":109,"line":246},12,[248],{"type":37,"tag":107,"props":249,"children":250},{"emptyLinePlaceholder":140},[251],{"type":43,"value":143},{"type":37,"tag":107,"props":253,"children":255},{"class":109,"line":254},13,[256],{"type":37,"tag":107,"props":257,"children":258},{"style":114},[259],{"type":43,"value":260},"# Post-run task validation\n",{"type":37,"tag":107,"props":262,"children":264},{"class":109,"line":263},14,[265,269,274],{"type":37,"tag":107,"props":266,"children":267},{"style":124},[268],{"type":43,"value":127},{"type":37,"tag":107,"props":270,"children":271},{"style":130},[272],{"type":43,"value":273}," scripts\u002Fauthoring\u002Fvalidate_task_run.py",{"type":37,"tag":107,"props":275,"children":276},{"style":130},[277],{"type":43,"value":278}," runs\u002Fstaging\u002Frun_dir\u002Ftask_id\n",{"type":37,"tag":107,"props":280,"children":282},{"class":109,"line":281},15,[283],{"type":37,"tag":107,"props":284,"children":285},{"emptyLinePlaceholder":140},[286],{"type":43,"value":143},{"type":37,"tag":107,"props":288,"children":290},{"class":109,"line":289},16,[291],{"type":37,"tag":107,"props":292,"children":293},{"style":114},[294],{"type":43,"value":295},"# Audit canonical evaluation contract\n",{"type":37,"tag":107,"props":297,"children":299},{"class":109,"line":298},17,[300,304],{"type":37,"tag":107,"props":301,"children":302},{"style":124},[303],{"type":43,"value":127},{"type":37,"tag":107,"props":305,"children":306},{"style":130},[307],{"type":43,"value":308}," scripts\u002Fevaluation\u002Faudit_canonical_evaluation_contract.py\n",{"type":37,"tag":46,"props":310,"children":312},{"id":311},"health-gate-checks",[313],{"type":43,"value":314},"Health Gate Checks",{"type":37,"tag":59,"props":316,"children":317},{},[318,329,339,349],{"type":37,"tag":63,"props":319,"children":320},{},[321,327],{"type":37,"tag":322,"props":323,"children":324},"strong",{},[325],{"type":43,"value":326},"Docs consistency",{"type":43,"value":328}," — CLAUDE.md, AGENTS.md, script index drift",{"type":37,"tag":63,"props":330,"children":331},{},[332,337],{"type":37,"tag":322,"props":333,"children":334},{},[335],{"type":43,"value":336},"Task preflight",{"type":43,"value":338}," — instruction length, test.sh present, no placeholders",{"type":37,"tag":63,"props":340,"children":341},{},[342,347],{"type":37,"tag":322,"props":343,"children":344},{},[345],{"type":43,"value":346},"Selection file",{"type":43,"value":348}," — configs\u002Fselected_benchmark_tasks.json valid JSON",{"type":37,"tag":63,"props":350,"children":351},{},[352,357],{"type":37,"tag":322,"props":353,"children":354},{},[355],{"type":43,"value":356},"Launch policy",{"type":43,"value":358}," — configs\u002F*.sh use _common.sh, no raw harbor run",{"type":37,"tag":46,"props":360,"children":362},{"id":361},"task-validation",[363],{"type":43,"value":364},"Task Validation",{"type":37,"tag":59,"props":366,"children":367},{},[368,373,378,383],{"type":37,"tag":63,"props":369,"children":370},{},[371],{"type":43,"value":372},"Task metadata in task.toml (language, difficulty, time_limit_sec)",{"type":37,"tag":63,"props":374,"children":375},{},[376],{"type":43,"value":377},"test.sh and oracle_checks.py present and executable",{"type":37,"tag":63,"props":379,"children":380},{},[381],{"type":43,"value":382},"Instruction.md length and format compliance",{"type":37,"tag":63,"props":384,"children":385},{},[386],{"type":43,"value":387},"Verifier contract (test, artifact, verification modes)",{"type":37,"tag":46,"props":389,"children":391},{"id":390},"related-skills",[392],{"type":43,"value":393},"Related Skills",{"type":37,"tag":59,"props":395,"children":396},{},[397,408],{"type":37,"tag":63,"props":398,"children":399},{},[400,406],{"type":37,"tag":103,"props":401,"children":403},{"className":402},[],[404],{"type":43,"value":405},"\u002Frun",{"type":43,"value":407}," — execute benchmarks that will be audited",{"type":37,"tag":63,"props":409,"children":410},{},[411,417],{"type":37,"tag":103,"props":412,"children":414},{"className":413},[],[415],{"type":43,"value":416},"\u002Freport",{"type":43,"value":418}," — compile audit findings into reports",{"type":37,"tag":420,"props":421,"children":422},"style",{},[423],{"type":43,"value":424},"html .light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html.light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"items":426,"total":207},[427,433,450,465,479,493,507,517,528],{"slug":4,"name":4,"fn":5,"description":6,"org":428,"tags":429,"stars":21,"repoUrl":22,"updatedAt":23},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[430,431,432],{"name":20,"slug":4,"type":15},{"name":13,"slug":14,"type":15},{"name":17,"slug":18,"type":15},{"slug":434,"name":434,"fn":435,"description":436,"org":437,"tags":438,"stars":21,"repoUrl":22,"updatedAt":449},"evaluate","score traces and evaluate benchmark results","Extract metrics, score traces, and evaluate benchmark task results.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[439,440,443,446],{"name":13,"slug":14,"type":15},{"name":441,"slug":442,"type":15},"Data Analysis","data-analysis",{"name":444,"slug":445,"type":15},"Engineering","engineering",{"name":447,"slug":448,"type":15},"Evals","evals","2026-07-16T06:04:41.910821",{"slug":451,"name":451,"fn":452,"description":453,"org":454,"tags":455,"stars":21,"repoUrl":22,"updatedAt":464},"infra","check infrastructure and system dependencies","Check infrastructure readiness, manage MCP tools, and audit system dependencies.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[456,457,458,461],{"name":20,"slug":4,"type":15},{"name":444,"slug":445,"type":15},{"name":459,"slug":460,"type":15},"Infrastructure","infrastructure",{"name":462,"slug":463,"type":15},"MCP","mcp","2026-07-16T06:04:41.188274",{"slug":466,"name":466,"fn":467,"description":468,"org":469,"tags":470,"stars":21,"repoUrl":22,"updatedAt":478},"next","plan benchmarking and coverage tasks","Plan upcoming work, analyze coverage gaps, and recommend next steps for benchmarking.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[471,472,475],{"name":13,"slug":14,"type":15},{"name":473,"slug":474,"type":15},"Planning","planning",{"name":476,"slug":477,"type":15},"Strategy","strategy","2026-07-17T06:06:57.69018",{"slug":480,"name":480,"fn":481,"description":482,"org":483,"tags":484,"stars":21,"repoUrl":22,"updatedAt":492},"report","generate CodeScaleBench evaluation reports","Generate evaluation reports, analyze run costs, and compare configurations.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[485,488,489],{"name":486,"slug":487,"type":15},"Analytics","analytics",{"name":13,"slug":14,"type":15},{"name":490,"slug":491,"type":15},"Reporting","reporting","2026-07-16T06:02:36.809556",{"slug":494,"name":494,"fn":495,"description":496,"org":497,"tags":498,"stars":21,"repoUrl":22,"updatedAt":506},"run","manage CodeScaleBench benchmark runs","Launch and manage CodeScaleBench benchmark runs with paired-run guardrails, quick reruns, and execution orchestration.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[499,502,503],{"name":500,"slug":501,"type":15},"Automation","automation",{"name":13,"slug":14,"type":15},{"name":504,"slug":505,"type":15},"Testing","testing","2026-07-16T06:04:40.848817",{"slug":508,"name":508,"fn":509,"description":510,"org":511,"tags":512,"stars":21,"repoUrl":22,"updatedAt":516},"scaffold","create and validate benchmark tasks","Create, mine, and validate new benchmark tasks and task suites.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[513,514,515],{"name":13,"slug":14,"type":15},{"name":444,"slug":445,"type":15},{"name":504,"slug":505,"type":15},"2026-07-16T06:04:41.525889",{"slug":518,"name":518,"fn":519,"description":520,"org":521,"tags":522,"stars":21,"repoUrl":22,"updatedAt":527},"status","monitor benchmark execution and task status","Monitor active runs, check task completion status, and watch benchmark execution progress.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[523,524],{"name":13,"slug":14,"type":15},{"name":525,"slug":526,"type":15},"Monitoring","monitoring","2026-07-16T06:02:37.137106",{"slug":529,"name":529,"fn":530,"description":531,"org":532,"tags":533,"stars":21,"repoUrl":22,"updatedAt":540},"triage","triage and analyze failed benchmark tasks","Investigate and triage failed benchmark tasks, analyze root causes, and plan reruns.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[534,535,538],{"name":13,"slug":14,"type":15},{"name":536,"slug":537,"type":15},"Debugging","debugging",{"name":539,"slug":529,"type":15},"Triage","2026-07-16T06:02:37.472337",{"items":542,"total":207},[543,549,556,563,569,575,581],{"slug":4,"name":4,"fn":5,"description":6,"org":544,"tags":545,"stars":21,"repoUrl":22,"updatedAt":23},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[546,547,548],{"name":20,"slug":4,"type":15},{"name":13,"slug":14,"type":15},{"name":17,"slug":18,"type":15},{"slug":434,"name":434,"fn":435,"description":436,"org":550,"tags":551,"stars":21,"repoUrl":22,"updatedAt":449},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[552,553,554,555],{"name":13,"slug":14,"type":15},{"name":441,"slug":442,"type":15},{"name":444,"slug":445,"type":15},{"name":447,"slug":448,"type":15},{"slug":451,"name":451,"fn":452,"description":453,"org":557,"tags":558,"stars":21,"repoUrl":22,"updatedAt":464},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[559,560,561,562],{"name":20,"slug":4,"type":15},{"name":444,"slug":445,"type":15},{"name":459,"slug":460,"type":15},{"name":462,"slug":463,"type":15},{"slug":466,"name":466,"fn":467,"description":468,"org":564,"tags":565,"stars":21,"repoUrl":22,"updatedAt":478},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[566,567,568],{"name":13,"slug":14,"type":15},{"name":473,"slug":474,"type":15},{"name":476,"slug":477,"type":15},{"slug":480,"name":480,"fn":481,"description":482,"org":570,"tags":571,"stars":21,"repoUrl":22,"updatedAt":492},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[572,573,574],{"name":486,"slug":487,"type":15},{"name":13,"slug":14,"type":15},{"name":490,"slug":491,"type":15},{"slug":494,"name":494,"fn":495,"description":496,"org":576,"tags":577,"stars":21,"repoUrl":22,"updatedAt":506},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[578,579,580],{"name":500,"slug":501,"type":15},{"name":13,"slug":14,"type":15},{"name":504,"slug":505,"type":15},{"slug":508,"name":508,"fn":509,"description":510,"org":582,"tags":583,"stars":21,"repoUrl":22,"updatedAt":516},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[584,585,586],{"name":13,"slug":14,"type":15},{"name":444,"slug":445,"type":15},{"name":504,"slug":505,"type":15}]