[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78SA5WVECGFFTY7SZGTWS43":3,"skill-same:01M78SA5WVECGFFTY7SZGTWS43":75},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":46},"01M78SA5WVECGFFTY7SZGTWS43","detectors-and-explainers",null,"Use AIF360 MDSS and FACTS subgroup detectors plus metric text and JSON explainers.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Faif360\u002Fsub-skills\u002Fdetectors-and-explainers\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: detectors-and-explainers\ndescription: \"Use AIF360 MDSS and FACTS subgroup detectors plus metric text and\n  JSON explainers.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# AIF360 Detectors and Explainers\n\nUse this sub-skill when a task asks for subgroup bias scanning, MDSS\u002FFACTS\ndetectors, or text\u002FJSON explanations of AIF360 metric objects.\n\n## Start here\n\n1. Read [mdss-workflow.md](references\u002Fmdss-workflow.md) for legacy and sklearn\n   `bias_scan` signatures, inputs, modes, scoring choices, and output handling.\n2. Read [facts-workflow.md](references\u002Ffacts-workflow.md) for optional FACTS\n   counterfactual subgroup-recourse workflows and dependency requirements.\n3. Read [explainer-reference.md](references\u002Fexplainer-reference.md) for\n   `MetricTextExplainer` and `MetricJSONExplainer` usage with metric objects.\n4. Read [troubleshooting.md](references\u002Ftroubleshooting.md) when labels,\n   probabilities, indexes, optional extras, or metric objects do not match.\n5. Use [mdss_smoke.py](scripts\u002Fmdss_smoke.py) or\n   [explainer_smoke.py](scripts\u002Fexplainer_smoke.py) for no-download base smoke\n   checks.\n\n## Route by user intent\n\n| User asks for... | Use this route |\n| --- | --- |\n| \"Find a subgroup with unusually high error or bias\" | Use MDSS `bias_scan`; read [mdss-workflow.md](references\u002Fmdss-workflow.md). |\n| \"Score a known subgroup with MDSS inside classification metrics\" | Use `MDSSClassificationMetric` via [datasets-and-metrics](..\u002Fdatasets-and-metrics\u002FSKILL.md), then return here for scan interpretation if needed. |\n| \"Find subgroups that have worse recourse\u002Fcounterfactual action costs\" | Use optional FACTS; read [facts-workflow.md](references\u002Ffacts-workflow.md). |\n| \"Explain what this metric means in text or JSON\" | Use [explainer-reference.md](references\u002Fexplainer-reference.md). |\n| \"Compute fairness metrics before scanning\" | Route to [..\u002Fdatasets-and-metrics\u002FSKILL.md](..\u002Fdatasets-and-metrics\u002FSKILL.md) for legacy metrics or [..\u002Fsklearn-interface\u002FSKILL.md](..\u002Fsklearn-interface\u002FSKILL.md) for pandas metrics. |\n| \"Mitigate bias after detecting a problem\" | Route to [..\u002Fmitigation-algorithms\u002FSKILL.md](..\u002Fmitigation-algorithms\u002FSKILL.md). |\n\n## Detector\u002Fexplainer distinction\n\n- **MDSS detectors** search for subgroups whose observed outcomes differ from\n  expectations under a scoring function.\n- **FACTS** searches for subgroups with unequal counterfactual recourse cost or\n  effectiveness; it is optional-extra gated.\n- **Metric explainers** wrap an existing AIF360 metric object and render method\n  outputs in human-readable text or structured JSON; they do not compute new\n  metrics independently.\n\n## Safe smoke checks\n\n```bash\npython sub-skills\u002Fdetectors-and-explainers\u002Fscripts\u002Fmdss_smoke.py --json\npython sub-skills\u002Fdetectors-and-explainers\u002Fscripts\u002Fexplainer_smoke.py --json\n```\n\nBoth scripts use synthetic in-memory data and require only the base package\nsurface that was verified for this skill construction run.\n","# AIF360 Detectors and Explainers\n\nUse this sub-skill when a task asks for subgroup bias scanning, MDSS\u002FFACTS\ndetectors, or text\u002FJSON explanations of AIF360 metric objects.\n\n## Start here\n\n1. Read [mdss-workflow.md](references\u002Fmdss-workflow.md) for legacy and sklearn\n   `bias_scan` signatures, inputs, modes, scoring choices, and output handling.\n2. Read [facts-workflow.md](references\u002Ffacts-workflow.md) for optional FACTS\n   counterfactual subgroup-recourse workflows and dependency requirements.\n3. Read [explainer-reference.md](references\u002Fexplainer-reference.md) for\n   `MetricTextExplainer` and `MetricJSONExplainer` usage with metric objects.\n4. Read [troubleshooting.md](references\u002Ftroubleshooting.md) when labels,\n   probabilities, indexes, optional extras, or metric objects do not match.\n5. Use [mdss_smoke.py](scripts\u002Fmdss_smoke.py) or\n   [explainer_smoke.py](scripts\u002Fexplainer_smoke.py) for no-download base smoke\n   checks.\n\n## Route by user intent\n\n| User asks for... | Use this route |\n| --- | --- |\n| \"Find a subgroup with unusually high error or bias\" | Use MDSS `bias_scan`; read [mdss-workflow.md](references\u002Fmdss-workflow.md). |\n| \"Score a known subgroup with MDSS inside classification metrics\" | Use `MDSSClassificationMetric` via [datasets-and-metrics](..\u002Fdatasets-and-metrics\u002FSKILL.md), then return here for scan interpretation if needed. |\n| \"Find subgroups that have worse recourse\u002Fcounterfactual action costs\" | Use optional FACTS; read [facts-workflow.md](references\u002Ffacts-workflow.md). |\n| \"Explain what this metric means in text or JSON\" | Use [explainer-reference.md](references\u002Fexplainer-reference.md). |\n| \"Compute fairness metrics before scanning\" | Route to [..\u002Fdatasets-and-metrics\u002FSKILL.md](..\u002Fdatasets-and-metrics\u002FSKILL.md) for legacy metrics or [..\u002Fsklearn-interface\u002FSKILL.md](..\u002Fsklearn-interface\u002FSKILL.md) for pandas metrics. |\n| \"Mitigate bias after detecting a problem\" | Route to [..\u002Fmitigation-algorithms\u002FSKILL.md](..\u002Fmitigation-algorithms\u002FSKILL.md). |\n\n## Detector\u002Fexplainer distinction\n\n- **MDSS detectors** search for subgroups whose observed outcomes differ from\n  expectations under a scoring function.\n- **FACTS** searches for subgroups with unequal counterfactual recourse cost or\n  effectiveness; it is optional-extra gated.\n- **Metric explainers** wrap an existing AIF360 metric object and render method\n  outputs in human-readable text or structured JSON; they do not compute new\n  metrics independently.\n\n## Safe smoke checks\n\n```bash\npython sub-skills\u002Fdetectors-and-explainers\u002Fscripts\u002Fmdss_smoke.py --json\npython sub-skills\u002Fdetectors-and-explainers\u002Fscripts\u002Fexplainer_smoke.py --json\n```\n\nBoth scripts use synthetic in-memory data and require only the base package\nsurface that was verified for this skill construction run.\n",{"name":5,"license":23,"metadata":24,"description":7,"disable-model-invocation":26},"Apache 2.0",{"disco-role":25},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Faif360\u002Fsub-skills\u002Fdetectors-and-explainers",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":26},[36,39,42],{"tool":37,"command":38},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill detectors-and-explainers",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill detectors-and-explainers",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill detectors-and-explainers","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Faif360\u002Fsub-skills\u002Fdetectors-and-explainers\u002FSKILL.md",[47,53,57,61,65,71],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fexplainer-reference.md","REFERENCE","参考文档",2975,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Faif360\u002Fsub-skills\u002Fdetectors-and-explainers\u002Freferences\u002Fexplainer-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Ffacts-workflow.md",2354,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Faif360\u002Fsub-skills\u002Fdetectors-and-explainers\u002Freferences\u002Ffacts-workflow.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fmdss-workflow.md",3102,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Faif360\u002Fsub-skills\u002Fdetectors-and-explainers\u002Freferences\u002Fmdss-workflow.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Ftroubleshooting.md",3445,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Faif360\u002Fsub-skills\u002Fdetectors-and-explainers\u002Freferences\u002Ftroubleshooting.md",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Fexplainer_smoke.py","SCRIPT","脚本",2720,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Faif360\u002Fsub-skills\u002Fdetectors-and-explainers\u002Fscripts\u002Fexplainer_smoke.py",{"path":72,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":73,"sourceHtmlUrl":74},"scripts\u002Fmdss_smoke.py",2152,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Faif360\u002Fsub-skills\u002Fdetectors-and-explainers\u002Fscripts\u002Fmdss_smoke.py",[76,83,90,97,104,111],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":18},"01M799NYSH1R3RVAHSM2D88Y84","passnet-triton-opt","Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block\u002Fgrid\u002Fwarp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":18},"01M799NS5APEC0N1FZ7XZVW6BN","passnet-solve","END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-solve\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":18},"01M799NNY9BKSM21V5R7QVTBJX","passnet-skill","PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under .\u002Fpass_dir\u002F, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-skill\u002FSKILL.md",[],[],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":18},"01M799NHH6NP7Z1RK77KGXAN6S","passnet-pattern-fusion","Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()\u002Freplacement_args()\u002Freplacement_func() files, when a pass \"failed to match\", or when deciding how to fuse multiple kernels\u002Fops.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-pattern-fusion\u002FSKILL.md",[],[],{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":18},"01M799ND2J4WNC2PGAZ0A06NDF","passnet-orchestrate","Round\u002Fbatch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep\u002Frevert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-orchestrate\u002FSKILL.md",[],[],{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"publishedAt":18},"01M799N8SBTMY02ZDG2AZF5ZWE","passnet-feedback","Fast, deterministic feedback for PassNet work: pre-flight pattern\u002Fmatch verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-feedback\u002FSKILL.md",[],[]]