[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78WWAMZ2JRJXZN2AQK2A7E9":3,"skill-same:01M78WWAMZ2JRJXZN2AQK2A7E9":62},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":32,"install":33,"resources":45},"01M78WWAMZ2JRJXZN2AQK2A7E9","installation",null,"Install, inspect, and troubleshoot Fairlearn runtimes, optional plotting\u002Fadversarial dependencies, and version diagnostics.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"MIT","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ffairlearn\u002Fsub-skills\u002Finstallation\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: installation\ndescription: \"Install, inspect, and troubleshoot Fairlearn runtimes, optional\n  plotting\u002Fadversarial dependencies, and version diagnostics.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Fairlearn installation\n\nUse this sub-skill when the task is about installing Fairlearn, confirming imports, inspecting versions, optional dependencies, plotting extras, PyTorch\u002FTensorFlow adversarial backends, `show_versions`, missing dependency errors, or package-runtime diagnostics.\n\n## Quick workflow\n\n1. Determine whether the user is using a released package, a local checkout, or a prepared environment.\n2. Install the smallest dependency set needed for the requested workflow.\n3. Run the root check script or the wrapper in this sub-skill.\n4. If optional plotting or adversarial backends are absent, decide whether the requested workflow actually requires them before installing.\n5. Route back to the workflow-owning sub-skill after imports and optional dependencies are resolved.\n\n## Read these references\n\n- [`..\u002F..\u002Freferences\u002Finstallation.md`](..\u002F..\u002Freferences\u002Finstallation.md) for root install commands, optional dependency table, raw import checks, and `show_versions` guidance.\n- [`references\u002Fruntime-and-version-checks.md`](references\u002Fruntime-and-version-checks.md) for workflow-specific runtime probes and version diagnostics.\n- [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) for install\u002Fimport, extras, `show_versions`, backend, and version-skew recovery.\n- [`scripts\u002Fcheck_runtime.py`](scripts\u002Fcheck_runtime.py) wraps the root installation check from this sub-skill location.\n\n## Core facts\n\n- Package name: `fairlearn`.\n- Python requirement in the inspected source: `>=3.11`.\n- Core dependencies: `narwhals`, `numpy`, `pandas`, `scikit-learn`, and `scipy`.\n- Public version check: `import fairlearn; print(fairlearn.__version__)`.\n- Environment report: `fairlearn.show_versions()`.\n- No Fairlearn-specific CLI entry points were found in the inspected source.\n\n## Optional dependency ownership\n\n| Dependency | Owned workflow | First route |\n| --- | --- | --- |\n| `matplotlib` | assessment and postprocessing plots | `..\u002Fassessment\u002F` or `..\u002Fpostprocessing\u002F` |\n| `torch` | PyTorch adversarial backend | `..\u002Fadversarial\u002F` |\n| `tensorflow` \u002F `keras` | TensorFlow adversarial backend | `..\u002Fadversarial\u002F` with explicit unverified-backend note |\n| OpenML\u002Fnetwork\u002Fcache | dataset loaders | `..\u002Fdatasets\u002F` |\n\n## Fast validation\n\nFrom this skill directory:\n\n```bash\npython sub-skills\u002Finstallation\u002Fscripts\u002Fcheck_runtime.py --include-optional\n```\n\nOr from the root skill directory:\n\n```bash\npython scripts\u002Fcheck_install.py --include-optional\n```\n\nIf the check passes but a workflow still fails, switch to that workflow's troubleshooting reference.\n","# Fairlearn installation\n\nUse this sub-skill when the task is about installing Fairlearn, confirming imports, inspecting versions, optional dependencies, plotting extras, PyTorch\u002FTensorFlow adversarial backends, `show_versions`, missing dependency errors, or package-runtime diagnostics.\n\n## Quick workflow\n\n1. Determine whether the user is using a released package, a local checkout, or a prepared environment.\n2. Install the smallest dependency set needed for the requested workflow.\n3. Run the root check script or the wrapper in this sub-skill.\n4. If optional plotting or adversarial backends are absent, decide whether the requested workflow actually requires them before installing.\n5. Route back to the workflow-owning sub-skill after imports and optional dependencies are resolved.\n\n## Read these references\n\n- [`..\u002F..\u002Freferences\u002Finstallation.md`](..\u002F..\u002Freferences\u002Finstallation.md) for root install commands, optional dependency table, raw import checks, and `show_versions` guidance.\n- [`references\u002Fruntime-and-version-checks.md`](references\u002Fruntime-and-version-checks.md) for workflow-specific runtime probes and version diagnostics.\n- [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) for install\u002Fimport, extras, `show_versions`, backend, and version-skew recovery.\n- [`scripts\u002Fcheck_runtime.py`](scripts\u002Fcheck_runtime.py) wraps the root installation check from this sub-skill location.\n\n## Core facts\n\n- Package name: `fairlearn`.\n- Python requirement in the inspected source: `>=3.11`.\n- Core dependencies: `narwhals`, `numpy`, `pandas`, `scikit-learn`, and `scipy`.\n- Public version check: `import fairlearn; print(fairlearn.__version__)`.\n- Environment report: `fairlearn.show_versions()`.\n- No Fairlearn-specific CLI entry points were found in the inspected source.\n\n## Optional dependency ownership\n\n| Dependency | Owned workflow | First route |\n| --- | --- | --- |\n| `matplotlib` | assessment and postprocessing plots | `..\u002Fassessment\u002F` or `..\u002Fpostprocessing\u002F` |\n| `torch` | PyTorch adversarial backend | `..\u002Fadversarial\u002F` |\n| `tensorflow` \u002F `keras` | TensorFlow adversarial backend | `..\u002Fadversarial\u002F` with explicit unverified-backend note |\n| OpenML\u002Fnetwork\u002Fcache | dataset loaders | `..\u002Fdatasets\u002F` |\n\n## Fast validation\n\nFrom this skill directory:\n\n```bash\npython sub-skills\u002Finstallation\u002Fscripts\u002Fcheck_runtime.py --include-optional\n```\n\nOr from the root skill directory:\n\n```bash\npython scripts\u002Fcheck_install.py --include-optional\n```\n\nIf the check passes but a workflow still fails, switch to that workflow's troubleshooting reference.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Ffairlearn\u002Fsub-skills\u002Finstallation",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":25},[35,38,41],{"tool":36,"command":37},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill installation",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill installation",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill installation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ffairlearn\u002Fsub-skills\u002Finstallation\u002FSKILL.md",[46,52,56],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fruntime-and-version-checks.md","REFERENCE","参考文档",2968,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ffairlearn\u002Fsub-skills\u002Finstallation\u002Freferences\u002Fruntime-and-version-checks.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Ftroubleshooting.md",1832,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ffairlearn\u002Fsub-skills\u002Finstallation\u002Freferences\u002Ftroubleshooting.md",{"path":57,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":60,"sourceHtmlUrl":61},"scripts\u002Fcheck_runtime.py","SCRIPT","脚本",606,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ffairlearn\u002Fsub-skills\u002Finstallation\u002Fscripts\u002Fcheck_runtime.py",[63,71,78,85,92,99],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":67,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"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.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":67,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"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":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":67,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"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":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":67,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"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":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":67,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"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":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":67,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"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",[],[]]