[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78T6C360DKZARQPC8J3JB5W":3,"skill-same:01M78T6C360DKZARQPC8J3JB5W":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},"01M78T6C360DKZARQPC8J3JB5W","repo-maintenance",null,"Maintain a BayesianOptimization checkout with safe install, test, lint, docs, CI-matrix, and release-boundary guidance.","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\u002Fbayesian-optimization\u002Fsub-skills\u002Frepo-maintenance\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: repo-maintenance\ndescription: \"Maintain a BayesianOptimization checkout with safe install, test,\n  lint, docs, CI-matrix, and release-boundary guidance.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Repo Maintenance\n\nUse this sub-skill only when the user is maintaining or editing a\n`bayesian-optimization` source checkout. It covers development installs,\nfocused native tests, lint\u002Fformat decisions, docs\u002Fnotebook checks, CI matrix\nexpectations, and safe debugging paths.\n\nFor package usage questions, route away from maintenance:\n\n- Optimizer construction, registration\u002Fprobing, fitting, save\u002Fload, or\n  prediction workflows: [`..\u002Foptimizer-workflows\u002FSKILL.md`](..\u002Foptimizer-workflows\u002FSKILL.md)\n- Acquisition-function selection or exploration\u002Fexploitation controls:\n  [`..\u002Facquisition-control\u002FSKILL.md`](..\u002Facquisition-control\u002FSKILL.md)\n- Constraints, typed parameters, categorical\u002Finteger domains, sequential domain\n  reduction, or advanced examples:\n  [`..\u002Fadvanced-domain-features\u002FSKILL.md`](..\u002Fadvanced-domain-features\u002FSKILL.md)\n\n## Maintainer workflow\n\n1. Identify touched checkout files and choose the smallest native checks from\n   [`references\u002Fdevelopment-workflows.md`](references\u002Fdevelopment-workflows.md).\n2. Prefer non-mutating verification first: focused `pytest`, Ruff format check,\n   and Ruff lint check.\n3. Use [`scripts\u002Fselect_native_checks.py`](scripts\u002Fselect_native_checks.py) to\n   print recommended command groups from touched paths or capability flags. The\n   helper only prints commands; it does not execute them.\n4. Escalate to full unit, notebook, docs, or CI-matrix coverage only when the\n   touched files affect those surfaces or when preparing a broad change.\n5. Use [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) for\n   Python\u002FNumPy marker conflicts, pre-commit or Ruff failures, notebook timeouts,\n   docs build failures, import confusion, and release\u002Fpublish limits.\n\n## Safety rules\n\n- Treat commands as checkout-maintenance commands, not runtime user guidance.\n- Do not run `scripts\u002Fformat.sh` unless the user explicitly wants formatting or\n  automatic fixes; it mutates source files.\n- Do not use `scripts\u002Fcheck_precommit.sh` as a routine verification shortcut; it\n  installs hooks before running all files. Prefer direct non-mutating Ruff or\n  pre-commit commands when verification is enough.\n- Never provide credentialed publishing steps. PyPI publishing is release-only\n  and guarded by repository secrets.\n","# Repo Maintenance\n\nUse this sub-skill only when the user is maintaining or editing a\n`bayesian-optimization` source checkout. It covers development installs,\nfocused native tests, lint\u002Fformat decisions, docs\u002Fnotebook checks, CI matrix\nexpectations, and safe debugging paths.\n\nFor package usage questions, route away from maintenance:\n\n- Optimizer construction, registration\u002Fprobing, fitting, save\u002Fload, or\n  prediction workflows: [`..\u002Foptimizer-workflows\u002FSKILL.md`](..\u002Foptimizer-workflows\u002FSKILL.md)\n- Acquisition-function selection or exploration\u002Fexploitation controls:\n  [`..\u002Facquisition-control\u002FSKILL.md`](..\u002Facquisition-control\u002FSKILL.md)\n- Constraints, typed parameters, categorical\u002Finteger domains, sequential domain\n  reduction, or advanced examples:\n  [`..\u002Fadvanced-domain-features\u002FSKILL.md`](..\u002Fadvanced-domain-features\u002FSKILL.md)\n\n## Maintainer workflow\n\n1. Identify touched checkout files and choose the smallest native checks from\n   [`references\u002Fdevelopment-workflows.md`](references\u002Fdevelopment-workflows.md).\n2. Prefer non-mutating verification first: focused `pytest`, Ruff format check,\n   and Ruff lint check.\n3. Use [`scripts\u002Fselect_native_checks.py`](scripts\u002Fselect_native_checks.py) to\n   print recommended command groups from touched paths or capability flags. The\n   helper only prints commands; it does not execute them.\n4. Escalate to full unit, notebook, docs, or CI-matrix coverage only when the\n   touched files affect those surfaces or when preparing a broad change.\n5. Use [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) for\n   Python\u002FNumPy marker conflicts, pre-commit or Ruff failures, notebook timeouts,\n   docs build failures, import confusion, and release\u002Fpublish limits.\n\n## Safety rules\n\n- Treat commands as checkout-maintenance commands, not runtime user guidance.\n- Do not run `scripts\u002Fformat.sh` unless the user explicitly wants formatting or\n  automatic fixes; it mutates source files.\n- Do not use `scripts\u002Fcheck_precommit.sh` as a routine verification shortcut; it\n  installs hooks before running all files. Prefer direct non-mutating Ruff or\n  pre-commit commands when verification is enough.\n- Never provide credentialed publishing steps. PyPI publishing is release-only\n  and guarded by repository secrets.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fbayesian-optimization\u002Fsub-skills\u002Frepo-maintenance",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 repo-maintenance",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill repo-maintenance",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill repo-maintenance","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fbayesian-optimization\u002Fsub-skills\u002Frepo-maintenance\u002FSKILL.md",[46,52,56],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fdevelopment-workflows.md","REFERENCE","参考文档",8698,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fbayesian-optimization\u002Fsub-skills\u002Frepo-maintenance\u002Freferences\u002Fdevelopment-workflows.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Ftroubleshooting.md",8872,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fbayesian-optimization\u002Fsub-skills\u002Frepo-maintenance\u002Freferences\u002Ftroubleshooting.md",{"path":57,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":60,"sourceHtmlUrl":61},"scripts\u002Fselect_native_checks.py","SCRIPT","脚本",16614,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fbayesian-optimization\u002Fsub-skills\u002Frepo-maintenance\u002Fscripts\u002Fselect_native_checks.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",[],[]]