[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78T0VGMKK4ZDVPVXC04Z95S":3,"skill-same:01M78T0VGMKK4ZDVPVXC04Z95S":74},{"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},"01M78T0VGMKK4ZDVPVXC04Z95S","optimization-workflows",null,"Route users who need flatten\u002Funflatten helpers, structured optimizers, fixed-point differentiation helpers, and SciPy minimize integration using value_and_grad.","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\u002Fautograd\u002Fsub-skills\u002Foptimization-workflows\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: optimization-workflows\ndescription: \"Route users who need flatten\u002Funflatten helpers, structured\n  optimizers, fixed-point differentiation helpers, and SciPy minimize\n  integration using value_and_grad.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Optimization Workflows\n\nUse this sub-skill for optimization tasks built from nested parameter trees,\nfixed-point recurrences, or SciPy minimization loops.\n\n## Route here when the user needs\n\n- `flatten` or `flatten_func` to turn nested dict\u002Flist\u002Ftuple parameter trees\n  into flat arrays and back.\n- Structured optimizers such as `sgd`, `rmsprop`, or `adam` on nested\n  containers.\n- `fixed_point` for differentiable iterative updates.\n- `scipy.optimize.minimize` combined with `value_and_grad`.\n\n## Route elsewhere when the question is really about\n\n- `value_and_grad` semantics, scalar-output constraints, or Jacobian\u002FHessian\n  selection: [differentiation-core](..\u002Fdifferentiation-core\u002FSKILL.md).\n- General `autograd.scipy` wrapper behavior or SciPy wrapper coverage:\n  [numpy-scipy-primitives](..\u002Fnumpy-scipy-primitives\u002FSKILL.md).\n- Custom primitive or staged VJP\u002FJVP mechanics:\n  [extend-primitives](..\u002Fextend-primitives\u002FSKILL.md).\n\n## Bundled runtime helpers\n\n- `scripts\u002Fstructured_optimizer_smoke.py`\n- `scripts\u002Frosenbrock_minimize.py`\n- `scripts\u002Ffixed_point_smoke.py`\n\nThese scripts use tiny synthetic fixtures only; they do not download data and\nthere is no CLI entry point to discover.\n\n## What this sub-skill does not own\n\n- Ordinary differentiation operators and higher-order autodiff semantics.\n- Custom primitive registration or gradient-rule authoring.\n- General NumPy\u002FSciPy wrapper troubleshooting outside optimization workflows.\n","# Optimization Workflows\n\nUse this sub-skill for optimization tasks built from nested parameter trees,\nfixed-point recurrences, or SciPy minimization loops.\n\n## Route here when the user needs\n\n- `flatten` or `flatten_func` to turn nested dict\u002Flist\u002Ftuple parameter trees\n  into flat arrays and back.\n- Structured optimizers such as `sgd`, `rmsprop`, or `adam` on nested\n  containers.\n- `fixed_point` for differentiable iterative updates.\n- `scipy.optimize.minimize` combined with `value_and_grad`.\n\n## Route elsewhere when the question is really about\n\n- `value_and_grad` semantics, scalar-output constraints, or Jacobian\u002FHessian\n  selection: [differentiation-core](..\u002Fdifferentiation-core\u002FSKILL.md).\n- General `autograd.scipy` wrapper behavior or SciPy wrapper coverage:\n  [numpy-scipy-primitives](..\u002Fnumpy-scipy-primitives\u002FSKILL.md).\n- Custom primitive or staged VJP\u002FJVP mechanics:\n  [extend-primitives](..\u002Fextend-primitives\u002FSKILL.md).\n\n## Bundled runtime helpers\n\n- `scripts\u002Fstructured_optimizer_smoke.py`\n- `scripts\u002Frosenbrock_minimize.py`\n- `scripts\u002Ffixed_point_smoke.py`\n\nThese scripts use tiny synthetic fixtures only; they do not download data and\nthere is no CLI entry point to discover.\n\n## What this sub-skill does not own\n\n- Ordinary differentiation operators and higher-order autodiff semantics.\n- Custom primitive registration or gradient-rule authoring.\n- General NumPy\u002FSciPy wrapper troubleshooting outside optimization workflows.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fautograd\u002Fsub-skills\u002Foptimization-workflows",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 optimization-workflows",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill optimization-workflows",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill optimization-workflows","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fautograd\u002Fsub-skills\u002Foptimization-workflows\u002FSKILL.md",[46,52,56,60,66,70],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fapi-reference.md","REFERENCE","参考文档",3491,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fautograd\u002Fsub-skills\u002Foptimization-workflows\u002Freferences\u002Fapi-reference.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Ftroubleshooting.md",3057,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fautograd\u002Fsub-skills\u002Foptimization-workflows\u002Freferences\u002Ftroubleshooting.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fworkflows.md",3071,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fautograd\u002Fsub-skills\u002Foptimization-workflows\u002Freferences\u002Fworkflows.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Ffixed_point_smoke.py","SCRIPT","脚本",936,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fautograd\u002Fsub-skills\u002Foptimization-workflows\u002Fscripts\u002Ffixed_point_smoke.py",{"path":67,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Frosenbrock_minimize.py",679,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fautograd\u002Fsub-skills\u002Foptimization-workflows\u002Fscripts\u002Frosenbrock_minimize.py",{"path":71,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":72,"sourceHtmlUrl":73},"scripts\u002Fstructured_optimizer_smoke.py",3525,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fautograd\u002Fsub-skills\u002Foptimization-workflows\u002Fscripts\u002Fstructured_optimizer_smoke.py",[75,83,90,97,104,111],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"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.","Apache-2.0","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":79,"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":79,"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":79,"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":79,"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":79,"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",[],[]]