[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M791DF1V8KVXH506YGCMNPMG":3,"skill-same:01M791DF1V8KVXH506YGCMNPMG":71},{"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},"01M791DF1V8KVXH506YGCMNPMG","advanced-contrib",null,"Route and use optional NumPyro contrib workflows while keeping dependency and core-API boundaries explicit.","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\u002Fnumpyro\u002Fsub-skills\u002Fadvanced-contrib\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: advanced-contrib\ndescription: \"Route and use optional NumPyro contrib workflows while keeping\n  dependency and core-API boundaries explicit.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# advanced-contrib\n\nUse this sub-skill when a NumPyro task explicitly involves optional or experimental `numpyro.contrib.*` workflows rather than always-installed core modeling, distributions, MCMC, or SVI.\n\n## Triggers\n\nLoad this sub-skill for requests involving:\n\n- `numpyro.contrib.funsor` enumeration helpers: `config_enumerate`, `infer_discrete`, `markov`, enum handlers, or exact marginalization of discrete latent variables.\n- Hilbert-space Gaussian process approximations in `numpyro.contrib.hsgp`.\n- `numpyro.contrib.nested_sampling.NestedSampler` and nested sampling through `jaxns`.\n- `numpyro.contrib.einstein` particle\u002FStein inference: `SteinVI`, `SVGD`, `ASVGD`, Stein kernels, or `MixtureGuidePredictive`.\n- `numpyro.contrib.module` wrappers for Flax Linen, Flax NNX, or Equinox modules.\n- TensorFlow Probability integration through `numpyro.contrib.tfp` or direct TFP JAX substrate distributions in NumPyro models.\n- Stochastic-support inference: `DCC`, `SDVI`, or branch sites marked with `infer={\"branching\": True}`.\n\n## First routing decision\n\n1. If the request is plain `sample`, `param`, `plate`, handlers, `module`, `mutable`, `scan`, or `cond`, route to [modeling-primitives](..\u002Fmodeling-primitives\u002FSKILL.md).\n2. If it is native `numpyro.distributions`, constraints, transforms, support, shapes, or TFP distribution fallback selection, route to [distributions-transforms](..\u002Fdistributions-transforms\u002FSKILL.md) and return here only for TFP-specific caveats.\n3. If it is ordinary `MCMC`, `NUTS`, `HMC`, diagnostics, chain methods, or discrete HMC Gibbs, route to [mcmc-diagnostics](..\u002Fmcmc-diagnostics\u002FSKILL.md) and return here only for `NestedSampler` or TFP MCMC kernels.\n4. If it is ordinary `SVI`, ELBO choice, autoguides, optimizers, or predictive use, route to [svi-autoguides](..\u002Fsvi-autoguides\u002FSKILL.md) and return here only for SteinVI\u002FSVGD\u002FASVGD or `SDVI`.\n5. If the task names `contrib`, an optional dependency, or one of the APIs above, stay in this sub-skill and check optional dependencies before coding.\n\n## Required workflow\n\n- Treat contrib features as optional. A missing optional dependency is not evidence that core NumPyro is broken.\n- Before suggesting or executing contrib code in a minimal environment, run or adapt `scripts\u002Fcheck_optional_dependencies.py`:\n  - `python scripts\u002Fcheck_optional_dependencies.py --pretty`\n  - `python scripts\u002Fcheck_optional_dependencies.py --require nested_sampling`\n  - `python scripts\u002Fcheck_optional_dependencies.py --require module_flax`\n- Keep examples bounded: tiny synthetic data, CPU-safe sample counts, no downloads, no plotting unless the task explicitly asks for plots and plotting dependencies are present.\n- Prefer native NumPyro APIs for core tasks; use contrib only when it adds a capability not covered by the sibling sub-skills.\n\n## Reference map\n\n- [Contrib overview and routing](references\u002Fadvanced-contrib.md)\n- [Optional dependency matrix](references\u002Foptional-dependencies.md)\n- [HSGP, TFP, and nested sampling](references\u002Fhsgp-and-tfp.md)\n- [Troubleshooting optional workflows](references\u002Ftroubleshooting.md)\n","# advanced-contrib\n\nUse this sub-skill when a NumPyro task explicitly involves optional or experimental `numpyro.contrib.*` workflows rather than always-installed core modeling, distributions, MCMC, or SVI.\n\n## Triggers\n\nLoad this sub-skill for requests involving:\n\n- `numpyro.contrib.funsor` enumeration helpers: `config_enumerate`, `infer_discrete`, `markov`, enum handlers, or exact marginalization of discrete latent variables.\n- Hilbert-space Gaussian process approximations in `numpyro.contrib.hsgp`.\n- `numpyro.contrib.nested_sampling.NestedSampler` and nested sampling through `jaxns`.\n- `numpyro.contrib.einstein` particle\u002FStein inference: `SteinVI`, `SVGD`, `ASVGD`, Stein kernels, or `MixtureGuidePredictive`.\n- `numpyro.contrib.module` wrappers for Flax Linen, Flax NNX, or Equinox modules.\n- TensorFlow Probability integration through `numpyro.contrib.tfp` or direct TFP JAX substrate distributions in NumPyro models.\n- Stochastic-support inference: `DCC`, `SDVI`, or branch sites marked with `infer={\"branching\": True}`.\n\n## First routing decision\n\n1. If the request is plain `sample`, `param`, `plate`, handlers, `module`, `mutable`, `scan`, or `cond`, route to [modeling-primitives](..\u002Fmodeling-primitives\u002FSKILL.md).\n2. If it is native `numpyro.distributions`, constraints, transforms, support, shapes, or TFP distribution fallback selection, route to [distributions-transforms](..\u002Fdistributions-transforms\u002FSKILL.md) and return here only for TFP-specific caveats.\n3. If it is ordinary `MCMC`, `NUTS`, `HMC`, diagnostics, chain methods, or discrete HMC Gibbs, route to [mcmc-diagnostics](..\u002Fmcmc-diagnostics\u002FSKILL.md) and return here only for `NestedSampler` or TFP MCMC kernels.\n4. If it is ordinary `SVI`, ELBO choice, autoguides, optimizers, or predictive use, route to [svi-autoguides](..\u002Fsvi-autoguides\u002FSKILL.md) and return here only for SteinVI\u002FSVGD\u002FASVGD or `SDVI`.\n5. If the task names `contrib`, an optional dependency, or one of the APIs above, stay in this sub-skill and check optional dependencies before coding.\n\n## Required workflow\n\n- Treat contrib features as optional. A missing optional dependency is not evidence that core NumPyro is broken.\n- Before suggesting or executing contrib code in a minimal environment, run or adapt `scripts\u002Fcheck_optional_dependencies.py`:\n  - `python scripts\u002Fcheck_optional_dependencies.py --pretty`\n  - `python scripts\u002Fcheck_optional_dependencies.py --require nested_sampling`\n  - `python scripts\u002Fcheck_optional_dependencies.py --require module_flax`\n- Keep examples bounded: tiny synthetic data, CPU-safe sample counts, no downloads, no plotting unless the task explicitly asks for plots and plotting dependencies are present.\n- Prefer native NumPyro APIs for core tasks; use contrib only when it adds a capability not covered by the sibling sub-skills.\n\n## Reference map\n\n- [Contrib overview and routing](references\u002Fadvanced-contrib.md)\n- [Optional dependency matrix](references\u002Foptional-dependencies.md)\n- [HSGP, TFP, and nested sampling](references\u002Fhsgp-and-tfp.md)\n- [Troubleshooting optional workflows](references\u002Ftroubleshooting.md)\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\u002Fnumpyro\u002Fsub-skills\u002Fadvanced-contrib",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 advanced-contrib",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill advanced-contrib",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill advanced-contrib","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fnumpyro\u002Fsub-skills\u002Fadvanced-contrib\u002FSKILL.md",[47,53,57,61,65],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fadvanced-contrib.md","REFERENCE","参考文档",11625,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fnumpyro\u002Fsub-skills\u002Fadvanced-contrib\u002Freferences\u002Fadvanced-contrib.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fhsgp-and-tfp.md",7485,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fnumpyro\u002Fsub-skills\u002Fadvanced-contrib\u002Freferences\u002Fhsgp-and-tfp.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Foptional-dependencies.md",5971,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fnumpyro\u002Fsub-skills\u002Fadvanced-contrib\u002Freferences\u002Foptional-dependencies.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Ftroubleshooting.md",8088,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fnumpyro\u002Fsub-skills\u002Fadvanced-contrib\u002Freferences\u002Ftroubleshooting.md",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Fcheck_optional_dependencies.py","SCRIPT","脚本",7877,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fnumpyro\u002Fsub-skills\u002Fadvanced-contrib\u002Fscripts\u002Fcheck_optional_dependencies.py",[72,79,86,93,100,107],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"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":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"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":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"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":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"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":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"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":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"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",[],[]]