[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M793FDPASB6F62M7GP0SGTMR":3,"skill-same:01M793FDPASB6F62M7GP0SGTMR":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},"01M793FDPASB6F62M7GP0SGTMR","pyro",null,"Use Pyro probabilistic programming APIs for models, distributions, SVI, MCMC, poutine, enumeration, and contrib workflows.","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\u002Fpyro\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: pyro\ndescription: \"Use Pyro probabilistic programming APIs for models, distributions,\n  SVI, MCMC, poutine, enumeration, and contrib workflows.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Pyro Repo Skill\n\nUse this repo skill when the task involves the `pyro-ppl` package imported as\n`pyro`: probabilistic models, distributions, stochastic variational inference,\nHMC\u002FNUTS\u002FMCMC, posterior prediction, poutine effect handlers, discrete\nenumeration, reparameterizers, `PyroModule`, or Pyro contributed modules.\n\nThis skill targets the Pyro 1.9.1 API family. It is self-contained for package\nuse; do not depend on a source checkout, original examples, original tests, or\nnotebooks at runtime.\n\n## Install and Import Check\n\nPyro's distribution name is `pyro-ppl` and the import name is `pyro`:\n\n```bash\npython -m pip install pyro-ppl\npython - \u003C\u003C'PY'\nimport pyro, torch\nprint(pyro.__version__)\nprint(torch.__version__, torch.cuda.is_available())\nPY\n```\n\nFor a safe diagnostic that also reports optional integrations, run\n[scripts\u002Fcheck_pyro_environment.py](scripts\u002Fcheck_pyro_environment.py). Start\nwith `python scripts\u002Fcheck_pyro_environment.py --help`; use `--smoke` to run a\ntiny CPU SVI check.\n\n## Route by Task\n\n- Basic stochastic functions, `pyro.sample`, `pyro.param`, observed sites,\n  `pyro.plate`, parameter-store state, validation, RNG seeds, `PyroModule`,\n  `PyroParam`, and `PyroSample`: read\n  [sub-skills\u002Fmodeling-basics\u002FSKILL.md](sub-skills\u002Fmodeling-basics\u002FSKILL.md).\n- Distribution selection, constraints\u002Ftransforms, `.to_event()`, `Independent`,\n  HMM\u002Fzero-inflated\u002Fstable\u002Fmatching distributions, and event\u002Fbatch\u002Fplate shape\n  debugging: read\n  [sub-skills\u002Fdistributions-and-shapes\u002FSKILL.md](sub-skills\u002Fdistributions-and-shapes\u002FSKILL.md).\n- SVI training loops, ELBO choice, autoguides, Pyro optimizers, vanilla PyTorch\n  optimizer loops, minibatching, JIT\u002Fvectorized particles, and SVI\n  troubleshooting: read\n  [sub-skills\u002Fsvi-and-autoguides\u002FSKILL.md](sub-skills\u002Fsvi-and-autoguides\u002FSKILL.md).\n- HMC\u002FNUTS\u002FMCMC runs, initialization, warmup\u002Fsample\u002Fchain choices, diagnostics,\n  `Predictive`, `WeighedPredictive`, and posterior\u002Fprior predictive shapes:\n  read\n  [sub-skills\u002Fmcmc-and-prediction\u002FSKILL.md](sub-skills\u002Fmcmc-and-prediction\u002FSKILL.md).\n- Poutine handlers, trace\u002Fcondition\u002Freplay\u002Fblock\u002Fscale\u002Fmask\u002Fseed\u002Fsubstitute,\n  discrete enumeration, `TraceEnum_ELBO`, `infer_discrete`, `config_enumerate`,\n  reparameterizers, and inference-tied `pyro.ops`: read\n  [sub-skills\u002Feffect-handlers-and-enumeration\u002FSKILL.md](sub-skills\u002Feffect-handlers-and-enumeration\u002FSKILL.md).\n- `pyro.contrib`, MiniPyro\u002Fgeneric backend, forecasting, GP, epidemiology,\n  tracking, easyguide, CEVAE, Funsor, Horovod, Lightning, domain examples, and\n  optional dependency policy: read\n  [sub-skills\u002Fcontrib-and-domain-workflows\u002FSKILL.md](sub-skills\u002Fcontrib-and-domain-workflows\u002FSKILL.md).\n\nFor a compact root API map and verified signature highlights, read\n[references\u002Fapi-cheatsheet.md](references\u002Fapi-cheatsheet.md). For install\u002Fimport,\nbackend, optional dependency, validation, and routing failures, read\n[references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md). For staleness\nchecks against a repository checkout, read\n[references\u002Frepo-provenance.md](references\u002Frepo-provenance.md).\n\n## Fast Decision Rules\n\n1. If the user has an error, ask first for the Pyro version, PyTorch version,\n   CPU\u002FCUDA backend, and a minimal model\u002Fguide snippet unless already present.\n2. Turn on validation while debugging: `pyro.enable_validation(True)`.\n3. Clear parameter state between independent experiments:\n   `pyro.clear_param_store()`.\n4. For any shape or plate problem, trace the model and inspect\n   `trace.format_shapes()` before changing model structure.\n5. Do not use HMC\u002FNUTS directly on discrete latent variables. Enumerate,\n   marginalize, or use another inference strategy.\n6. Treat CUDA, Funsor, Horovod, Lightning, Graphviz, torchvision, pandas,\n   scanpy, and long example\u002Ftutorial dependencies as optional until the user's\n   active environment proves support.\n7. Prefer tiny synthetic tensors and this skill's bundled smoke scripts before\n   attempting long training, downloads, plotting, or GPU-specific runs.\n\n## What Not to Use This Skill For\n\n- Generic PyTorch training that does not use Pyro primitives or distributions.\n- PyMC, NumPyro, Bean Machine, Stan, or TensorFlow Probability code unless the\n  task is explicitly translating concepts to Pyro.\n- Full scientific reproduction of every Pyro tutorial\u002Fexample; use this skill\n  to implement or debug the package workflow, then request task-specific data,\n  runtime, and budget.\n- Maintainer release, benchmark, profiling, Docker, or documentation-build work\n  unless the user explicitly asks to edit the Pyro repository.\n","# Pyro Repo Skill\n\nUse this repo skill when the task involves the `pyro-ppl` package imported as\n`pyro`: probabilistic models, distributions, stochastic variational inference,\nHMC\u002FNUTS\u002FMCMC, posterior prediction, poutine effect handlers, discrete\nenumeration, reparameterizers, `PyroModule`, or Pyro contributed modules.\n\nThis skill targets the Pyro 1.9.1 API family. It is self-contained for package\nuse; do not depend on a source checkout, original examples, original tests, or\nnotebooks at runtime.\n\n## Install and Import Check\n\nPyro's distribution name is `pyro-ppl` and the import name is `pyro`:\n\n```bash\npython -m pip install pyro-ppl\npython - \u003C\u003C'PY'\nimport pyro, torch\nprint(pyro.__version__)\nprint(torch.__version__, torch.cuda.is_available())\nPY\n```\n\nFor a safe diagnostic that also reports optional integrations, run\n[scripts\u002Fcheck_pyro_environment.py](scripts\u002Fcheck_pyro_environment.py). Start\nwith `python scripts\u002Fcheck_pyro_environment.py --help`; use `--smoke` to run a\ntiny CPU SVI check.\n\n## Route by Task\n\n- Basic stochastic functions, `pyro.sample`, `pyro.param`, observed sites,\n  `pyro.plate`, parameter-store state, validation, RNG seeds, `PyroModule`,\n  `PyroParam`, and `PyroSample`: read\n  [sub-skills\u002Fmodeling-basics\u002FSKILL.md](sub-skills\u002Fmodeling-basics\u002FSKILL.md).\n- Distribution selection, constraints\u002Ftransforms, `.to_event()`, `Independent`,\n  HMM\u002Fzero-inflated\u002Fstable\u002Fmatching distributions, and event\u002Fbatch\u002Fplate shape\n  debugging: read\n  [sub-skills\u002Fdistributions-and-shapes\u002FSKILL.md](sub-skills\u002Fdistributions-and-shapes\u002FSKILL.md).\n- SVI training loops, ELBO choice, autoguides, Pyro optimizers, vanilla PyTorch\n  optimizer loops, minibatching, JIT\u002Fvectorized particles, and SVI\n  troubleshooting: read\n  [sub-skills\u002Fsvi-and-autoguides\u002FSKILL.md](sub-skills\u002Fsvi-and-autoguides\u002FSKILL.md).\n- HMC\u002FNUTS\u002FMCMC runs, initialization, warmup\u002Fsample\u002Fchain choices, diagnostics,\n  `Predictive`, `WeighedPredictive`, and posterior\u002Fprior predictive shapes:\n  read\n  [sub-skills\u002Fmcmc-and-prediction\u002FSKILL.md](sub-skills\u002Fmcmc-and-prediction\u002FSKILL.md).\n- Poutine handlers, trace\u002Fcondition\u002Freplay\u002Fblock\u002Fscale\u002Fmask\u002Fseed\u002Fsubstitute,\n  discrete enumeration, `TraceEnum_ELBO`, `infer_discrete`, `config_enumerate`,\n  reparameterizers, and inference-tied `pyro.ops`: read\n  [sub-skills\u002Feffect-handlers-and-enumeration\u002FSKILL.md](sub-skills\u002Feffect-handlers-and-enumeration\u002FSKILL.md).\n- `pyro.contrib`, MiniPyro\u002Fgeneric backend, forecasting, GP, epidemiology,\n  tracking, easyguide, CEVAE, Funsor, Horovod, Lightning, domain examples, and\n  optional dependency policy: read\n  [sub-skills\u002Fcontrib-and-domain-workflows\u002FSKILL.md](sub-skills\u002Fcontrib-and-domain-workflows\u002FSKILL.md).\n\nFor a compact root API map and verified signature highlights, read\n[references\u002Fapi-cheatsheet.md](references\u002Fapi-cheatsheet.md). For install\u002Fimport,\nbackend, optional dependency, validation, and routing failures, read\n[references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md). For staleness\nchecks against a repository checkout, read\n[references\u002Frepo-provenance.md](references\u002Frepo-provenance.md).\n\n## Fast Decision Rules\n\n1. If the user has an error, ask first for the Pyro version, PyTorch version,\n   CPU\u002FCUDA backend, and a minimal model\u002Fguide snippet unless already present.\n2. Turn on validation while debugging: `pyro.enable_validation(True)`.\n3. Clear parameter state between independent experiments:\n   `pyro.clear_param_store()`.\n4. For any shape or plate problem, trace the model and inspect\n   `trace.format_shapes()` before changing model structure.\n5. Do not use HMC\u002FNUTS directly on discrete latent variables. Enumerate,\n   marginalize, or use another inference strategy.\n6. Treat CUDA, Funsor, Horovod, Lightning, Graphviz, torchvision, pandas,\n   scanpy, and long example\u002Ftutorial dependencies as optional until the user's\n   active environment proves support.\n7. Prefer tiny synthetic tensors and this skill's bundled smoke scripts before\n   attempting long training, downloads, plotting, or GPU-specific runs.\n\n## What Not to Use This Skill For\n\n- Generic PyTorch training that does not use Pyro primitives or distributions.\n- PyMC, NumPyro, Bean Machine, Stan, or TensorFlow Probability code unless the\n  task is explicitly translating concepts to Pyro.\n- Full scientific reproduction of every Pyro tutorial\u002Fexample; use this skill\n  to implement or debug the package workflow, then request task-specific data,\n  runtime, and budget.\n- Maintainer release, benchmark, profiling, Docker, or documentation-build work\n  unless the user explicitly asks to edit the Pyro repository.\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\u002Fpyro",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 pyro",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill pyro",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill pyro","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpyro\u002FSKILL.md",[47,53,57,61,65],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fapi-cheatsheet.md","REFERENCE","参考文档",5587,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpyro\u002Freferences\u002Fapi-cheatsheet.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Frepo-provenance.md",2819,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpyro\u002Freferences\u002Frepo-provenance.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Frepo-routing-metadata.json",329,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpyro\u002Freferences\u002Frepo-routing-metadata.json",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Ftroubleshooting.md",6495,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpyro\u002Freferences\u002Ftroubleshooting.md",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Fcheck_pyro_environment.py","SCRIPT","脚本",5765,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpyro\u002Fscripts\u002Fcheck_pyro_environment.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",[],[]]