[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M793FKTYTJS95P9W8R1A3V8Q":3,"skill-same:01M793FKTYTJS95P9W8R1A3V8Q":61},{"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},"01M793FKTYTJS95P9W8R1A3V8Q","distributions-and-shapes",null,"Choose Pyro distributions and debug batch, event, plate, support, and transform shapes.","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\u002Fsub-skills\u002Fdistributions-and-shapes\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: distributions-and-shapes\ndescription: \"Choose Pyro distributions and debug batch, event, plate, support,\n  and transform shapes.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Distributions And Shapes\n\nUse this sub-skill when the user needs to choose a `pyro.distributions`\ndistribution, reason about `sample_shape`, `batch_shape`, `event_shape`, or\n`pyro.plate` dimensions, add constraints\u002Ftransforms, or debug `log_prob`, support,\nvalidation, NaN\u002FInf, HMM, stable, zero-inflated, mixture, matching, or CUDA shape\nissues.\n\n## Route First\n\n- For distribution selection, Pyro-specific distribution families, constructor\n  signatures, constraints\u002Ftransforms, LKJ, HMM, matching, stable, mixture, and\n  optional SciPy caveats, read\n  [references\u002Fdistribution-catalog.md](references\u002Fdistribution-catalog.md).\n- For shape algebra, `plate` dimension placement, `.to_event()`\u002F`Independent`,\n  observation shape checks, trace shape diagnostics, and HMM\u002Fzero-inflated shape\n  recipes, read [references\u002Fshapes-and-plates.md](references\u002Fshapes-and-plates.md).\n- For concrete recovery steps after errors such as invalid support, argument\n  constraint violations, invalid `log_prob` shape, NaNs\u002FInfs, CUDA device\n  mismatches, SciPy-dependent helper failures, and HMM duration\u002Fbroadcast\n  mistakes, read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md).\n\n## Best-Fit Tasks\n\nUse this sub-skill for requests like:\n\n- \"which Pyro distribution should I use for zero-inflated counts, correlations,\n  an HMM, a stable process, a matching, or a mixture?\";\n- \"why does `log_prob()` have the wrong shape under `plate`?\";\n- \"should this tensor dimension be a batch dim, event dim, or plate dim?\";\n- \"fix `ValueError: invalid log_prob shape`, `expected value argument...`,\n  `components event_shape disagree`, or an HMM `duration` mismatch\";\n- \"use `constraints`, `transform_to`, `biject_to`, or `TransformedDistribution`\n  safely\";\n- \"make the same distribution code work on CPU and optional CUDA\".\n\n## Boundaries And Reroutes\n\n- Basic `pyro.sample`, `pyro.param`, `pyro.plate` introductions, parameter-store\n  lifecycle, `PyroModule`, and observation basics: route to\n  `..\u002Fmodeling-basics\u002F`.\n- SVI, ELBO choice, autoguides, optimizers, and training-loop decisions: route to\n  `..\u002Fsvi-and-autoguides\u002F` after this sub-skill has resolved distribution and\n  shape contracts.\n- MCMC\u002FNUTS\u002FHMC, initialization strategies, posterior prediction, and predictive\n  sample shapes: route to `..\u002Fmcmc-and-prediction\u002F` after this sub-skill has\n  resolved support and transform constraints.\n- Poutine handler composition, enumeration, `config_enumerate`, `infer_discrete`,\n  `TraceEnum_ELBO`, and enum dimension allocation: route to\n  `..\u002Feffect-handlers-and-enumeration\u002F`.\n- Domain-specific contributed workflows and optional integrations such as funsor,\n  Horovod, Lightning, Graphviz, torchvision, pandas, scanpy, or zuko: route to\n  `..\u002Fcontrib-and-domain-workflows\u002F` and treat them as optional unless the active\n  environment proves support.\n\n## High-Value Checks Before Answering\n\n1. Start with the support and event type: real scalar, positive scalar, simplex,\n   vector, matrix\u002Fcorrelation, integer count, category, sequence\u002FHMM, matching,\n   or transformed variable.\n2. Inspect `d.batch_shape`, `d.event_shape`, `d.shape(sample_shape)`, and\n   `d.log_prob(value).shape` before proposing a `plate` or `.to_event()` fix.\n3. Keep Pyro validation enabled while debugging; pass `validate_args=True` for a\n   single suspect distribution if global validation is uncertain.\n4. Every non-event batch dimension in a Pyro sample site must be declared by an\n   enclosing `pyro.plate` or deliberately reinterpreted with `.to_event()`.\n5. For observed data, require `obs` to broadcast to\n   `fn.batch_shape + fn.event_shape`; `obs_mask` broadcasts only to\n   `fn.batch_shape`.\n6. Treat CUDA, SciPy-backed helpers, and flow\u002Fdomain extras as optional; do not\n   claim they are available merely because CPU Pyro imports.\n","# Distributions And Shapes\n\nUse this sub-skill when the user needs to choose a `pyro.distributions`\ndistribution, reason about `sample_shape`, `batch_shape`, `event_shape`, or\n`pyro.plate` dimensions, add constraints\u002Ftransforms, or debug `log_prob`, support,\nvalidation, NaN\u002FInf, HMM, stable, zero-inflated, mixture, matching, or CUDA shape\nissues.\n\n## Route First\n\n- For distribution selection, Pyro-specific distribution families, constructor\n  signatures, constraints\u002Ftransforms, LKJ, HMM, matching, stable, mixture, and\n  optional SciPy caveats, read\n  [references\u002Fdistribution-catalog.md](references\u002Fdistribution-catalog.md).\n- For shape algebra, `plate` dimension placement, `.to_event()`\u002F`Independent`,\n  observation shape checks, trace shape diagnostics, and HMM\u002Fzero-inflated shape\n  recipes, read [references\u002Fshapes-and-plates.md](references\u002Fshapes-and-plates.md).\n- For concrete recovery steps after errors such as invalid support, argument\n  constraint violations, invalid `log_prob` shape, NaNs\u002FInfs, CUDA device\n  mismatches, SciPy-dependent helper failures, and HMM duration\u002Fbroadcast\n  mistakes, read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md).\n\n## Best-Fit Tasks\n\nUse this sub-skill for requests like:\n\n- \"which Pyro distribution should I use for zero-inflated counts, correlations,\n  an HMM, a stable process, a matching, or a mixture?\";\n- \"why does `log_prob()` have the wrong shape under `plate`?\";\n- \"should this tensor dimension be a batch dim, event dim, or plate dim?\";\n- \"fix `ValueError: invalid log_prob shape`, `expected value argument...`,\n  `components event_shape disagree`, or an HMM `duration` mismatch\";\n- \"use `constraints`, `transform_to`, `biject_to`, or `TransformedDistribution`\n  safely\";\n- \"make the same distribution code work on CPU and optional CUDA\".\n\n## Boundaries And Reroutes\n\n- Basic `pyro.sample`, `pyro.param`, `pyro.plate` introductions, parameter-store\n  lifecycle, `PyroModule`, and observation basics: route to\n  `..\u002Fmodeling-basics\u002F`.\n- SVI, ELBO choice, autoguides, optimizers, and training-loop decisions: route to\n  `..\u002Fsvi-and-autoguides\u002F` after this sub-skill has resolved distribution and\n  shape contracts.\n- MCMC\u002FNUTS\u002FHMC, initialization strategies, posterior prediction, and predictive\n  sample shapes: route to `..\u002Fmcmc-and-prediction\u002F` after this sub-skill has\n  resolved support and transform constraints.\n- Poutine handler composition, enumeration, `config_enumerate`, `infer_discrete`,\n  `TraceEnum_ELBO`, and enum dimension allocation: route to\n  `..\u002Feffect-handlers-and-enumeration\u002F`.\n- Domain-specific contributed workflows and optional integrations such as funsor,\n  Horovod, Lightning, Graphviz, torchvision, pandas, scanpy, or zuko: route to\n  `..\u002Fcontrib-and-domain-workflows\u002F` and treat them as optional unless the active\n  environment proves support.\n\n## High-Value Checks Before Answering\n\n1. Start with the support and event type: real scalar, positive scalar, simplex,\n   vector, matrix\u002Fcorrelation, integer count, category, sequence\u002FHMM, matching,\n   or transformed variable.\n2. Inspect `d.batch_shape`, `d.event_shape`, `d.shape(sample_shape)`, and\n   `d.log_prob(value).shape` before proposing a `plate` or `.to_event()` fix.\n3. Keep Pyro validation enabled while debugging; pass `validate_args=True` for a\n   single suspect distribution if global validation is uncertain.\n4. Every non-event batch dimension in a Pyro sample site must be declared by an\n   enclosing `pyro.plate` or deliberately reinterpreted with `.to_event()`.\n5. For observed data, require `obs` to broadcast to\n   `fn.batch_shape + fn.event_shape`; `obs_mask` broadcasts only to\n   `fn.batch_shape`.\n6. Treat CUDA, SciPy-backed helpers, and flow\u002Fdomain extras as optional; do not\n   claim they are available merely because CPU Pyro imports.\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\u002Fsub-skills\u002Fdistributions-and-shapes",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 distributions-and-shapes",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill distributions-and-shapes",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill distributions-and-shapes","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpyro\u002Fsub-skills\u002Fdistributions-and-shapes\u002FSKILL.md",[47,53,57],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fdistribution-catalog.md","REFERENCE","参考文档",14080,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpyro\u002Fsub-skills\u002Fdistributions-and-shapes\u002Freferences\u002Fdistribution-catalog.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fshapes-and-plates.md",12197,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpyro\u002Fsub-skills\u002Fdistributions-and-shapes\u002Freferences\u002Fshapes-and-plates.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",18026,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpyro\u002Fsub-skills\u002Fdistributions-and-shapes\u002Freferences\u002Ftroubleshooting.md",[62,69,76,83,90,97],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"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":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"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":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"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":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"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":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"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":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"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",[],[]]