[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M797Q33S3F2DFWP0F5GTRFRF":3,"skill-same:01M797Q33S3F2DFWP0F5GTRFRF":86},{"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},"01M797Q33S3F2DFWP0F5GTRFRF","zhusuan",null,"Use ZhuSuan for Bayesian networks, variational inference, HMC\u002FSG-MCMC sampling, and importance-sampling workflows on TensorFlow 1.x.","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\u002Fzhusuan\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: zhusuan\ndescription: \"Use ZhuSuan for Bayesian networks, variational inference,\n  HMC\u002FSG-MCMC sampling, and importance-sampling workflows on TensorFlow 1.x.\"\nmetadata:\n  disco-role: operating\ndisable-model-invocation: true\nlicense: MIT\n---\n\n# ZhuSuan\n\nZhuSuan is a TensorFlow 1.x probabilistic-programming library for Bayesian deep\nlearning. Use this skill when the user asks about `import zhusuan as zs`,\nBayesian networks, latent-variable models, variational objectives, posterior\nsampling, or the repo's example workflows.\n\n## Quick start\n\n1. Read `references\u002Foverview.md` for the module map and installation note.\n2. Read `references\u002Fworkflows.md` for the example-family map and dataset notes.\n3. Read `references\u002Fapi-reference.md` when you need exact signatures.\n4. Read `references\u002Ftroubleshooting.md` when install, TF1, dtype, or shape\n   issues show up.\n5. Run `scripts\u002Fcore_smoke.py` after installing the package if you want a fast\n   import-and-objective sanity check.\n\n## Route to a sub-skill\n\n- `sub-skills\u002Fmodeling-primitives\u002FSKILL.md` for distributions, BayesianNet,\n  MetaBayesianNet, observations, deterministic nodes, and node inspection.\n- `sub-skills\u002Fvariational-inference\u002FSKILL.md` for ELBO, IWAE, KLPQ,\n  importance-sampling likelihoods, normalizing flows, and VAE\u002FBNN\u002FSVGP-style\n  training.\n- `sub-skills\u002Fmcmc-and-sampling\u002FSKILL.md` for HMC, SGLD, PSGLD, SGHMC, SGNHT,\n  AIS, and chain diagnostics.\n\n## What this root skill is for\n\n- Give the fastest route to the right workflow and reference.\n- Provide the package-level install, import, and troubleshooting entry point.\n- Keep the skill usable after the original checkout disappears.\n\n## What this root skill is not for\n\n- It is not a full API manual; read the relevant reference file instead.\n- It is not a training script collection; the example families are summarized in\n  `references\u002Fworkflows.md` and the sub-skills.\n- It is not a replacement for the sub-skills; those carry the detailed workflow\n  guidance.\n\n## Practical reminders\n\n- ZhuSuan's core API is graph-based and TF1-style. Sessions, placeholders, and\n  variable scopes still matter.\n- The verified inspection environment used TensorFlow 1.15.5 with SciPy and\n  mock on Python 3.6.\n- The example families often need external data or optional image helpers, so\n  keep them as references unless the user explicitly wants a full run.\n","# ZhuSuan\n\nZhuSuan is a TensorFlow 1.x probabilistic-programming library for Bayesian deep\nlearning. Use this skill when the user asks about `import zhusuan as zs`,\nBayesian networks, latent-variable models, variational objectives, posterior\nsampling, or the repo's example workflows.\n\n## Quick start\n\n1. Read `references\u002Foverview.md` for the module map and installation note.\n2. Read `references\u002Fworkflows.md` for the example-family map and dataset notes.\n3. Read `references\u002Fapi-reference.md` when you need exact signatures.\n4. Read `references\u002Ftroubleshooting.md` when install, TF1, dtype, or shape\n   issues show up.\n5. Run `scripts\u002Fcore_smoke.py` after installing the package if you want a fast\n   import-and-objective sanity check.\n\n## Route to a sub-skill\n\n- `sub-skills\u002Fmodeling-primitives\u002FSKILL.md` for distributions, BayesianNet,\n  MetaBayesianNet, observations, deterministic nodes, and node inspection.\n- `sub-skills\u002Fvariational-inference\u002FSKILL.md` for ELBO, IWAE, KLPQ,\n  importance-sampling likelihoods, normalizing flows, and VAE\u002FBNN\u002FSVGP-style\n  training.\n- `sub-skills\u002Fmcmc-and-sampling\u002FSKILL.md` for HMC, SGLD, PSGLD, SGHMC, SGNHT,\n  AIS, and chain diagnostics.\n\n## What this root skill is for\n\n- Give the fastest route to the right workflow and reference.\n- Provide the package-level install, import, and troubleshooting entry point.\n- Keep the skill usable after the original checkout disappears.\n\n## What this root skill is not for\n\n- It is not a full API manual; read the relevant reference file instead.\n- It is not a training script collection; the example families are summarized in\n  `references\u002Fworkflows.md` and the sub-skills.\n- It is not a replacement for the sub-skills; those carry the detailed workflow\n  guidance.\n\n## Practical reminders\n\n- ZhuSuan's core API is graph-based and TF1-style. Sessions, placeholders, and\n  variable scopes still matter.\n- The verified inspection environment used TensorFlow 1.15.5 with SciPy and\n  mock on Python 3.6.\n- The example families often need external data or optional image helpers, so\n  keep them as references unless the user explicitly wants a full run.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fzhusuan",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 zhusuan",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill zhusuan",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill zhusuan","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fzhusuan\u002FSKILL.md",[46,52,56,60,64,68,72,78,82],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fapi-reference.md","REFERENCE","参考文档",3075,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fzhusuan\u002Freferences\u002Fapi-reference.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Foverview.md",1429,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fzhusuan\u002Freferences\u002Foverview.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Frepo-provenance.md",734,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fzhusuan\u002Freferences\u002Frepo-provenance.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Frepo-routing-metadata.json",432,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fzhusuan\u002Freferences\u002Frepo-routing-metadata.json",{"path":65,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Ftroubleshooting.md",2065,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fzhusuan\u002Freferences\u002Ftroubleshooting.md",{"path":69,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":70,"sourceHtmlUrl":71},"references\u002Fworkflows.md",2524,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fzhusuan\u002Freferences\u002Fworkflows.md",{"path":73,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":76,"sourceHtmlUrl":77},"scripts\u002Fcore_smoke.py","SCRIPT","脚本",1265,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fzhusuan\u002Fscripts\u002Fcore_smoke.py",{"path":79,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":80,"sourceHtmlUrl":81},"scripts\u002Fdata_helpers.py",1272,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fzhusuan\u002Fscripts\u002Fdata_helpers.py",{"path":83,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":84,"sourceHtmlUrl":85},"scripts\u002Fimage_grid.py",2059,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fzhusuan\u002Fscripts\u002Fimage_grid.py",[87,95,102,109,116,123],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":91,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"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":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":91,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"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":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":91,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"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":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":91,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":115,"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":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":91,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":122,"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":124,"name":125,"nameZh":6,"description":126,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":91,"licenseFileUrl":6,"sourceHtmlUrl":127,"categories":128,"keywords":129,"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",[],[]]