[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78XQ5RNBAASGAPP3G6PWHXP":3,"skill-same:01M78XQ5RNBAASGAPP3G6PWHXP":75},{"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},"01M78XQ5RNBAASGAPP3G6PWHXP","graph-models",null,"Build Graph Nets blocks and high-level Sonnet model architectures.","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\u002Fgraph-nets\u002Fsub-skills\u002Fgraph-models\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: graph-models\ndescription: \"Build Graph Nets blocks and high-level Sonnet model architectures.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Graph Models\n\nUse this sub-skill when the task is to assemble, adapt, or debug Graph Nets neural-network modules: low-level broadcasters\u002Faggregators, `EdgeBlock` \u002F `NodeBlock` \u002F `GlobalBlock`, high-level `graph_nets.modules` architectures, or Sonnet model factories for Graph Nets demos.\n\n## Route here for\n\n- Choosing and wiring `graph_nets.blocks` broadcasters, aggregators, reducers, or update blocks.\n- Building `GraphIndependent`, `GraphNetwork`, `InteractionNetwork`, `RelationNetwork`, `DeepSets`, `CommNet`, or `SelfAttention` modules.\n- Writing Sonnet 1 or Sonnet 2 `*_model_fn` factories for edge, node, global, encoder, core, decoder, or output transforms.\n- Adapting the bundled demo architectures in [`scripts\u002Fdemo_models_tf1.py`](scripts\u002Fdemo_models_tf1.py) or [`scripts\u002Fdemo_models_tf2.py`](scripts\u002Fdemo_models_tf2.py).\n- Running a tiny installed-package model smoke with [`scripts\u002Fgraph_model_smoke.py`](scripts\u002Fgraph_model_smoke.py).\n\n## Route elsewhere\n\n- Raw `GraphsTuple` construction, dictionary batching, and NetworkX conversion belong in [`..\u002Fgraph-data\u002FSKILL.md`](..\u002Fgraph-data\u002FSKILL.md).\n- TensorFlow utilities, placeholders, padding, masks, `utils_tf.concat`, `tf.function` signatures, and session\u002Ffeed details belong in [`..\u002Ftensorflow-ops\u002FSKILL.md`](..\u002Ftensorflow-ops\u002FSKILL.md).\n- Full training-loop or notebook reproduction work should use the root Graph Nets recipe guidance first, then return here only for the model\u002Fmodule layer.\n\n## Required reading for model work\n\n1. [`references\u002Fapi-reference.md`](references\u002Fapi-reference.md) for constructor contracts, field requirements, reducer defaults, and Sonnet version differences.\n2. [`references\u002Fworkflows.md`](references\u002Fworkflows.md) for practical recipes: independent encoders\u002Fdecoders, generic message passing, relation\u002Fset\u002Fcommunication modules, self-attention, and encode-process-decode.\n3. [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) when a graph field is `None`, senders\u002Freceivers are absent, reducers are missing, concatenation shapes fail, or TF\u002FSonnet major versions mismatch.\n\n## Operating checklist\n\n- Confirm the installed stack before choosing code style: Sonnet 1 uses `snt.AbstractModule` and TF1 sessions\u002Fplaceholders; Sonnet 2 uses `snt.Module`, eager tensors, and optional `tf.function` wrapping.\n- Decide which graph fields the module is allowed to read. Match every `use_*` flag to non-`None` input fields and to required reducers.\n- Keep model factories as zero-argument callables that return a Sonnet module or callable. Do not instantiate a fresh submodule inside every call of an already-built model.\n- Validate all concatenated features share the same rank and all non-last axes after broadcasting\u002Faggregation; only the last feature axis should differ.\n- Preserve sub-skill boundaries: fix invalid graph data before model assembly and delegate padding\u002Fsession mechanics to the TensorFlow ops sub-skill.\n","# Graph Models\n\nUse this sub-skill when the task is to assemble, adapt, or debug Graph Nets neural-network modules: low-level broadcasters\u002Faggregators, `EdgeBlock` \u002F `NodeBlock` \u002F `GlobalBlock`, high-level `graph_nets.modules` architectures, or Sonnet model factories for Graph Nets demos.\n\n## Route here for\n\n- Choosing and wiring `graph_nets.blocks` broadcasters, aggregators, reducers, or update blocks.\n- Building `GraphIndependent`, `GraphNetwork`, `InteractionNetwork`, `RelationNetwork`, `DeepSets`, `CommNet`, or `SelfAttention` modules.\n- Writing Sonnet 1 or Sonnet 2 `*_model_fn` factories for edge, node, global, encoder, core, decoder, or output transforms.\n- Adapting the bundled demo architectures in [`scripts\u002Fdemo_models_tf1.py`](scripts\u002Fdemo_models_tf1.py) or [`scripts\u002Fdemo_models_tf2.py`](scripts\u002Fdemo_models_tf2.py).\n- Running a tiny installed-package model smoke with [`scripts\u002Fgraph_model_smoke.py`](scripts\u002Fgraph_model_smoke.py).\n\n## Route elsewhere\n\n- Raw `GraphsTuple` construction, dictionary batching, and NetworkX conversion belong in [`..\u002Fgraph-data\u002FSKILL.md`](..\u002Fgraph-data\u002FSKILL.md).\n- TensorFlow utilities, placeholders, padding, masks, `utils_tf.concat`, `tf.function` signatures, and session\u002Ffeed details belong in [`..\u002Ftensorflow-ops\u002FSKILL.md`](..\u002Ftensorflow-ops\u002FSKILL.md).\n- Full training-loop or notebook reproduction work should use the root Graph Nets recipe guidance first, then return here only for the model\u002Fmodule layer.\n\n## Required reading for model work\n\n1. [`references\u002Fapi-reference.md`](references\u002Fapi-reference.md) for constructor contracts, field requirements, reducer defaults, and Sonnet version differences.\n2. [`references\u002Fworkflows.md`](references\u002Fworkflows.md) for practical recipes: independent encoders\u002Fdecoders, generic message passing, relation\u002Fset\u002Fcommunication modules, self-attention, and encode-process-decode.\n3. [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) when a graph field is `None`, senders\u002Freceivers are absent, reducers are missing, concatenation shapes fail, or TF\u002FSonnet major versions mismatch.\n\n## Operating checklist\n\n- Confirm the installed stack before choosing code style: Sonnet 1 uses `snt.AbstractModule` and TF1 sessions\u002Fplaceholders; Sonnet 2 uses `snt.Module`, eager tensors, and optional `tf.function` wrapping.\n- Decide which graph fields the module is allowed to read. Match every `use_*` flag to non-`None` input fields and to required reducers.\n- Keep model factories as zero-argument callables that return a Sonnet module or callable. Do not instantiate a fresh submodule inside every call of an already-built model.\n- Validate all concatenated features share the same rank and all non-last axes after broadcasting\u002Faggregation; only the last feature axis should differ.\n- Preserve sub-skill boundaries: fix invalid graph data before model assembly and delegate padding\u002Fsession mechanics to the TensorFlow ops sub-skill.\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\u002Fgraph-nets\u002Fsub-skills\u002Fgraph-models",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 graph-models",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill graph-models",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill graph-models","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgraph-nets\u002Fsub-skills\u002Fgraph-models\u002FSKILL.md",[47,53,57,61,67,71],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fapi-reference.md","REFERENCE","参考文档",14738,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgraph-nets\u002Fsub-skills\u002Fgraph-models\u002Freferences\u002Fapi-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Ftroubleshooting.md",9976,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgraph-nets\u002Fsub-skills\u002Fgraph-models\u002Freferences\u002Ftroubleshooting.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fworkflows.md",11932,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgraph-nets\u002Fsub-skills\u002Fgraph-models\u002Freferences\u002Fworkflows.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fdemo_models_tf1.py","SCRIPT","脚本",7293,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgraph-nets\u002Fsub-skills\u002Fgraph-models\u002Fscripts\u002Fdemo_models_tf1.py",{"path":68,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Fdemo_models_tf2.py",6756,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgraph-nets\u002Fsub-skills\u002Fgraph-models\u002Fscripts\u002Fdemo_models_tf2.py",{"path":72,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":73,"sourceHtmlUrl":74},"scripts\u002Fgraph_model_smoke.py",6322,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgraph-nets\u002Fsub-skills\u002Fgraph-models\u002Fscripts\u002Fgraph_model_smoke.py",[76,83,90,97,104,111],{"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},"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":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},"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":14,"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":14,"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":14,"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":14,"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",[],[]]