[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78WQB8Y12WPFS3FSSXBGE22":3,"skill-same:01M78WQB8Y12WPFS3FSSXBGE22":57},{"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},"01M78WQB8Y12WPFS3FSSXBGE22","nn-and-state",null,"Use Equinox neural-network layers, Sequential models, stateful layers, and inference mode.","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\u002Fequinox\u002Fsub-skills\u002Fnn-and-state\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: nn-and-state\ndescription: \"Use Equinox neural-network layers, Sequential models, stateful\n  layers, and inference mode.\"\nmetadata:\n  disco-role: operating\ndisable-model-invocation: true\nlicense: Apache 2.0\n---\n\n# Neural Networks and State\n\nUse this sub-skill for `equinox.nn` layers and stateful model workflows.\n\n## Use when\n\n- The user asks how to build a model with `eqx.nn.Linear`, `MLP`, `Sequential`,\n  `Conv*`, `MultiheadAttention`, `Embedding`, pooling, RNN cells, or\n  normalization layers.\n- A task needs `Dropout`, `BatchNorm`, `SpectralNorm`, `WeightNorm`,\n  `inference_mode`, or explicit PRNG key handling.\n- The user needs `eqx.nn.State`, `StateIndex`, `make_with_state`,\n  `delete_init_state`, or a custom stateful layer.\n- A model needs tied parameters with `eqx.nn.Shared`.\n- A training loop combines Equinox layers with `filter_grad`, Optax, and\n  `apply_updates`.\n\n## Route elsewhere\n\n- Use `..\u002Fmodule-and-trees\u002F` for raw `eqx.Module` field design, tree surgery,\n  filtering, and optimizer parameter selection.\n- Use `..\u002Ffiltered-transformations\u002F` when the dominant issue is JIT, AD, vmap,\n  pmap, callbacks, or sharding.\n- Use `..\u002Fdiagnostics-and-serialization\u002F` for saving\u002Floading, runtime errors,\n  debug tracing, or pretty printing.\n- Use `..\u002Finternal-advanced\u002F` for semi-public internal loops and primitives.\n\n## Read first\n\n- [`references\u002Fnn-and-state.md`](references\u002Fnn-and-state.md) for layer families, stateful workflows,\n  single-example calling rules, and training-step patterns.\n- [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) for `BatchNorm`, stale `State`, dropout,\n  `Sequential`, and shared-weight failures.\n- [`..\u002F..\u002Freferences\u002Fapi-reference.md`](..\u002F..\u002Freferences\u002Fapi-reference.md) for cross-skill signatures.\n\n## Core workflow\n\n1. Choose the layer family and confirm whether it is stateless, stochastic, or\n   stateful.\n2. Remember that most `equinox.nn` layers consume one example. Use `jax.vmap` or\n   `eqx.filter_vmap` around layer calls for batches.\n3. Use `Sequential` for ordered layers. Wrap activation functions with\n   `eqx.nn.Lambda` when they live inside `Sequential`.\n4. Pass PRNG keys to constructors and to stochastic calls such as dropout.\n5. For stateful layers, construct with `eqx.nn.make_with_state(ModelClass)` and\n   thread the returned `State` through every call.\n6. Toggle inference behavior with `eqx.nn.inference_mode(model, value=True)`.\n7. Use `eqx.nn.Shared` for intentional tied weights instead of relying on object\n   identity in a PyTree.\n8. For training, combine this sub-skill with `filtered-transformations` and\n   `module-and-trees`.\n\n## Minimal validation\n\nFrom the generated skill root (set `EQUINOX_SKILL_ROOT` to its absolute path),\nrun:\n\n```bash\ncd \"$EQUINOX_SKILL_ROOT\" && python scripts\u002Fsmoke.py --mode nn\n```\n\nThis validates tiny `MLP`, `Sequential`, custom state, and `Shared` examples.\nIt does not run expensive training or download datasets.\n\n## Scope note\n\nThis sub-skill distills Equinox's built-in layer, state, and sharing workflows\ninto the bundled references and smoke helper. The source repository's tests,\ndocs, and notebooks were construction evidence only, not runtime dependencies.\n\n## Key cautions\n\n- `BatchNorm` must run inside a `vmap` or `pmap` with a matching `axis_name` for\n  training statistics.\n- `State.set` and `State.update` return a new state and invalidate the old one.\n- `MLP(..., scan=True)` changes the internal representation for compile-time\n  reasons; do not call the scanned hidden layer stack directly.\n- `Shared` requires matching source\u002Fdestination structure, shapes, and dtypes.\n- Stochastic layers use explicit keys; do not hide key generation inside a JITed\n  training step without a reproducible split plan.\n","# Neural Networks and State\n\nUse this sub-skill for `equinox.nn` layers and stateful model workflows.\n\n## Use when\n\n- The user asks how to build a model with `eqx.nn.Linear`, `MLP`, `Sequential`,\n  `Conv*`, `MultiheadAttention`, `Embedding`, pooling, RNN cells, or\n  normalization layers.\n- A task needs `Dropout`, `BatchNorm`, `SpectralNorm`, `WeightNorm`,\n  `inference_mode`, or explicit PRNG key handling.\n- The user needs `eqx.nn.State`, `StateIndex`, `make_with_state`,\n  `delete_init_state`, or a custom stateful layer.\n- A model needs tied parameters with `eqx.nn.Shared`.\n- A training loop combines Equinox layers with `filter_grad`, Optax, and\n  `apply_updates`.\n\n## Route elsewhere\n\n- Use `..\u002Fmodule-and-trees\u002F` for raw `eqx.Module` field design, tree surgery,\n  filtering, and optimizer parameter selection.\n- Use `..\u002Ffiltered-transformations\u002F` when the dominant issue is JIT, AD, vmap,\n  pmap, callbacks, or sharding.\n- Use `..\u002Fdiagnostics-and-serialization\u002F` for saving\u002Floading, runtime errors,\n  debug tracing, or pretty printing.\n- Use `..\u002Finternal-advanced\u002F` for semi-public internal loops and primitives.\n\n## Read first\n\n- [`references\u002Fnn-and-state.md`](references\u002Fnn-and-state.md) for layer families, stateful workflows,\n  single-example calling rules, and training-step patterns.\n- [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) for `BatchNorm`, stale `State`, dropout,\n  `Sequential`, and shared-weight failures.\n- [`..\u002F..\u002Freferences\u002Fapi-reference.md`](..\u002F..\u002Freferences\u002Fapi-reference.md) for cross-skill signatures.\n\n## Core workflow\n\n1. Choose the layer family and confirm whether it is stateless, stochastic, or\n   stateful.\n2. Remember that most `equinox.nn` layers consume one example. Use `jax.vmap` or\n   `eqx.filter_vmap` around layer calls for batches.\n3. Use `Sequential` for ordered layers. Wrap activation functions with\n   `eqx.nn.Lambda` when they live inside `Sequential`.\n4. Pass PRNG keys to constructors and to stochastic calls such as dropout.\n5. For stateful layers, construct with `eqx.nn.make_with_state(ModelClass)` and\n   thread the returned `State` through every call.\n6. Toggle inference behavior with `eqx.nn.inference_mode(model, value=True)`.\n7. Use `eqx.nn.Shared` for intentional tied weights instead of relying on object\n   identity in a PyTree.\n8. For training, combine this sub-skill with `filtered-transformations` and\n   `module-and-trees`.\n\n## Minimal validation\n\nFrom the generated skill root (set `EQUINOX_SKILL_ROOT` to its absolute path),\nrun:\n\n```bash\ncd \"$EQUINOX_SKILL_ROOT\" && python scripts\u002Fsmoke.py --mode nn\n```\n\nThis validates tiny `MLP`, `Sequential`, custom state, and `Shared` examples.\nIt does not run expensive training or download datasets.\n\n## Scope note\n\nThis sub-skill distills Equinox's built-in layer, state, and sharing workflows\ninto the bundled references and smoke helper. The source repository's tests,\ndocs, and notebooks were construction evidence only, not runtime dependencies.\n\n## Key cautions\n\n- `BatchNorm` must run inside a `vmap` or `pmap` with a matching `axis_name` for\n  training statistics.\n- `State.set` and `State.update` return a new state and invalidate the old one.\n- `MLP(..., scan=True)` changes the internal representation for compile-time\n  reasons; do not call the scanned hidden layer stack directly.\n- `Shared` requires matching source\u002Fdestination structure, shapes, and dtypes.\n- Stochastic layers use explicit keys; do not hide key generation inside a JITed\n  training step without a reproducible split plan.\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\u002Fequinox\u002Fsub-skills\u002Fnn-and-state",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 nn-and-state",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill nn-and-state",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill nn-and-state","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fequinox\u002Fsub-skills\u002Fnn-and-state\u002FSKILL.md",[47,53],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fnn-and-state.md","REFERENCE","参考文档",5535,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fequinox\u002Fsub-skills\u002Fnn-and-state\u002Freferences\u002Fnn-and-state.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Ftroubleshooting.md",3598,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fequinox\u002Fsub-skills\u002Fnn-and-state\u002Freferences\u002Ftroubleshooting.md",[58,65,72,79,86,93],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"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":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"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":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},"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":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},"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":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},"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":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},"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",[],[]]