[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78WQ8HTX4R8CYM3VN7FT8PS":3,"skill-same:01M78WQ8HTX4R8CYM3VN7FT8PS":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},"01M78WQ8HTX4R8CYM3VN7FT8PS","module-and-trees",null,"Use Equinox modules, fields, PyTree filtering, and tree surgery correctly.","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\u002Fmodule-and-trees\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: module-and-trees\ndescription: \"Use Equinox modules, fields, PyTree filtering, and tree surgery correctly.\"\nmetadata:\n  disco-role: operating\ndisable-model-invocation: true\nlicense: Apache 2.0\n---\n\n# Module and Trees\n\nUse this sub-skill for Equinox’s core model-as-PyTree abstraction and the\nutilities that manipulate mixed PyTrees.\n\n## Use when\n\n- The user is defining or debugging an `eqx.Module` subclass.\n- A model has JAX arrays plus Python functions, strings, booleans, or other\n  non-array leaves.\n- The task mentions `eqx.field`, converters, static fields, `AbstractVar`,\n  `AbstractClassVar`, or `__check_init__`.\n- The task asks for model surgery with `tree_at`, trainable\u002Fstatic partitioning,\n  `tree_equal`, `tree_check`, `apply_updates`, or `Partial`.\n- A task needs to prepare a model PyTree for Optax, JAX transforms, or\n  serialization.\n\n## Route elsewhere\n\n- Use `..\u002Ffiltered-transformations\u002F` when the main issue is `filter_jit`,\n  `filter_grad`, `filter_vmap`, `filter_pmap`, AD, callbacks, or sharding.\n- Use `..\u002Fnn-and-state\u002F` for built-in `equinox.nn` layers, stateful modules,\n  `Shared`, and inference-mode behavior.\n- Use `..\u002Fdiagnostics-and-serialization\u002F` for saving\u002Floading leaves, runtime\n  errors, pretty printing, progress meters, or debug tools.\n- Use `..\u002Finternal-advanced\u002F` only for semi-public `equinox.internal` helpers.\n\n## Read first\n\n- [`references\u002Fmodule-and-trees.md`](references\u002Fmodule-and-trees.md) for module patterns, API decisions, and\n  model-surgery recipes.\n- [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) for common `eqx.Module`, static-field,\n  converter, and mixed-leaf failures.\n- [`..\u002F..\u002Freferences\u002Fapi-reference.md`](..\u002F..\u002Freferences\u002Fapi-reference.md) for a cross-skill symbol index.\n\n## Core workflow\n\n1. Identify the PyTree boundary. Decide which values are array leaves,\n   non-array dynamic objects, or static metadata.\n2. Define an `eqx.Module` subclass with annotated fields. Use a custom\n   `__init__` only when construction logic needs it; otherwise rely on dataclass\n   initialization.\n3. Mark metadata such as strings, booleans, shapes, or callables with\n   `eqx.field(static=True)` when it should not be a PyTree leaf.\n4. Use `eqx.field(converter=...)` for safe field normalization at initialization\n   time.\n5. Use `__check_init__` for invariant checks; do not mutate fields inside it.\n6. Split trainable and static leaves with `eqx.partition` or `eqx.filter`,\n   using predicates such as `eqx.is_inexact_array`, before optimizers or raw\n   JAX transforms.\n7. Use `eqx.tree_at` for out-of-place surgery such as replacing a final layer,\n   changing an initializer result, or toggling nested leaves.\n8. Validate structure with `eqx.tree_check` and compare expected outputs with\n   `eqx.tree_equal`.\n\n## Minimal validation\n\nFrom the generated skill root (set `EQUINOX_SKILL_ROOT` to its absolute path),\nrun the bundled smoke helper after installing Equinox:\n\n```bash\ncd \"$EQUINOX_SKILL_ROOT\" && python scripts\u002Fsmoke.py --mode module\n```\n\nThis checks module construction, static-field preservation, partition\u002Fcombine,\n`tree_at`, and `tree_check` using only the installed package and bundled runtime\nfiles.\n\n## Scope note\n\nThis sub-skill distills Equinox's public module, filter, tree-manipulation, and\ntraining-update behavior into the bundled references. Future agents should use\n`references\u002Fmodule-and-trees.md`, `references\u002Ftroubleshooting.md`, and\n`scripts\u002Fsmoke.py`; the source repository was construction evidence only, not a\nruntime dependency.\n\n## Key cautions\n\n- An Equinox module is a frozen dataclass and a PyTree. Treat object identity as\n  secondary to tree value and structure.\n- Plain `jax.jit` and `jax.grad` are valid only when their dynamic arguments are\n  all JAX-compatible leaves. Use filtered transforms for mixed modules.\n- Do not store bound methods on a module field; use a property or wrapper.\n- Do not mark trainable arrays static just to silence JAX errors; filter the\n  model instead.\n","# Module and Trees\n\nUse this sub-skill for Equinox’s core model-as-PyTree abstraction and the\nutilities that manipulate mixed PyTrees.\n\n## Use when\n\n- The user is defining or debugging an `eqx.Module` subclass.\n- A model has JAX arrays plus Python functions, strings, booleans, or other\n  non-array leaves.\n- The task mentions `eqx.field`, converters, static fields, `AbstractVar`,\n  `AbstractClassVar`, or `__check_init__`.\n- The task asks for model surgery with `tree_at`, trainable\u002Fstatic partitioning,\n  `tree_equal`, `tree_check`, `apply_updates`, or `Partial`.\n- A task needs to prepare a model PyTree for Optax, JAX transforms, or\n  serialization.\n\n## Route elsewhere\n\n- Use `..\u002Ffiltered-transformations\u002F` when the main issue is `filter_jit`,\n  `filter_grad`, `filter_vmap`, `filter_pmap`, AD, callbacks, or sharding.\n- Use `..\u002Fnn-and-state\u002F` for built-in `equinox.nn` layers, stateful modules,\n  `Shared`, and inference-mode behavior.\n- Use `..\u002Fdiagnostics-and-serialization\u002F` for saving\u002Floading leaves, runtime\n  errors, pretty printing, progress meters, or debug tools.\n- Use `..\u002Finternal-advanced\u002F` only for semi-public `equinox.internal` helpers.\n\n## Read first\n\n- [`references\u002Fmodule-and-trees.md`](references\u002Fmodule-and-trees.md) for module patterns, API decisions, and\n  model-surgery recipes.\n- [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) for common `eqx.Module`, static-field,\n  converter, and mixed-leaf failures.\n- [`..\u002F..\u002Freferences\u002Fapi-reference.md`](..\u002F..\u002Freferences\u002Fapi-reference.md) for a cross-skill symbol index.\n\n## Core workflow\n\n1. Identify the PyTree boundary. Decide which values are array leaves,\n   non-array dynamic objects, or static metadata.\n2. Define an `eqx.Module` subclass with annotated fields. Use a custom\n   `__init__` only when construction logic needs it; otherwise rely on dataclass\n   initialization.\n3. Mark metadata such as strings, booleans, shapes, or callables with\n   `eqx.field(static=True)` when it should not be a PyTree leaf.\n4. Use `eqx.field(converter=...)` for safe field normalization at initialization\n   time.\n5. Use `__check_init__` for invariant checks; do not mutate fields inside it.\n6. Split trainable and static leaves with `eqx.partition` or `eqx.filter`,\n   using predicates such as `eqx.is_inexact_array`, before optimizers or raw\n   JAX transforms.\n7. Use `eqx.tree_at` for out-of-place surgery such as replacing a final layer,\n   changing an initializer result, or toggling nested leaves.\n8. Validate structure with `eqx.tree_check` and compare expected outputs with\n   `eqx.tree_equal`.\n\n## Minimal validation\n\nFrom the generated skill root (set `EQUINOX_SKILL_ROOT` to its absolute path),\nrun the bundled smoke helper after installing Equinox:\n\n```bash\ncd \"$EQUINOX_SKILL_ROOT\" && python scripts\u002Fsmoke.py --mode module\n```\n\nThis checks module construction, static-field preservation, partition\u002Fcombine,\n`tree_at`, and `tree_check` using only the installed package and bundled runtime\nfiles.\n\n## Scope note\n\nThis sub-skill distills Equinox's public module, filter, tree-manipulation, and\ntraining-update behavior into the bundled references. Future agents should use\n`references\u002Fmodule-and-trees.md`, `references\u002Ftroubleshooting.md`, and\n`scripts\u002Fsmoke.py`; the source repository was construction evidence only, not a\nruntime dependency.\n\n## Key cautions\n\n- An Equinox module is a frozen dataclass and a PyTree. Treat object identity as\n  secondary to tree value and structure.\n- Plain `jax.jit` and `jax.grad` are valid only when their dynamic arguments are\n  all JAX-compatible leaves. Use filtered transforms for mixed modules.\n- Do not store bound methods on a module field; use a property or wrapper.\n- Do not mark trainable arrays static just to silence JAX errors; filter the\n  model instead.\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\u002Fmodule-and-trees",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 module-and-trees",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill module-and-trees",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill module-and-trees","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fequinox\u002Fsub-skills\u002Fmodule-and-trees\u002FSKILL.md",[47,53],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fmodule-and-trees.md","REFERENCE","参考文档",6251,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fequinox\u002Fsub-skills\u002Fmodule-and-trees\u002Freferences\u002Fmodule-and-trees.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Ftroubleshooting.md",3991,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fequinox\u002Fsub-skills\u002Fmodule-and-trees\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",[],[]]