[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78XQ2T4BXP4F1AVCB4CXGAF":3,"skill-same:01M78XQ2T4BXP4F1AVCB4CXGAF":67},{"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},"01M78XQ2T4BXP4F1AVCB4CXGAF","graph-data",null,"Create, validate, batch, slice, and convert Graph Nets graph data with GraphsTuple, data dictionaries, NumPy arrays, and NetworkX graphs.","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-data\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: graph-data\ndescription: \"Create, validate, batch, slice, and convert Graph Nets graph data\n  with GraphsTuple, data dictionaries, NumPy arrays, and NetworkX graphs.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Graph Data\n\nUse this sub-skill when a task needs to build or inspect Graph Nets data before it reaches TensorFlow or Sonnet modules. It covers `graphs.GraphsTuple`, per-graph data dictionaries, NumPy arrays, NetworkX conversion, batching, unbatching, and slicing.\n\n## Read first\n\n- [Data formats](references\u002Fdata-formats.md): field semantics, valid `None` combinations, batch offsets, data dictionary rules, and NetworkX feature conventions.\n- [API reference](references\u002Fapi-reference.md): exact NumPy conversion and slicing functions, expected inputs\u002Foutputs, and common preflight checks.\n- [Troubleshooting](references\u002Ftroubleshooting.md): fast diagnosis for key-set, endpoint, feature, and NetworkX compatibility failures.\n- [Smoke script](scripts\u002Fgraph_data_smoke.py): deterministic round-trip check that prints JSON and can be run from any working directory.\n\n## Typical workflows\n\n1. **Create a `GraphsTuple` directly** when arrays are already in batched form. Provide all seven fields: `nodes`, `edges`, `receivers`, `senders`, `globals`, `n_node`, and `n_edge`; keep `n_node` and `n_edge` non-`None`.\n2. **Create from per-graph data dictionaries** when each sample is easier to describe independently. Use `utils_np.data_dicts_to_graphs_tuple`, and make every dictionary have the same non-`None` field set.\n3. **Create from NetworkX** when graph topology is naturally object-based. Use `utils_np.networkx_to_data_dict` for one graph or `utils_np.networkxs_to_graphs_tuple` for a batch; enforce ordered integer node keys and the `\"features\"` attribute convention.\n4. **Round-trip or inspect a batch** with `utils_np.graphs_tuple_to_data_dicts`, `utils_np.graphs_tuple_to_networkxs`, or `utils_np.get_graph`.\n5. **Use `GraphsTuple.replace` or `GraphsTuple.map`** for structural-preserving field updates; invalid `None` combinations still raise immediately.\n\n## Boundary routing\n\n- TensorFlow placeholders, tensor batching, padding, specs, `tf.Session` handling, and `utils_tf` workflows belong to [tensorflow-ops](..\u002Ftensorflow-ops\u002FSKILL.md).\n- Sonnet blocks, graph network modules, learned architecture choices, and model call requirements belong to [graph-models](..\u002Fgraph-models\u002FSKILL.md).\n- Long notebook-style training recipes belong to the root [demo recipes](..\u002F..\u002Freferences\u002Fdemo-recipes.md) and, for model construction, [graph-models](..\u002Fgraph-models\u002FSKILL.md).\n\n## Minimum preflight checklist\n\n- Confirm whether the graph is featureful or featureless separately for nodes, edges, and globals.\n- Confirm `receivers` and `senders` are both present or both absent; featureless edges still need endpoints.\n- Confirm `n_node` and `n_edge` are present for manually constructed `GraphsTuple` objects and for featureless\u002Fempty data dictionaries that cannot infer counts from arrays.\n- When batching, confirm all data dictionaries have identical non-`None` key sets, including number fields if any dictionary provides them.\n- When using NetworkX, confirm the runtime has `networkx.OrderedMultiDiGraph` or another compatible `networkx\u003C3` graph class accepted by the conversion path.\n","# Graph Data\n\nUse this sub-skill when a task needs to build or inspect Graph Nets data before it reaches TensorFlow or Sonnet modules. It covers `graphs.GraphsTuple`, per-graph data dictionaries, NumPy arrays, NetworkX conversion, batching, unbatching, and slicing.\n\n## Read first\n\n- [Data formats](references\u002Fdata-formats.md): field semantics, valid `None` combinations, batch offsets, data dictionary rules, and NetworkX feature conventions.\n- [API reference](references\u002Fapi-reference.md): exact NumPy conversion and slicing functions, expected inputs\u002Foutputs, and common preflight checks.\n- [Troubleshooting](references\u002Ftroubleshooting.md): fast diagnosis for key-set, endpoint, feature, and NetworkX compatibility failures.\n- [Smoke script](scripts\u002Fgraph_data_smoke.py): deterministic round-trip check that prints JSON and can be run from any working directory.\n\n## Typical workflows\n\n1. **Create a `GraphsTuple` directly** when arrays are already in batched form. Provide all seven fields: `nodes`, `edges`, `receivers`, `senders`, `globals`, `n_node`, and `n_edge`; keep `n_node` and `n_edge` non-`None`.\n2. **Create from per-graph data dictionaries** when each sample is easier to describe independently. Use `utils_np.data_dicts_to_graphs_tuple`, and make every dictionary have the same non-`None` field set.\n3. **Create from NetworkX** when graph topology is naturally object-based. Use `utils_np.networkx_to_data_dict` for one graph or `utils_np.networkxs_to_graphs_tuple` for a batch; enforce ordered integer node keys and the `\"features\"` attribute convention.\n4. **Round-trip or inspect a batch** with `utils_np.graphs_tuple_to_data_dicts`, `utils_np.graphs_tuple_to_networkxs`, or `utils_np.get_graph`.\n5. **Use `GraphsTuple.replace` or `GraphsTuple.map`** for structural-preserving field updates; invalid `None` combinations still raise immediately.\n\n## Boundary routing\n\n- TensorFlow placeholders, tensor batching, padding, specs, `tf.Session` handling, and `utils_tf` workflows belong to [tensorflow-ops](..\u002Ftensorflow-ops\u002FSKILL.md).\n- Sonnet blocks, graph network modules, learned architecture choices, and model call requirements belong to [graph-models](..\u002Fgraph-models\u002FSKILL.md).\n- Long notebook-style training recipes belong to the root [demo recipes](..\u002F..\u002Freferences\u002Fdemo-recipes.md) and, for model construction, [graph-models](..\u002Fgraph-models\u002FSKILL.md).\n\n## Minimum preflight checklist\n\n- Confirm whether the graph is featureful or featureless separately for nodes, edges, and globals.\n- Confirm `receivers` and `senders` are both present or both absent; featureless edges still need endpoints.\n- Confirm `n_node` and `n_edge` are present for manually constructed `GraphsTuple` objects and for featureless\u002Fempty data dictionaries that cannot infer counts from arrays.\n- When batching, confirm all data dictionaries have identical non-`None` key sets, including number fields if any dictionary provides them.\n- When using NetworkX, confirm the runtime has `networkx.OrderedMultiDiGraph` or another compatible `networkx\u003C3` graph class accepted by the conversion path.\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-data",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-data",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill graph-data",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill graph-data","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-data\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fapi-reference.md","REFERENCE","参考文档",7418,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgraph-nets\u002Fsub-skills\u002Fgraph-data\u002Freferences\u002Fapi-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fdata-formats.md",7021,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgraph-nets\u002Fsub-skills\u002Fgraph-data\u002Freferences\u002Fdata-formats.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",7526,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgraph-nets\u002Fsub-skills\u002Fgraph-data\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fgraph_data_smoke.py","SCRIPT","脚本",5835,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgraph-nets\u002Fsub-skills\u002Fgraph-data\u002Fscripts\u002Fgraph_data_smoke.py",[68,75,82,89,96,103],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"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":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"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":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"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":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"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":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"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":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"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",[],[]]