[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78TZCVJPMYAFAY80VF41WNV":3,"skill-same:01M78TZCVJPMYAFAY80VF41WNV":74},{"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},"01M78TZCVJPMYAFAY80VF41WNV","graph-data-and-datasets",null,"Use CogDL graph data objects, custom datasets, built-in dataset selection, masks, batching, and no-download data validation.","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\u002Fcogdl\u002Fsub-skills\u002Fgraph-data-and-datasets\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: graph-data-and-datasets\ndescription: \"Use CogDL graph data objects, custom datasets, built-in dataset\n  selection, masks, batching, and no-download data validation.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# CogDL Graph Data and Datasets\n\nUse this sub-skill when the task is about CogDL data objects rather than model\narchitecture or training orchestration.\n\n## Use when\n\n- Creating or inspecting `cogdl.data.Graph`, `Adjacency`, `Dataset`,\n  `NodeDataset`, `GraphDataset`, `generate_random_graph`, or `DataLoader`.\n- Building a no-download custom node-classification or graph-classification\n  fixture.\n- Choosing a built-in dataset name while making download\u002Fcache\u002Fdependency\n  effects explicit.\n- Debugging `edge_index`, CSR fields, masks, labels, node features, subgraphs,\n  `local_graph`, self-loops, normalization, or batched graph objects.\n\n## Route elsewhere\n\n- Training loops, wrapper matching, checkpoints, loggers, or `Trainer` details:\n  `..\u002Ftraining-wrappers-and-customization\u002FSKILL.md`.\n- High-level `experiment()` calls, CLI flags, variants, or AutoML:\n  `..\u002Fexperiments-and-cli\u002FSKILL.md`.\n- Model, layer, sparse operator, PyG\u002FJittor\u002FDGL, or CUDA acceleration details:\n  `..\u002Fmodels-layers-and-operators\u002FSKILL.md`.\n- Application pipelines such as OAG-BERT, recommendation, visualization, or\n  embedding pipelines: `..\u002Fpipelines-and-applications\u002FSKILL.md`.\n\n## Operating checklist\n\n1. Prefer a self-contained `Graph` or custom dataset artifact before loading a\n   built-in dataset. Built-in datasets may download data and write caches when\n   missing.\n2. Validate node-classification fixtures before handing them to experiments or\n   wrappers. Use the bundled `scripts\u002Fvalidate_graph_masks.py` on a saved\n   `Graph` or `NodeDataset` artifact.\n3. For quick no-download examples, use\n   `scripts\u002Fcreate_tiny_graph_dataset.py --output-dir \u003Cdirectory>` to create\n   deterministic node and graph classification artifacts.\n4. Keep `Graph` schemas explicit: tensor `x`, tensor `y`, COO `edge_index`, and\n   boolean or index masks with node-count-compatible lengths.\n5. For graph classification, save a list of local-node-indexed `Graph` objects\n   and batch them with `cogdl.data.DataLoader`; if node features are absent,\n   route the degree-feature training decision to the training-wrapper sub-skill.\n\n## Reference map\n\n- `references\u002Fgraph-and-dataset-api.md`: verified public data APIs and graph\n  methods.\n- `references\u002Fdata-formats.md`: COO\u002FCSR formats, masks, batching, mutation\n  semantics, and validation checklist.\n- `references\u002Fbuilt-in-datasets.md`: dataset families, registered names, and\n  network\u002Fcache\u002Fdependency caveats.\n- `references\u002Ftroubleshooting.md`: common failures and recovery steps for graph\n  data construction.\n\n","# CogDL Graph Data and Datasets\n\nUse this sub-skill when the task is about CogDL data objects rather than model\narchitecture or training orchestration.\n\n## Use when\n\n- Creating or inspecting `cogdl.data.Graph`, `Adjacency`, `Dataset`,\n  `NodeDataset`, `GraphDataset`, `generate_random_graph`, or `DataLoader`.\n- Building a no-download custom node-classification or graph-classification\n  fixture.\n- Choosing a built-in dataset name while making download\u002Fcache\u002Fdependency\n  effects explicit.\n- Debugging `edge_index`, CSR fields, masks, labels, node features, subgraphs,\n  `local_graph`, self-loops, normalization, or batched graph objects.\n\n## Route elsewhere\n\n- Training loops, wrapper matching, checkpoints, loggers, or `Trainer` details:\n  `..\u002Ftraining-wrappers-and-customization\u002FSKILL.md`.\n- High-level `experiment()` calls, CLI flags, variants, or AutoML:\n  `..\u002Fexperiments-and-cli\u002FSKILL.md`.\n- Model, layer, sparse operator, PyG\u002FJittor\u002FDGL, or CUDA acceleration details:\n  `..\u002Fmodels-layers-and-operators\u002FSKILL.md`.\n- Application pipelines such as OAG-BERT, recommendation, visualization, or\n  embedding pipelines: `..\u002Fpipelines-and-applications\u002FSKILL.md`.\n\n## Operating checklist\n\n1. Prefer a self-contained `Graph` or custom dataset artifact before loading a\n   built-in dataset. Built-in datasets may download data and write caches when\n   missing.\n2. Validate node-classification fixtures before handing them to experiments or\n   wrappers. Use the bundled `scripts\u002Fvalidate_graph_masks.py` on a saved\n   `Graph` or `NodeDataset` artifact.\n3. For quick no-download examples, use\n   `scripts\u002Fcreate_tiny_graph_dataset.py --output-dir \u003Cdirectory>` to create\n   deterministic node and graph classification artifacts.\n4. Keep `Graph` schemas explicit: tensor `x`, tensor `y`, COO `edge_index`, and\n   boolean or index masks with node-count-compatible lengths.\n5. For graph classification, save a list of local-node-indexed `Graph` objects\n   and batch them with `cogdl.data.DataLoader`; if node features are absent,\n   route the degree-feature training decision to the training-wrapper sub-skill.\n\n## Reference map\n\n- `references\u002Fgraph-and-dataset-api.md`: verified public data APIs and graph\n  methods.\n- `references\u002Fdata-formats.md`: COO\u002FCSR formats, masks, batching, mutation\n  semantics, and validation checklist.\n- `references\u002Fbuilt-in-datasets.md`: dataset families, registered names, and\n  network\u002Fcache\u002Fdependency caveats.\n- `references\u002Ftroubleshooting.md`: common failures and recovery steps for graph\n  data construction.\n\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fcogdl\u002Fsub-skills\u002Fgraph-data-and-datasets",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 graph-data-and-datasets",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill graph-data-and-datasets",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill graph-data-and-datasets","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fcogdl\u002Fsub-skills\u002Fgraph-data-and-datasets\u002FSKILL.md",[46,52,56,60,64,70],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fbuilt-in-datasets.md","REFERENCE","参考文档",7328,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fcogdl\u002Fsub-skills\u002Fgraph-data-and-datasets\u002Freferences\u002Fbuilt-in-datasets.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fdata-formats.md",6927,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fcogdl\u002Fsub-skills\u002Fgraph-data-and-datasets\u002Freferences\u002Fdata-formats.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fgraph-and-dataset-api.md",9840,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fcogdl\u002Fsub-skills\u002Fgraph-data-and-datasets\u002Freferences\u002Fgraph-and-dataset-api.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Ftroubleshooting.md",6286,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fcogdl\u002Fsub-skills\u002Fgraph-data-and-datasets\u002Freferences\u002Ftroubleshooting.md",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Fcreate_tiny_graph_dataset.py","SCRIPT","脚本",10638,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fcogdl\u002Fsub-skills\u002Fgraph-data-and-datasets\u002Fscripts\u002Fcreate_tiny_graph_dataset.py",{"path":71,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":72,"sourceHtmlUrl":73},"scripts\u002Fvalidate_graph_masks.py",13631,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fcogdl\u002Fsub-skills\u002Fgraph-data-and-datasets\u002Fscripts\u002Fvalidate_graph_masks.py",[75,83,90,97,104,111],{"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":79,"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.","Apache-2.0","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":79,"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":79,"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":79,"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":79,"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":79,"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",[],[]]