[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M795D267B0GNGGZBEECWNCZX":3,"skill-same:01M795D267B0GNGGZBEECWNCZX":70},{"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},"01M795D267B0GNGGZBEECWNCZX","gnn-models",null,"Guides Spektral graph neural network layers, pooling, ready-made models, message passing, and explanation workflows.","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\u002Fspektral\u002Fsub-skills\u002Fgnn-models\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: gnn-models\ndescription: \"Guides Spektral graph neural network layers, pooling, ready-made\n  models, message passing, and explanation workflows.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Spektral GNN Models\n\nUse this sub-skill when the task is about building, selecting, debugging, or explaining graph neural network layers and models with Spektral.\n\n## Read first\n\n- `references\u002Flayer-catalog.md` for convolution, pooling, base layer, and mode-support summaries.\n- `references\u002Fapi-reference.md` for verified model, layer, utility, and explainer signatures.\n- `references\u002Fworkflows.md` for GCN, GeneralGNN, custom `MessagePassing`, batch-mask, and explainer recipes.\n- `references\u002Ftroubleshooting.md` for sparse\u002Fdense adjacency, mask propagation, Keras compatibility, layer-input, pooling, and explainer failures.\n- `scripts\u002Fsmoke_models.py` for a tiny no-download CPU model\u002Flayer sanity check.\n\n## Core decisions\n\n1. Decide the data mode with `..\u002Fgraph-data\u002FSKILL.md` before selecting layers.\n2. Match layer mode support to loader output:\n   - `SingleLoader` and `DisjointLoader` usually work with sparse-aware layers.\n   - `BatchLoader` emits dense padded tensors; use only layers that support batch mode.\n   - `MixedLoader` shares one adjacency matrix and needs layers\u002Fmodels that support mixed mode.\n3. Apply required adjacency preprocessing before training. Many layers implement `preprocess(a)` and can be paired with `LayerPreprocess`.\n4. Use `GraphMasking` when `BatchLoader(mask=True)` appends a mask feature for dense padded batches.\n5. Keep full training\u002Fbenchmark runs separate from smoke checks; the bundled script only validates wiring.\n\n## Start points\n\n| Task | Start with | Notes |\n| --- | --- | --- |\n| Simple citation-style node prediction | `GCN` or `GCNConv` | `GCN` outputs node predictions and accepts `(x, a)` or `(x, a, i)` |\n| General graph classification\u002Fregression | `GeneralGNN` plus `DisjointLoader` | Defaults use GeneralConv blocks and global sum pooling |\n| Custom architecture | Keras functional\u002Fsubclassed model plus Spektral layers | Use layer catalog to match data mode and edge-feature needs |\n| Custom sparse message passing | `MessagePassing` subclass | Single\u002Fdisjoint sparse adjacency only |\n| Dense pooling | `BatchLoader(mask=True)`, `GraphMasking`, then dense pooling layer | MinCut\u002FDiffPool-style layers expect batch-compatible shapes |\n| Explanation | `GNNExplainer` | Node or graph explanations after a model is trained or otherwise produces predictions |\n\n## Minimal validation\n\nRun from the generated skill tree after installing Spektral:\n\n```bash\npython sub-skills\u002Fgnn-models\u002Fscripts\u002Fsmoke_models.py\n```\n\nExpected signal: successful tiny forward passes for `GeneralGNN`, `GCN`, `GCNConv` with batch masking, and a custom `MessagePassing` subclass, followed by `smoke_ok`.\n\n## Important compatibility note\n\nThis Spektral source revision was verified with TensorFlow `2.15.1` and Keras `2.15.0`. In a latest TensorFlow\u002FKeras 3 environment, `GCN`\u002F`GCNConv` mask handling may fail with an error about converting `None` to a tensor. If that happens, use the troubleshooting page to pin a TensorFlow\u002FKeras 2.x-compatible stack or rewrite the model call path to avoid the incompatible mask behavior.\n\n## Route away when\n\n- The task is about constructing `Graph` or `Dataset` objects, choosing loaders, or configuring dataset downloads: use `..\u002Fgraph-data\u002FSKILL.md`.\n- The task is about generic Keras layer authoring unrelated to graph matrices: use TensorFlow\u002FKeras guidance first.\n- The task asks for PyTorch Geometric, DGL, or NetworkX-only algorithms without Spektral layers.\n","# Spektral GNN Models\n\nUse this sub-skill when the task is about building, selecting, debugging, or explaining graph neural network layers and models with Spektral.\n\n## Read first\n\n- `references\u002Flayer-catalog.md` for convolution, pooling, base layer, and mode-support summaries.\n- `references\u002Fapi-reference.md` for verified model, layer, utility, and explainer signatures.\n- `references\u002Fworkflows.md` for GCN, GeneralGNN, custom `MessagePassing`, batch-mask, and explainer recipes.\n- `references\u002Ftroubleshooting.md` for sparse\u002Fdense adjacency, mask propagation, Keras compatibility, layer-input, pooling, and explainer failures.\n- `scripts\u002Fsmoke_models.py` for a tiny no-download CPU model\u002Flayer sanity check.\n\n## Core decisions\n\n1. Decide the data mode with `..\u002Fgraph-data\u002FSKILL.md` before selecting layers.\n2. Match layer mode support to loader output:\n   - `SingleLoader` and `DisjointLoader` usually work with sparse-aware layers.\n   - `BatchLoader` emits dense padded tensors; use only layers that support batch mode.\n   - `MixedLoader` shares one adjacency matrix and needs layers\u002Fmodels that support mixed mode.\n3. Apply required adjacency preprocessing before training. Many layers implement `preprocess(a)` and can be paired with `LayerPreprocess`.\n4. Use `GraphMasking` when `BatchLoader(mask=True)` appends a mask feature for dense padded batches.\n5. Keep full training\u002Fbenchmark runs separate from smoke checks; the bundled script only validates wiring.\n\n## Start points\n\n| Task | Start with | Notes |\n| --- | --- | --- |\n| Simple citation-style node prediction | `GCN` or `GCNConv` | `GCN` outputs node predictions and accepts `(x, a)` or `(x, a, i)` |\n| General graph classification\u002Fregression | `GeneralGNN` plus `DisjointLoader` | Defaults use GeneralConv blocks and global sum pooling |\n| Custom architecture | Keras functional\u002Fsubclassed model plus Spektral layers | Use layer catalog to match data mode and edge-feature needs |\n| Custom sparse message passing | `MessagePassing` subclass | Single\u002Fdisjoint sparse adjacency only |\n| Dense pooling | `BatchLoader(mask=True)`, `GraphMasking`, then dense pooling layer | MinCut\u002FDiffPool-style layers expect batch-compatible shapes |\n| Explanation | `GNNExplainer` | Node or graph explanations after a model is trained or otherwise produces predictions |\n\n## Minimal validation\n\nRun from the generated skill tree after installing Spektral:\n\n```bash\npython sub-skills\u002Fgnn-models\u002Fscripts\u002Fsmoke_models.py\n```\n\nExpected signal: successful tiny forward passes for `GeneralGNN`, `GCN`, `GCNConv` with batch masking, and a custom `MessagePassing` subclass, followed by `smoke_ok`.\n\n## Important compatibility note\n\nThis Spektral source revision was verified with TensorFlow `2.15.1` and Keras `2.15.0`. In a latest TensorFlow\u002FKeras 3 environment, `GCN`\u002F`GCNConv` mask handling may fail with an error about converting `None` to a tensor. If that happens, use the troubleshooting page to pin a TensorFlow\u002FKeras 2.x-compatible stack or rewrite the model call path to avoid the incompatible mask behavior.\n\n## Route away when\n\n- The task is about constructing `Graph` or `Dataset` objects, choosing loaders, or configuring dataset downloads: use `..\u002Fgraph-data\u002FSKILL.md`.\n- The task is about generic Keras layer authoring unrelated to graph matrices: use TensorFlow\u002FKeras guidance first.\n- The task asks for PyTorch Geometric, DGL, or NetworkX-only algorithms without Spektral layers.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fspektral\u002Fsub-skills\u002Fgnn-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":34,"prompt":44,"zipAvailable":25},[35,38,41],{"tool":36,"command":37},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill gnn-models",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill gnn-models",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill gnn-models","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fspektral\u002Fsub-skills\u002Fgnn-models\u002FSKILL.md",[46,52,56,60,64],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fapi-reference.md","REFERENCE","参考文档",6013,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fspektral\u002Fsub-skills\u002Fgnn-models\u002Freferences\u002Fapi-reference.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Flayer-catalog.md",4847,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fspektral\u002Fsub-skills\u002Fgnn-models\u002Freferences\u002Flayer-catalog.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Ftroubleshooting.md",4098,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fspektral\u002Fsub-skills\u002Fgnn-models\u002Freferences\u002Ftroubleshooting.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Fworkflows.md",4357,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fspektral\u002Fsub-skills\u002Fgnn-models\u002Freferences\u002Fworkflows.md",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Fsmoke_models.py","SCRIPT","脚本",3665,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fspektral\u002Fsub-skills\u002Fgnn-models\u002Fscripts\u002Fsmoke_models.py",[71,79,86,93,100,107],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"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":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"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":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"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":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"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":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"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":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"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",[],[]]