[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M793NJ6959FAF8A2MH5MACGA":3,"skill-same:01M793NJ6959FAF8A2MH5MACGA":66},{"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},"01M793NJ6959FAF8A2MH5MACGA","explainability",null,"Configure PyTorch Geometric Explainer workflows, explanation algorithms, masks, thresholds, metrics, and explainability failure recovery.","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\u002Fpytorch-geometric\u002Fsub-skills\u002Fexplainability\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: explainability\ndescription: \"Configure PyTorch Geometric Explainer workflows, explanation\n  algorithms, masks, thresholds, metrics, and explainability failure recovery.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Explainability\n\nUse this sub-skill when configuring `torch_geometric.explain.Explainer`, choosing algorithms such as `GNNExplainer`, generating homogeneous or heterogeneous explanations, applying mask thresholds, evaluating explanation metrics, or recovering from explainability-specific configuration failures.\n\nDo not use this sub-skill for training a production base model from scratch, designing generic GNN architectures, building heterogeneous graph schemas, sampling at scale, or dataset construction. Route those to sibling sub-skills when present, then return here once the model exposes a stable forward signature to explain.\n\n## Start Here\n\n- Read `references\u002Fexplainer-api.md` when choosing `Explainer`, `GNNExplainer`, `Explanation`, `HeteroExplanation`, `ModelConfig`, mask types, threshold types, or metric APIs.\n- Read `references\u002Fexplanation-workflows.md` when implementing node, graph, link, or heterogeneous explanation workflows and deciding how to pass `target`, `index`, `batch`, or typed dictionaries.\n- Read `references\u002Ftroubleshooting.md` when errors mention `model_config`, missing mask types, invalid thresholds, unavailable masks, hetero routing, repeated backward passes, or slow explainer epochs.\n- Run `scripts\u002Ftiny_explainer_smoke.py --epochs 2` to verify a CPU-only synthetic `GNNExplainer` path without downloads, GPUs, credentials, or long training.\n\n## Common Tasks\n\n- Wrap a trained PyG model with `Explainer(model, algorithm=GNNExplainer(...), explanation_type='model', model_config=..., node_mask_type=..., edge_mask_type=...)`.\n- Match `model_config` to actual model output: `mode` is `binary_classification`, `multiclass_classification`, or `regression`; `task_level` is `node`, `edge`, or `graph`; `return_type` is `raw`, `probs`, or `log_probs`.\n- Use at least one mask type: `node_mask_type='attributes'`, `'common_attributes'`, or `'object'`; `edge_mask_type='object'` or `None`.\n- Explain a specific node or output row with `explanation = explainer(x, edge_index, index=node_index)` and inspect `explanation.available_explanations`, `explanation.node_mask`, and `explanation.edge_mask`.\n- Evaluate classification explanations with metrics such as `fidelity(explainer, explanation)` or `unfaithfulness(explainer, explanation)` after confirming the explanation has the masks those metrics need.\n\n## Safe Validation\n\n```bash\npython scripts\u002Ftiny_explainer_smoke.py --epochs 2\npython scripts\u002Ftiny_explainer_smoke.py --epochs 1 --threshold-topk 3 --node-index 2\npython scripts\u002Ftiny_explainer_smoke.py --help\n```\n\nExpected output includes available explanation mask names, node\u002Fedge mask shapes, finite mask sums, model prediction for the explained node, and `tiny_explainer_smoke: ok`.\n","# Explainability\n\nUse this sub-skill when configuring `torch_geometric.explain.Explainer`, choosing algorithms such as `GNNExplainer`, generating homogeneous or heterogeneous explanations, applying mask thresholds, evaluating explanation metrics, or recovering from explainability-specific configuration failures.\n\nDo not use this sub-skill for training a production base model from scratch, designing generic GNN architectures, building heterogeneous graph schemas, sampling at scale, or dataset construction. Route those to sibling sub-skills when present, then return here once the model exposes a stable forward signature to explain.\n\n## Start Here\n\n- Read `references\u002Fexplainer-api.md` when choosing `Explainer`, `GNNExplainer`, `Explanation`, `HeteroExplanation`, `ModelConfig`, mask types, threshold types, or metric APIs.\n- Read `references\u002Fexplanation-workflows.md` when implementing node, graph, link, or heterogeneous explanation workflows and deciding how to pass `target`, `index`, `batch`, or typed dictionaries.\n- Read `references\u002Ftroubleshooting.md` when errors mention `model_config`, missing mask types, invalid thresholds, unavailable masks, hetero routing, repeated backward passes, or slow explainer epochs.\n- Run `scripts\u002Ftiny_explainer_smoke.py --epochs 2` to verify a CPU-only synthetic `GNNExplainer` path without downloads, GPUs, credentials, or long training.\n\n## Common Tasks\n\n- Wrap a trained PyG model with `Explainer(model, algorithm=GNNExplainer(...), explanation_type='model', model_config=..., node_mask_type=..., edge_mask_type=...)`.\n- Match `model_config` to actual model output: `mode` is `binary_classification`, `multiclass_classification`, or `regression`; `task_level` is `node`, `edge`, or `graph`; `return_type` is `raw`, `probs`, or `log_probs`.\n- Use at least one mask type: `node_mask_type='attributes'`, `'common_attributes'`, or `'object'`; `edge_mask_type='object'` or `None`.\n- Explain a specific node or output row with `explanation = explainer(x, edge_index, index=node_index)` and inspect `explanation.available_explanations`, `explanation.node_mask`, and `explanation.edge_mask`.\n- Evaluate classification explanations with metrics such as `fidelity(explainer, explanation)` or `unfaithfulness(explainer, explanation)` after confirming the explanation has the masks those metrics need.\n\n## Safe Validation\n\n```bash\npython scripts\u002Ftiny_explainer_smoke.py --epochs 2\npython scripts\u002Ftiny_explainer_smoke.py --epochs 1 --threshold-topk 3 --node-index 2\npython scripts\u002Ftiny_explainer_smoke.py --help\n```\n\nExpected output includes available explanation mask names, node\u002Fedge mask shapes, finite mask sums, model prediction for the explained node, and `tiny_explainer_smoke: ok`.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fpytorch-geometric\u002Fsub-skills\u002Fexplainability",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 explainability",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill explainability",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill explainability","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpytorch-geometric\u002Fsub-skills\u002Fexplainability\u002FSKILL.md",[46,52,56,60],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fexplainer-api.md","REFERENCE","参考文档",5675,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpytorch-geometric\u002Fsub-skills\u002Fexplainability\u002Freferences\u002Fexplainer-api.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fexplanation-workflows.md",6019,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpytorch-geometric\u002Fsub-skills\u002Fexplainability\u002Freferences\u002Fexplanation-workflows.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Ftroubleshooting.md",5616,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpytorch-geometric\u002Fsub-skills\u002Fexplainability\u002Freferences\u002Ftroubleshooting.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Ftiny_explainer_smoke.py","SCRIPT","脚本",6830,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpytorch-geometric\u002Fsub-skills\u002Fexplainability\u002Fscripts\u002Ftiny_explainer_smoke.py",[67,75,82,89,96,103],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"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.","Apache-2.0","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":71,"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":71,"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":71,"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":71,"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":71,"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",[],[]]