[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M795N1BC6M75KFHH7WJ2P1FS":3,"skill-same:01M795N1BC6M75KFHH7WJ2P1FS":71},{"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},"01M795N1BC6M75KFHH7WJ2P1FS","model-ops-interpretability",null,"Guides StellarGraph saved-model loading, custom Keras layers, calibration, ensembles, saliency and integrated gradients, randomness utilities, plotting, and optional Neo4j connector workflows.","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\u002Fstellargraph\u002Fsub-skills\u002Fmodel-ops-interpretability\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: model-ops-interpretability\ndescription: \"Guides StellarGraph saved-model loading, custom Keras layers,\n  calibration, ensembles, saliency and integrated gradients, randomness\n  utilities, plotting, and optional Neo4j connector workflows.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Model Operations and Interpretability\n\nUse this sub-skill for operational tasks around StellarGraph models after or\naround training: saved-model loading, probability calibration, ensembles,\ninterpretability, plotting\u002Fhistory, random seeds, and optional Neo4j connector\nworkflows.\n\n## Read first\n\n- [`references\u002Foperations.md`](references\u002Foperations.md) for\n  `custom_keras_layers`, calibration, ensembles, history plotting, and seed\n  utilities.\n- [`references\u002Finterpretability.md`](references\u002Finterpretability.md) for GCN\u002FGAT\n  saliency and integrated-gradient workflows.\n- [`references\u002Fneo4j.md`](references\u002Fneo4j.md) for optional Neo4j connector\n  classes, service requirements, ID\u002Ffeatures properties, and warnings.\n- [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) for saved\n  model, calibration\u002Fensemble, saliency, TensorFlow, and Neo4j failures.\n- [`scripts\u002Fcalibration_smoke.py`](scripts\u002Fcalibration_smoke.py) for a safe tiny\n  calibration smoke.\n\n## Route here when the user asks to\n\n- load a Keras model containing StellarGraph custom layers;\n- calibrate model outputs with `TemperatureCalibration`, `IsotonicCalibration`,\n  expected calibration error, or reliability diagrams;\n- build `Ensemble` or `BaggingEnsemble` wrappers;\n- explain node\u002Fedge importance with GCN\u002FGAT saliency maps or integrated\n  gradients;\n- check reproducibility utilities such as random seeds;\n- use `Neo4jStellarGraph`, `Neo4jStellarDiGraph`, or Neo4j GraphSAGE generators.\n\n## Route elsewhere\n\nCore model training still belongs to the owning workflow route:\n\n- node models: [`..\u002Fnode-classification-gnns\u002FSKILL.md`](..\u002Fnode-classification-gnns\u002FSKILL.md);\n- link prediction\u002FKG: [`..\u002Flink-prediction-kg\u002FSKILL.md`](..\u002Flink-prediction-kg\u002FSKILL.md);\n- embeddings: [`..\u002Fembedding-workflows\u002FSKILL.md`](..\u002Fembedding-workflows\u002FSKILL.md);\n- graph\u002Ftime-series: [`..\u002Fgraph-time-series-workflows\u002FSKILL.md`](..\u002Fgraph-time-series-workflows\u002FSKILL.md).\n\n## Operating workflow\n\n1. Identify the operational surface: saved model, probability outputs,\n   uncertainty\u002Fensemble, saliency, or Neo4j-backed graph access.\n2. Verify package\u002FTensorFlow import with the root diagnostic if the environment\n   is suspect.\n3. For saved models, pass `stellargraph.custom_keras_layers` as Keras\n   `custom_objects`.\n4. For calibration, use logits or probabilities with the shapes required by the\n   calibration class; validate with a tiny smoke before applying to model\n   outputs.\n5. For saliency, keep generator sparse\u002Fdense settings consistent with the model\n   and use node indices\u002Fclasses that exist.\n6. For Neo4j, confirm `py2neo`, service reachability, ID property, feature\n   property, and uniqueness constraints before expecting model generators to\n   work.\n\n## Safe check\n\n```bash\npython sub-skills\u002Fmodel-ops-interpretability\u002Fscripts\u002Fcalibration_smoke.py --help\npython sub-skills\u002Fmodel-ops-interpretability\u002Fscripts\u002Fcalibration_smoke.py\n```\n","# Model Operations and Interpretability\n\nUse this sub-skill for operational tasks around StellarGraph models after or\naround training: saved-model loading, probability calibration, ensembles,\ninterpretability, plotting\u002Fhistory, random seeds, and optional Neo4j connector\nworkflows.\n\n## Read first\n\n- [`references\u002Foperations.md`](references\u002Foperations.md) for\n  `custom_keras_layers`, calibration, ensembles, history plotting, and seed\n  utilities.\n- [`references\u002Finterpretability.md`](references\u002Finterpretability.md) for GCN\u002FGAT\n  saliency and integrated-gradient workflows.\n- [`references\u002Fneo4j.md`](references\u002Fneo4j.md) for optional Neo4j connector\n  classes, service requirements, ID\u002Ffeatures properties, and warnings.\n- [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) for saved\n  model, calibration\u002Fensemble, saliency, TensorFlow, and Neo4j failures.\n- [`scripts\u002Fcalibration_smoke.py`](scripts\u002Fcalibration_smoke.py) for a safe tiny\n  calibration smoke.\n\n## Route here when the user asks to\n\n- load a Keras model containing StellarGraph custom layers;\n- calibrate model outputs with `TemperatureCalibration`, `IsotonicCalibration`,\n  expected calibration error, or reliability diagrams;\n- build `Ensemble` or `BaggingEnsemble` wrappers;\n- explain node\u002Fedge importance with GCN\u002FGAT saliency maps or integrated\n  gradients;\n- check reproducibility utilities such as random seeds;\n- use `Neo4jStellarGraph`, `Neo4jStellarDiGraph`, or Neo4j GraphSAGE generators.\n\n## Route elsewhere\n\nCore model training still belongs to the owning workflow route:\n\n- node models: [`..\u002Fnode-classification-gnns\u002FSKILL.md`](..\u002Fnode-classification-gnns\u002FSKILL.md);\n- link prediction\u002FKG: [`..\u002Flink-prediction-kg\u002FSKILL.md`](..\u002Flink-prediction-kg\u002FSKILL.md);\n- embeddings: [`..\u002Fembedding-workflows\u002FSKILL.md`](..\u002Fembedding-workflows\u002FSKILL.md);\n- graph\u002Ftime-series: [`..\u002Fgraph-time-series-workflows\u002FSKILL.md`](..\u002Fgraph-time-series-workflows\u002FSKILL.md).\n\n## Operating workflow\n\n1. Identify the operational surface: saved model, probability outputs,\n   uncertainty\u002Fensemble, saliency, or Neo4j-backed graph access.\n2. Verify package\u002FTensorFlow import with the root diagnostic if the environment\n   is suspect.\n3. For saved models, pass `stellargraph.custom_keras_layers` as Keras\n   `custom_objects`.\n4. For calibration, use logits or probabilities with the shapes required by the\n   calibration class; validate with a tiny smoke before applying to model\n   outputs.\n5. For saliency, keep generator sparse\u002Fdense settings consistent with the model\n   and use node indices\u002Fclasses that exist.\n6. For Neo4j, confirm `py2neo`, service reachability, ID property, feature\n   property, and uniqueness constraints before expecting model generators to\n   work.\n\n## Safe check\n\n```bash\npython sub-skills\u002Fmodel-ops-interpretability\u002Fscripts\u002Fcalibration_smoke.py --help\npython sub-skills\u002Fmodel-ops-interpretability\u002Fscripts\u002Fcalibration_smoke.py\n```\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\u002Fstellargraph\u002Fsub-skills\u002Fmodel-ops-interpretability",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 model-ops-interpretability",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill model-ops-interpretability",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill model-ops-interpretability","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fstellargraph\u002Fsub-skills\u002Fmodel-ops-interpretability\u002FSKILL.md",[47,53,57,61,65],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Finterpretability.md","REFERENCE","参考文档",1823,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fstellargraph\u002Fsub-skills\u002Fmodel-ops-interpretability\u002Freferences\u002Finterpretability.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fneo4j.md",1961,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fstellargraph\u002Fsub-skills\u002Fmodel-ops-interpretability\u002Freferences\u002Fneo4j.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Foperations.md",1902,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fstellargraph\u002Fsub-skills\u002Fmodel-ops-interpretability\u002Freferences\u002Foperations.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Ftroubleshooting.md",1596,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fstellargraph\u002Fsub-skills\u002Fmodel-ops-interpretability\u002Freferences\u002Ftroubleshooting.md",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Fcalibration_smoke.py","SCRIPT","脚本",905,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fstellargraph\u002Fsub-skills\u002Fmodel-ops-interpretability\u002Fscripts\u002Fcalibration_smoke.py",[72,79,86,93,100,107],{"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},"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":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},"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":14,"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":14,"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":14,"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":14,"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",[],[]]