[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M791KECTFAS6KFE6A8C700QD":3,"skill-same:01M791KECTFAS6KFE6A8C700QD":60},{"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},"01M791KECTFAS6KFE6A8C700QD","link-property-prediction",null,"Routes OGB link-prediction workflows for ogbl datasets, ranking metrics, and KG completion.","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\u002Fogb\u002Fsub-skills\u002Flink-property-prediction\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: link-property-prediction\ndescription: \"Routes OGB link-prediction workflows for ogbl datasets, ranking\n  metrics, and KG completion.\"\nmetadata:\n  disco-role: operating\ndisable-model-invocation: true\nlicense: MIT\n---\n\n# Link Property Prediction\n\nUse this subskill for the link-property family: `ogbl-*` datasets, ranking\nmetrics, and knowledge-graph completion workflows.\n\n## Use this subskill when\n\n- The task names `LinkPropPredDataset`, `PygLinkPropPredDataset`,\n  `DglLinkPropPredDataset`, or `ogbl-*`.\n- The task asks for `hits@K`, `mrr`, or link-level `rocauc` evaluation.\n- The task mentions `ogbl-collab`, `ogbl-ppa`, `ogbl-citation2`,\n  `ogbl-ddi`, `ogbl-biokg`, `ogbl-wikikg2`, or `ogbl-vessel`.\n\n## First decisions\n\n1. Read [`references\u002Fworkflows.md`](references\u002Fworkflows.md) for the link\n   prediction flow and metric-specific shapes.\n2. Read [`references\u002Fapi-reference.md`](references\u002Fapi-reference.md) for the\n   public class names, split structure, and evaluator inputs.\n3. Read [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) when\n   ranking shapes or top-k arrays fail validation.\n\n## Main workflow\n\n- Pick the exact `ogbl-*` dataset name.\n- Load the dataset and inspect `get_edge_split()`.\n- Decide whether the task uses hits@K, MRR, or ROC-AUC.\n- Keep the positive and negative score shapes aligned before calling the\n  evaluator.\n- For knowledge-graph completion, pay attention to the rank-based inputs rather\n  than treating the task like ordinary binary edge classification.\n\n## Common routing choices\n\n- `ogbl-collab` \u002F `ogbl-ppa` -> graph link prediction baselines.\n- `ogbl-citation2` -> citation ranking with MRR-style evaluation.\n- `ogbl-biokg` \u002F `ogbl-wikikg2` -> knowledge-graph completion.\n- `ogbl-ddi` -> edge prediction with hits@20.\n- `ogbl-vessel` -> ROC-AUC with the external contribution workflow.\n\n## Optional backend note\n\nPyG and DGL wrappers are optional. If they are not installed, the core OGB link\nworkflow still works through the library-agnostic loader.\n\n## What not to do here\n\n- Do not treat link prediction as a node-classification task.\n- Do not feed score tensors with the wrong rank into the evaluator.\n- Do not depend on the original checkout for final runtime guidance.\n\n## Related references\n\n- [`..\u002F..\u002Freferences\u002Fapi-overview.md`](..\u002F..\u002Freferences\u002Fapi-overview.md)\n- [`..\u002F..\u002Freferences\u002Fdataset-catalog.md`](..\u002F..\u002Freferences\u002Fdataset-catalog.md)\n- [`..\u002F..\u002Freferences\u002Ftroubleshooting.md`](..\u002F..\u002Freferences\u002Ftroubleshooting.md)\n","# Link Property Prediction\n\nUse this subskill for the link-property family: `ogbl-*` datasets, ranking\nmetrics, and knowledge-graph completion workflows.\n\n## Use this subskill when\n\n- The task names `LinkPropPredDataset`, `PygLinkPropPredDataset`,\n  `DglLinkPropPredDataset`, or `ogbl-*`.\n- The task asks for `hits@K`, `mrr`, or link-level `rocauc` evaluation.\n- The task mentions `ogbl-collab`, `ogbl-ppa`, `ogbl-citation2`,\n  `ogbl-ddi`, `ogbl-biokg`, `ogbl-wikikg2`, or `ogbl-vessel`.\n\n## First decisions\n\n1. Read [`references\u002Fworkflows.md`](references\u002Fworkflows.md) for the link\n   prediction flow and metric-specific shapes.\n2. Read [`references\u002Fapi-reference.md`](references\u002Fapi-reference.md) for the\n   public class names, split structure, and evaluator inputs.\n3. Read [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) when\n   ranking shapes or top-k arrays fail validation.\n\n## Main workflow\n\n- Pick the exact `ogbl-*` dataset name.\n- Load the dataset and inspect `get_edge_split()`.\n- Decide whether the task uses hits@K, MRR, or ROC-AUC.\n- Keep the positive and negative score shapes aligned before calling the\n  evaluator.\n- For knowledge-graph completion, pay attention to the rank-based inputs rather\n  than treating the task like ordinary binary edge classification.\n\n## Common routing choices\n\n- `ogbl-collab` \u002F `ogbl-ppa` -> graph link prediction baselines.\n- `ogbl-citation2` -> citation ranking with MRR-style evaluation.\n- `ogbl-biokg` \u002F `ogbl-wikikg2` -> knowledge-graph completion.\n- `ogbl-ddi` -> edge prediction with hits@20.\n- `ogbl-vessel` -> ROC-AUC with the external contribution workflow.\n\n## Optional backend note\n\nPyG and DGL wrappers are optional. If they are not installed, the core OGB link\nworkflow still works through the library-agnostic loader.\n\n## What not to do here\n\n- Do not treat link prediction as a node-classification task.\n- Do not feed score tensors with the wrong rank into the evaluator.\n- Do not depend on the original checkout for final runtime guidance.\n\n## Related references\n\n- [`..\u002F..\u002Freferences\u002Fapi-overview.md`](..\u002F..\u002Freferences\u002Fapi-overview.md)\n- [`..\u002F..\u002Freferences\u002Fdataset-catalog.md`](..\u002F..\u002Freferences\u002Fdataset-catalog.md)\n- [`..\u002F..\u002Freferences\u002Ftroubleshooting.md`](..\u002F..\u002Freferences\u002Ftroubleshooting.md)\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fogb\u002Fsub-skills\u002Flink-property-prediction",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 link-property-prediction",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill link-property-prediction",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill link-property-prediction","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fogb\u002Fsub-skills\u002Flink-property-prediction\u002FSKILL.md",[46,52,56],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fapi-reference.md","REFERENCE","参考文档",941,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fogb\u002Fsub-skills\u002Flink-property-prediction\u002Freferences\u002Fapi-reference.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Ftroubleshooting.md",829,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fogb\u002Fsub-skills\u002Flink-property-prediction\u002Freferences\u002Ftroubleshooting.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fworkflows.md",1634,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fogb\u002Fsub-skills\u002Flink-property-prediction\u002Freferences\u002Fworkflows.md",[61,69,76,83,90,97],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":65,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"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":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":65,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"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":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":65,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"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":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":65,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"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":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":65,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"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":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":65,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"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",[],[]]