[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M795MXWNN44TJPFHPENCW1PS":3,"skill-same:01M795MXWNN44TJPFHPENCW1PS":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},"01M795MXWNN44TJPFHPENCW1PS","link-prediction-kg",null,"Guides StellarGraph link prediction, link regression, edge splitting, temporal link workflows, and knowledge graph completion with ComplEx, DistMult, RotatE, RotE, and RotH.","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\u002Flink-prediction-kg\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: link-prediction-kg\ndescription: \"Guides StellarGraph link prediction, link regression, edge\n  splitting, temporal link workflows, and knowledge graph completion with\n  ComplEx, DistMult, RotatE, RotE, and RotH.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Link Prediction and Knowledge Graphs\n\nUse this sub-skill when a StellarGraph task predicts edges\u002Fratings\u002Frelations,\nperforms link regression\u002Fclassification, splits graph edges into train\u002Ftest\nsets, or scores triples in a knowledge graph.\n\n## Read first\n\n- [`references\u002Flink-workflows.md`](references\u002Flink-workflows.md) for edge\n  splitting, link generators, Keras link heads, temporal link prediction, and\n  leakage checks.\n- [`references\u002Fknowledge-graphs.md`](references\u002Fknowledge-graphs.md) for\n  `KGTripleGenerator`, `ComplEx`, `DistMult`, `RotatE`, `RotE`, `RotH`, negative\n  sampling, and ranking.\n- [`references\u002Fapi-reference.md`](references\u002Fapi-reference.md) for verified\n  signatures and link\u002FKG object responsibilities.\n- [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) for edge\n  leakage, invalid endpoints, target-shape, negative sampling, and relation-type\n  failures.\n- [`scripts\u002Flink_prediction_smoke.py`](scripts\u002Flink_prediction_smoke.py) for a\n  tiny GCN link-classification wiring check.\n\n## Route here when the user asks to\n\n- use `EdgeSplitter.train_test_split`;\n- build link prediction with `GraphSAGELinkGenerator`, `HinSAGELinkGenerator`,\n  `FullBatchLinkGenerator`, `Attri2VecLinkGenerator`, or `Node2VecLinkGenerator`;\n- add `link_classification`, `link_regression`, or `link_inference` to source\n  and destination node embeddings;\n- perform knowledge graph completion with `KGTripleGenerator`, `ComplEx`,\n  `DistMult`, `RotatE`, `RotE`, or `RotH`;\n- use `SelfAdversarialNegativeSampling` or rank triples against all nodes;\n- adapt CTDNE or temporal link-prediction workflows.\n\n## Route elsewhere\n\n- Raw graph and dataset construction: [`..\u002Fgraph-data-loading\u002FSKILL.md`](..\u002Fgraph-data-loading\u002FSKILL.md).\n- Generator shape debugging: [`..\u002Fsampling-generators\u002FSKILL.md`](..\u002Fsampling-generators\u002FSKILL.md).\n- Node classification: [`..\u002Fnode-classification-gnns\u002FSKILL.md`](..\u002Fnode-classification-gnns\u002FSKILL.md).\n- Node embeddings before downstream edge tasks: [`..\u002Fembedding-workflows\u002FSKILL.md`](..\u002Fembedding-workflows\u002FSKILL.md).\n\n## Operating workflow\n\n1. Construct a graph with valid node IDs, edge IDs\u002Ftypes, and features required\n   by the chosen embedding model.\n2. Split edges for evaluation with `EdgeSplitter` or an equivalent leakage-safe\n   method. Keep train and test positives\u002Fnegatives separate.\n3. Choose a link generator:\n   - GCN\u002FGAT\u002FPPNP-style full-batch embeddings: `FullBatchLinkGenerator`;\n   - GraphSAGE: `GraphSAGELinkGenerator`;\n   - HinSAGE: `HinSAGELinkGenerator` with head node types;\n   - Attri2Vec\u002FNode2Vec link heads: matching link generators;\n   - knowledge graph completion: `KGTripleGenerator`.\n4. Build the base embedding model and call `in_out_tensors()`.\n5. Attach a link head such as `link_classification`, `link_regression`, or\n   `link_inference` to combine source\u002Fdestination embeddings.\n6. Compile and train\u002Fevaluate with generator `flow(link_ids, targets, ...)`.\n7. For knowledge graph models, use negative sampling and ranking routines\n   designed for triples rather than ordinary binary edge pairs.\n\n## Safe check\n\n```bash\npython sub-skills\u002Flink-prediction-kg\u002Fscripts\u002Flink_prediction_smoke.py --help\npython sub-skills\u002Flink-prediction-kg\u002Fscripts\u002Flink_prediction_smoke.py\n```\n\nThe smoke uses a tiny graph and does not download datasets or train a notebook.\n","# Link Prediction and Knowledge Graphs\n\nUse this sub-skill when a StellarGraph task predicts edges\u002Fratings\u002Frelations,\nperforms link regression\u002Fclassification, splits graph edges into train\u002Ftest\nsets, or scores triples in a knowledge graph.\n\n## Read first\n\n- [`references\u002Flink-workflows.md`](references\u002Flink-workflows.md) for edge\n  splitting, link generators, Keras link heads, temporal link prediction, and\n  leakage checks.\n- [`references\u002Fknowledge-graphs.md`](references\u002Fknowledge-graphs.md) for\n  `KGTripleGenerator`, `ComplEx`, `DistMult`, `RotatE`, `RotE`, `RotH`, negative\n  sampling, and ranking.\n- [`references\u002Fapi-reference.md`](references\u002Fapi-reference.md) for verified\n  signatures and link\u002FKG object responsibilities.\n- [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) for edge\n  leakage, invalid endpoints, target-shape, negative sampling, and relation-type\n  failures.\n- [`scripts\u002Flink_prediction_smoke.py`](scripts\u002Flink_prediction_smoke.py) for a\n  tiny GCN link-classification wiring check.\n\n## Route here when the user asks to\n\n- use `EdgeSplitter.train_test_split`;\n- build link prediction with `GraphSAGELinkGenerator`, `HinSAGELinkGenerator`,\n  `FullBatchLinkGenerator`, `Attri2VecLinkGenerator`, or `Node2VecLinkGenerator`;\n- add `link_classification`, `link_regression`, or `link_inference` to source\n  and destination node embeddings;\n- perform knowledge graph completion with `KGTripleGenerator`, `ComplEx`,\n  `DistMult`, `RotatE`, `RotE`, or `RotH`;\n- use `SelfAdversarialNegativeSampling` or rank triples against all nodes;\n- adapt CTDNE or temporal link-prediction workflows.\n\n## Route elsewhere\n\n- Raw graph and dataset construction: [`..\u002Fgraph-data-loading\u002FSKILL.md`](..\u002Fgraph-data-loading\u002FSKILL.md).\n- Generator shape debugging: [`..\u002Fsampling-generators\u002FSKILL.md`](..\u002Fsampling-generators\u002FSKILL.md).\n- Node classification: [`..\u002Fnode-classification-gnns\u002FSKILL.md`](..\u002Fnode-classification-gnns\u002FSKILL.md).\n- Node embeddings before downstream edge tasks: [`..\u002Fembedding-workflows\u002FSKILL.md`](..\u002Fembedding-workflows\u002FSKILL.md).\n\n## Operating workflow\n\n1. Construct a graph with valid node IDs, edge IDs\u002Ftypes, and features required\n   by the chosen embedding model.\n2. Split edges for evaluation with `EdgeSplitter` or an equivalent leakage-safe\n   method. Keep train and test positives\u002Fnegatives separate.\n3. Choose a link generator:\n   - GCN\u002FGAT\u002FPPNP-style full-batch embeddings: `FullBatchLinkGenerator`;\n   - GraphSAGE: `GraphSAGELinkGenerator`;\n   - HinSAGE: `HinSAGELinkGenerator` with head node types;\n   - Attri2Vec\u002FNode2Vec link heads: matching link generators;\n   - knowledge graph completion: `KGTripleGenerator`.\n4. Build the base embedding model and call `in_out_tensors()`.\n5. Attach a link head such as `link_classification`, `link_regression`, or\n   `link_inference` to combine source\u002Fdestination embeddings.\n6. Compile and train\u002Fevaluate with generator `flow(link_ids, targets, ...)`.\n7. For knowledge graph models, use negative sampling and ranking routines\n   designed for triples rather than ordinary binary edge pairs.\n\n## Safe check\n\n```bash\npython sub-skills\u002Flink-prediction-kg\u002Fscripts\u002Flink_prediction_smoke.py --help\npython sub-skills\u002Flink-prediction-kg\u002Fscripts\u002Flink_prediction_smoke.py\n```\n\nThe smoke uses a tiny graph and does not download datasets or train a notebook.\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\u002Flink-prediction-kg",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 link-prediction-kg",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill link-prediction-kg",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill link-prediction-kg","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fstellargraph\u002Fsub-skills\u002Flink-prediction-kg\u002FSKILL.md",[47,53,57,61,65],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fapi-reference.md","REFERENCE","参考文档",3831,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fstellargraph\u002Fsub-skills\u002Flink-prediction-kg\u002Freferences\u002Fapi-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fknowledge-graphs.md",3086,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fstellargraph\u002Fsub-skills\u002Flink-prediction-kg\u002Freferences\u002Fknowledge-graphs.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Flink-workflows.md",3683,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fstellargraph\u002Fsub-skills\u002Flink-prediction-kg\u002Freferences\u002Flink-workflows.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Ftroubleshooting.md",2611,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fstellargraph\u002Fsub-skills\u002Flink-prediction-kg\u002Freferences\u002Ftroubleshooting.md",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Flink_prediction_smoke.py","SCRIPT","脚本",2468,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fstellargraph\u002Fsub-skills\u002Flink-prediction-kg\u002Fscripts\u002Flink_prediction_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",[],[]]