[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M791KHSFG2ZNGC1SZP71S05X":3,"skill-same:01M791KHSFG2ZNGC1SZP71S05X":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},"01M791KHSFG2ZNGC1SZP71S05X","lsc-benchmarks",null,"Routes OGB-LSC workflows for PCQM4M, MAG240M, WikiKG90M, and submission helpers.","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\u002Flsc-benchmarks\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: lsc-benchmarks\ndescription: \"Routes OGB-LSC workflows for PCQM4M, MAG240M, WikiKG90M, and\n  submission helpers.\"\nmetadata:\n  disco-role: operating\ndisable-model-invocation: true\nlicense: MIT\n---\n\n# LSC Benchmarks\n\nUse this subskill for the OGB-LSC family: `PCQM4M`, `PCQM4Mv2`, `MAG240M`,\n`WikiKG90M`, `WikiKG90Mv2`, submission files, and evaluator smoke checks.\n\n## Use this subskill when\n\n- The task names `PCQM4M`, `PCQM4Mv2`, `MAG240M`, `WikiKG90M`,\n  `WikiKG90Mv2`, or `OGB-LSC`.\n- The task asks for `test-dev`, `test-challenge`, submission filenames, or\n  evaluator-specific smoke checks.\n- The task mentions `only_smiles`, `to_pyg_hetero_data`, `split_test`, or\n  checkpointed inference helpers.\n\n## First decisions\n\n1. Read [`references\u002Fworkflows.md`](references\u002Fworkflows.md) for the dataset\n   families and the main execution flow.\n2. Read [`references\u002Fapi-reference.md`](references\u002Fapi-reference.md) for the\n   public class names and evaluator expectations.\n3. Read [`references\u002Fsubmission.md`](references\u002Fsubmission.md) when the task is\n   about output filenames or submission shapes.\n4. Read [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) when a\n   dataset is deprecated, a checkpoint is missing, or a shape assertion fails.\n5. If you only need to verify evaluator shapes without downloading a dataset,\n   run [`scripts\u002Flsc-smoke.py`](scripts\u002Flsc-smoke.py).\n\n## Main workflow\n\n- Decide which LSC dataset family the request targets.\n- Check whether the request is a data-loading task, an evaluator task, or a\n  submission-format task.\n- Use `only_smiles=True` when you only need the molecular strings for the\n  PCQM4M family.\n- Use `to_pyg_hetero_data()` when you need a PyG hetero representation for\n  `MAG240M`.\n- Treat `WikiKG90M` as deprecated and prefer the `v2` workflow for new work.\n\n## Common routing choices\n\n- `PCQM4M` \u002F `PCQM4Mv2` -> molecular regression and submission helpers.\n- `MAG240M` -> large heterogeneous node classification.\n- `WikiKG90M` \u002F `WikiKG90Mv2` -> knowledge-graph completion and top-10\n  submission arrays.\n\n## Optional backend note\n\nThe LSC examples may rely on PyG, DGL, or external frameworks such as\nDGL-KE\u002FSMORE. Those are optional or external to the core OGB package. If they\nare missing, keep the workflow to the core dataset and evaluator surface unless\nthose extras are explicitly requested.\n\n## What not to do here\n\n- Do not run the full heavyweight benchmark training loops as the runtime\n  answer.\n- Do not treat `PCQM4M` or `WikiKG90M` as preferred starting points for new\n  work.\n- Do not depend on the source checkout for the final skill content.\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","# LSC Benchmarks\n\nUse this subskill for the OGB-LSC family: `PCQM4M`, `PCQM4Mv2`, `MAG240M`,\n`WikiKG90M`, `WikiKG90Mv2`, submission files, and evaluator smoke checks.\n\n## Use this subskill when\n\n- The task names `PCQM4M`, `PCQM4Mv2`, `MAG240M`, `WikiKG90M`,\n  `WikiKG90Mv2`, or `OGB-LSC`.\n- The task asks for `test-dev`, `test-challenge`, submission filenames, or\n  evaluator-specific smoke checks.\n- The task mentions `only_smiles`, `to_pyg_hetero_data`, `split_test`, or\n  checkpointed inference helpers.\n\n## First decisions\n\n1. Read [`references\u002Fworkflows.md`](references\u002Fworkflows.md) for the dataset\n   families and the main execution flow.\n2. Read [`references\u002Fapi-reference.md`](references\u002Fapi-reference.md) for the\n   public class names and evaluator expectations.\n3. Read [`references\u002Fsubmission.md`](references\u002Fsubmission.md) when the task is\n   about output filenames or submission shapes.\n4. Read [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) when a\n   dataset is deprecated, a checkpoint is missing, or a shape assertion fails.\n5. If you only need to verify evaluator shapes without downloading a dataset,\n   run [`scripts\u002Flsc-smoke.py`](scripts\u002Flsc-smoke.py).\n\n## Main workflow\n\n- Decide which LSC dataset family the request targets.\n- Check whether the request is a data-loading task, an evaluator task, or a\n  submission-format task.\n- Use `only_smiles=True` when you only need the molecular strings for the\n  PCQM4M family.\n- Use `to_pyg_hetero_data()` when you need a PyG hetero representation for\n  `MAG240M`.\n- Treat `WikiKG90M` as deprecated and prefer the `v2` workflow for new work.\n\n## Common routing choices\n\n- `PCQM4M` \u002F `PCQM4Mv2` -> molecular regression and submission helpers.\n- `MAG240M` -> large heterogeneous node classification.\n- `WikiKG90M` \u002F `WikiKG90Mv2` -> knowledge-graph completion and top-10\n  submission arrays.\n\n## Optional backend note\n\nThe LSC examples may rely on PyG, DGL, or external frameworks such as\nDGL-KE\u002FSMORE. Those are optional or external to the core OGB package. If they\nare missing, keep the workflow to the core dataset and evaluator surface unless\nthose extras are explicitly requested.\n\n## What not to do here\n\n- Do not run the full heavyweight benchmark training loops as the runtime\n  answer.\n- Do not treat `PCQM4M` or `WikiKG90M` as preferred starting points for new\n  work.\n- Do not depend on the source checkout for the final skill content.\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\u002Flsc-benchmarks",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 lsc-benchmarks",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill lsc-benchmarks",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill lsc-benchmarks","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fogb\u002Fsub-skills\u002Flsc-benchmarks\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",1202,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fogb\u002Fsub-skills\u002Flsc-benchmarks\u002Freferences\u002Fapi-reference.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fsubmission.md",882,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fogb\u002Fsub-skills\u002Flsc-benchmarks\u002Freferences\u002Fsubmission.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Ftroubleshooting.md",954,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fogb\u002Fsub-skills\u002Flsc-benchmarks\u002Freferences\u002Ftroubleshooting.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Fworkflows.md",1346,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fogb\u002Fsub-skills\u002Flsc-benchmarks\u002Freferences\u002Fworkflows.md",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Flsc-smoke.py","SCRIPT","脚本",1098,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fogb\u002Fsub-skills\u002Flsc-benchmarks\u002Fscripts\u002Flsc-smoke.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",[],[]]