[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78XR5RMAASC2KJ32HKY6X09":3,"skill-same:01M78XR5RMAASC2KJ32HKY6X09":74},{"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},"01M78XR5RMAASC2KJ32HKY6X09","graphormer",null,"Routes Graphormer users to fairseq training, dataset customization, pretrained evaluation, model extension, and DiG workflows.","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\u002Fgraphormer\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: graphormer\ndescription: \"Routes Graphormer users to fairseq training, dataset\n  customization, pretrained evaluation, model extension, and DiG workflows.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Graphormer\n\nGraphormer is a fairseq user-dir graph learning package for molecular modeling,\nmaterials-style structure tasks, and a small set of research-only DiG\nworkflows. Use this skill when the task mentions Graphormer, Graphormer3D,\nfairseq `--user-dir`, ZINC, PCQM4M, MolHIV, OC20, IS2RE, catalyst adsorption,\nprotein conformation sampling, protein-ligand diffusion, custom Graphormer\ndatasets, or Graphormer pretrained checkpoints.\n\nThis skill is a router, not a monolithic manual. Start with the most specific\nsub-skill that matches the workflow, then read the nearest bundled reference or\nhelper script.\n\n## Start here\n\n- [Installation and environment](references\u002Finstallation-and-environment.md)\n- [Cross-cutting troubleshooting](references\u002Ftroubleshooting.md)\n- [Source script map](references\u002Fsource-script-map.md)\n- [Repository provenance](references\u002Frepo-provenance.md)\n- [Environment check](scripts\u002Fcheck_graphormer_environment.py)\n\n## Route map\n\n- [fairseq-training](sub-skills\u002Ffairseq-training\u002FSKILL.md): Graphormer property-prediction and Graphormer3D training command templates for ZINC, PCQM4M, MolHIV FLAG, and OC20\u002FIS2RE.\n- [datasets-and-customization](sub-skills\u002Fdatasets-and-customization\u002FSKILL.md): built-in dataset selection, custom dataset registration, preprocessing, and batch-schema validation.\n- [pretrained-and-evaluation](sub-skills\u002Fpretrained-and-evaluation\u002FSKILL.md): pretrained checkpoint selection, fine-tuning, and evaluation.\n- [model-extension](sub-skills\u002Fmodel-extension\u002FSKILL.md): Graphormer fairseq registries, model\u002Ftask\u002Fcriterion wiring, and extension recipes.\n- [distributional-graphormer](sub-skills\u002Fdistributional-graphormer\u002FSKILL.md): optional DiG catalyst, property-guided, protein, and protein-ligand workflows.\n\n## Minimal environment check\n\nIf you only want to confirm that a Graphormer-compatible environment is ready,\nrun the bundled checker from a shell that can see the target environment:\n\n```bash\npython scripts\u002Fcheck_graphormer_environment.py --user-dir \u003Cgraphormer-package-dir> --format text\n```\n\nAdd `--require-complete` when you want the script to confirm the expected\nGraphormer model, task, criterion, and architecture registries. Add\n`--require-cuda` on a CUDA host when you also want a tiny device smoke check.\n\n## What this skill assumes\n\n- Graphormer is loaded through fairseq's `--user-dir` mechanism.\n- The user-dir points at the directory that contains Graphormer's `models\u002F`,\n  `tasks\u002F`, and `criterions\u002F` packages.\n- Full native training, dataset download, checkpoint download, or DiG runs are\n  optional and should be handled by a Researcher session only when the required\n  data, hardware, and time budget are available.\n\n## How to choose a sub-skill\n\n- Need a training command: start with `fairseq-training`.\n- Need to select a dataset or validate a custom data module: start with\n  `datasets-and-customization`.\n- Need to load a checkpoint or compare evaluation metrics: start with\n  `pretrained-and-evaluation`.\n- Need to add or inspect a registered model\u002Ftask\u002Fcriterion\u002Farchitecture:\n  start with `model-extension`.\n- Need the DiG catalyst, protein, or protein-ligand research code: start with\n  `distributional-graphormer`.\n\n## When to read provenance\n\nRead [Repository provenance](references\u002Frepo-provenance.md) before treating this\nskill as current or before refreshing it against a newer Graphormer checkout.\n","# Graphormer\n\nGraphormer is a fairseq user-dir graph learning package for molecular modeling,\nmaterials-style structure tasks, and a small set of research-only DiG\nworkflows. Use this skill when the task mentions Graphormer, Graphormer3D,\nfairseq `--user-dir`, ZINC, PCQM4M, MolHIV, OC20, IS2RE, catalyst adsorption,\nprotein conformation sampling, protein-ligand diffusion, custom Graphormer\ndatasets, or Graphormer pretrained checkpoints.\n\nThis skill is a router, not a monolithic manual. Start with the most specific\nsub-skill that matches the workflow, then read the nearest bundled reference or\nhelper script.\n\n## Start here\n\n- [Installation and environment](references\u002Finstallation-and-environment.md)\n- [Cross-cutting troubleshooting](references\u002Ftroubleshooting.md)\n- [Source script map](references\u002Fsource-script-map.md)\n- [Repository provenance](references\u002Frepo-provenance.md)\n- [Environment check](scripts\u002Fcheck_graphormer_environment.py)\n\n## Route map\n\n- [fairseq-training](sub-skills\u002Ffairseq-training\u002FSKILL.md): Graphormer property-prediction and Graphormer3D training command templates for ZINC, PCQM4M, MolHIV FLAG, and OC20\u002FIS2RE.\n- [datasets-and-customization](sub-skills\u002Fdatasets-and-customization\u002FSKILL.md): built-in dataset selection, custom dataset registration, preprocessing, and batch-schema validation.\n- [pretrained-and-evaluation](sub-skills\u002Fpretrained-and-evaluation\u002FSKILL.md): pretrained checkpoint selection, fine-tuning, and evaluation.\n- [model-extension](sub-skills\u002Fmodel-extension\u002FSKILL.md): Graphormer fairseq registries, model\u002Ftask\u002Fcriterion wiring, and extension recipes.\n- [distributional-graphormer](sub-skills\u002Fdistributional-graphormer\u002FSKILL.md): optional DiG catalyst, property-guided, protein, and protein-ligand workflows.\n\n## Minimal environment check\n\nIf you only want to confirm that a Graphormer-compatible environment is ready,\nrun the bundled checker from a shell that can see the target environment:\n\n```bash\npython scripts\u002Fcheck_graphormer_environment.py --user-dir \u003Cgraphormer-package-dir> --format text\n```\n\nAdd `--require-complete` when you want the script to confirm the expected\nGraphormer model, task, criterion, and architecture registries. Add\n`--require-cuda` on a CUDA host when you also want a tiny device smoke check.\n\n## What this skill assumes\n\n- Graphormer is loaded through fairseq's `--user-dir` mechanism.\n- The user-dir points at the directory that contains Graphormer's `models\u002F`,\n  `tasks\u002F`, and `criterions\u002F` packages.\n- Full native training, dataset download, checkpoint download, or DiG runs are\n  optional and should be handled by a Researcher session only when the required\n  data, hardware, and time budget are available.\n\n## How to choose a sub-skill\n\n- Need a training command: start with `fairseq-training`.\n- Need to select a dataset or validate a custom data module: start with\n  `datasets-and-customization`.\n- Need to load a checkpoint or compare evaluation metrics: start with\n  `pretrained-and-evaluation`.\n- Need to add or inspect a registered model\u002Ftask\u002Fcriterion\u002Farchitecture:\n  start with `model-extension`.\n- Need the DiG catalyst, protein, or protein-ligand research code: start with\n  `distributional-graphormer`.\n\n## When to read provenance\n\nRead [Repository provenance](references\u002Frepo-provenance.md) before treating this\nskill as current or before refreshing it against a newer Graphormer checkout.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fgraphormer",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 graphormer",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill graphormer",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill graphormer","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgraphormer\u002FSKILL.md",[46,52,56,60,64,68],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Finstallation-and-environment.md","REFERENCE","参考文档",3502,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgraphormer\u002Freferences\u002Finstallation-and-environment.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Frepo-provenance.md",1778,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgraphormer\u002Freferences\u002Frepo-provenance.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Frepo-routing-metadata.json",501,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgraphormer\u002Freferences\u002Frepo-routing-metadata.json",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Fsource-script-map.md",3736,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgraphormer\u002Freferences\u002Fsource-script-map.md",{"path":65,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Ftroubleshooting.md",4707,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgraphormer\u002Freferences\u002Ftroubleshooting.md",{"path":69,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":72,"sourceHtmlUrl":73},"scripts\u002Fcheck_graphormer_environment.py","SCRIPT","脚本",12402,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgraphormer\u002Fscripts\u002Fcheck_graphormer_environment.py",[75,83,90,97,104,111],{"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":79,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"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":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"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":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"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":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"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":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"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":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"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",[],[]]