[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M796CH0H1QQ2735FS5ZST2SV":3,"skill-same:01M796CH0H1QQ2735FS5ZST2SV":67},{"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},"01M796CH0H1QQ2735FS5ZST2SV","torchdrug",null,"Route TorchDrug graph learning, drug discovery, molecular ML, protein, knowledge graph, data, model, and training engine 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\u002Ftorchdrug\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: torchdrug\ndescription: \"Route TorchDrug graph learning, drug discovery, molecular ML,\n  protein, knowledge graph, data, model, and training engine workflows.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# TorchDrug\n\nUse this repo skill when a task involves TorchDrug, TorchProtein, graph neural networks for drug discovery, molecular property prediction, molecular generation, retrosynthesis, protein workflows, knowledge graph completion, or TorchDrug's `core.Engine` training stack.\n\n## Start Here\n\n- Read [references\u002Frepo-provenance.md](references\u002Frepo-provenance.md) before deciding whether this skill is current for a TorchDrug checkout or package version.\n- Read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) for install\u002Fimport, PyTorch\u002FPyG compiled packages, RDKit, data downloads, GPU, `mps`, and package-version pitfalls.\n- Run `python scripts\u002Fcheck_torchdrug_env.py` in the user's TorchDrug environment for a no-download import and capability check.\n\n## Install And Verify\n\nTorchDrug 0.2.1 supports Python `>=3.7,\u003C3.11` and PyTorch `>=1.8.0`. Prefer a fresh environment with Python 3.10 or earlier:\n\n```bash\npython -m pip install torchdrug\npython - \u003C\u003C'PY'\nimport torchdrug\nfrom torchdrug import data\nprint(torchdrug.__version__)\ngraph = data.Graph([[0, 1], [1, 0]], num_node=2)\nprint(graph.num_node, graph.num_edge)\nPY\n```\n\nWhen installing from pip, install PyTorch first, then choose `torch-scatter` and `torch-cluster` wheels that match the PyTorch and CUDA\u002FCPU build. Conda users can prefer the documented conda channels because they solve PyTorch, PyG, RDKit, and compiled packages together.\n\n## Route By Task\n\n| User task | Read |\n| --- | --- |\n| Graph, molecule, protein, dataset, SMILES, sequence, packing, masking, splitting, collator, or data validation tasks | [sub-skills\u002Fgraph-data\u002FSKILL.md](sub-skills\u002Fgraph-data\u002FSKILL.md) |\n| Choosing or customizing graph layers, representation models, readouts, samplers, variadic tensor utilities, or `MessagePassingBase` subclasses | [sub-skills\u002Flayers-and-extensions\u002FSKILL.md](sub-skills\u002Flayers-and-extensions\u002FSKILL.md) |\n| Building `core.Engine` loops, checkpointing, config serialization, logging, CPU\u002FGPU settings, task contracts, or training harnesses | [sub-skills\u002Ftraining-engine\u002FSKILL.md](sub-skills\u002Ftraining-engine\u002FSKILL.md) |\n| Molecular property prediction, molecular pretraining, generation with GCPN\u002FGraphAF, or USPTO50k retrosynthesis | [sub-skills\u002Fmolecular-workflows\u002FSKILL.md](sub-skills\u002Fmolecular-workflows\u002FSKILL.md) |\n| Knowledge graph triples, FB15k\u002FWN18\u002FYAGO\u002FHetionet, TransE\u002FRotatE\u002FNeuralLP\u002FKBGAT, negative sampling, or filtered ranking | [sub-skills\u002Fknowledge-graphs\u002FSKILL.md](sub-skills\u002Fknowledge-graphs\u002FSKILL.md) |\n| Protein sequences\u002Fstructures, contact prediction, GearNet, ESM, protein property\u002Ffunction, or protein-protein interaction workflows | [sub-skills\u002Fprotein-workflows\u002FSKILL.md](sub-skills\u002Fprotein-workflows\u002FSKILL.md) |\n\n## Common Workflows\n\n- For a tiny in-memory smoke test, route to `graph-data` and run its `scripts\u002Fsmoke_graph_data.py` helper.\n- For a new molecular prediction project, combine `graph-data` for the molecule dataset, `molecular-workflows` for task\u002Fmodel choices, and `training-engine` for `core.Engine` save\u002Fload.\n- For custom graph neural layers, use `layers-and-extensions` first, then return to `training-engine` to wire the module into a task.\n- For protein GearNet or ESM tasks, use `protein-workflows` for data\u002Fmodel\u002Ftask choices and `layers-and-extensions` only for graph construction internals.\n- For knowledge graph reasoning, use `knowledge-graphs` for model\u002Ftask\u002Fdataset decisions and `training-engine` for optimizer, evaluation, and checkpoint details.\n\n## Safety Boundaries\n\n- Do not run dataset downloads, long training, retrosynthesis generation, benchmark sweeps, or ESM weight downloads unless the user allows network, storage, and compute cost.\n- Do not assume `gpus=[0]` is valid. Use `gpus=None` for CPU-only work and check `torch.cuda.is_available()` before GPU examples.\n- Do not use Apple `mps`; TorchDrug documentation says Apple silicon can run on CPU but `mps` is unsupported.\n- Do not tell users to open original TorchDrug docs, tests, or examples as runtime requirements. This skill bundles the needed routes, references, and safe helpers.\n\n## Repository Scope\n\nThis skill covers public TorchDrug package usage and repo-derived workflows: source APIs under `torchdrug\u002F`, install metadata, Sphinx docs, tutorials, benchmarks, and representative tests. It intentionally does not cover maintainer release automation, full benchmark reproduction, or external dataset\u002Fmodel-weight acquisition beyond documented prerequisites.\n","# TorchDrug\n\nUse this repo skill when a task involves TorchDrug, TorchProtein, graph neural networks for drug discovery, molecular property prediction, molecular generation, retrosynthesis, protein workflows, knowledge graph completion, or TorchDrug's `core.Engine` training stack.\n\n## Start Here\n\n- Read [references\u002Frepo-provenance.md](references\u002Frepo-provenance.md) before deciding whether this skill is current for a TorchDrug checkout or package version.\n- Read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) for install\u002Fimport, PyTorch\u002FPyG compiled packages, RDKit, data downloads, GPU, `mps`, and package-version pitfalls.\n- Run `python scripts\u002Fcheck_torchdrug_env.py` in the user's TorchDrug environment for a no-download import and capability check.\n\n## Install And Verify\n\nTorchDrug 0.2.1 supports Python `>=3.7,\u003C3.11` and PyTorch `>=1.8.0`. Prefer a fresh environment with Python 3.10 or earlier:\n\n```bash\npython -m pip install torchdrug\npython - \u003C\u003C'PY'\nimport torchdrug\nfrom torchdrug import data\nprint(torchdrug.__version__)\ngraph = data.Graph([[0, 1], [1, 0]], num_node=2)\nprint(graph.num_node, graph.num_edge)\nPY\n```\n\nWhen installing from pip, install PyTorch first, then choose `torch-scatter` and `torch-cluster` wheels that match the PyTorch and CUDA\u002FCPU build. Conda users can prefer the documented conda channels because they solve PyTorch, PyG, RDKit, and compiled packages together.\n\n## Route By Task\n\n| User task | Read |\n| --- | --- |\n| Graph, molecule, protein, dataset, SMILES, sequence, packing, masking, splitting, collator, or data validation tasks | [sub-skills\u002Fgraph-data\u002FSKILL.md](sub-skills\u002Fgraph-data\u002FSKILL.md) |\n| Choosing or customizing graph layers, representation models, readouts, samplers, variadic tensor utilities, or `MessagePassingBase` subclasses | [sub-skills\u002Flayers-and-extensions\u002FSKILL.md](sub-skills\u002Flayers-and-extensions\u002FSKILL.md) |\n| Building `core.Engine` loops, checkpointing, config serialization, logging, CPU\u002FGPU settings, task contracts, or training harnesses | [sub-skills\u002Ftraining-engine\u002FSKILL.md](sub-skills\u002Ftraining-engine\u002FSKILL.md) |\n| Molecular property prediction, molecular pretraining, generation with GCPN\u002FGraphAF, or USPTO50k retrosynthesis | [sub-skills\u002Fmolecular-workflows\u002FSKILL.md](sub-skills\u002Fmolecular-workflows\u002FSKILL.md) |\n| Knowledge graph triples, FB15k\u002FWN18\u002FYAGO\u002FHetionet, TransE\u002FRotatE\u002FNeuralLP\u002FKBGAT, negative sampling, or filtered ranking | [sub-skills\u002Fknowledge-graphs\u002FSKILL.md](sub-skills\u002Fknowledge-graphs\u002FSKILL.md) |\n| Protein sequences\u002Fstructures, contact prediction, GearNet, ESM, protein property\u002Ffunction, or protein-protein interaction workflows | [sub-skills\u002Fprotein-workflows\u002FSKILL.md](sub-skills\u002Fprotein-workflows\u002FSKILL.md) |\n\n## Common Workflows\n\n- For a tiny in-memory smoke test, route to `graph-data` and run its `scripts\u002Fsmoke_graph_data.py` helper.\n- For a new molecular prediction project, combine `graph-data` for the molecule dataset, `molecular-workflows` for task\u002Fmodel choices, and `training-engine` for `core.Engine` save\u002Fload.\n- For custom graph neural layers, use `layers-and-extensions` first, then return to `training-engine` to wire the module into a task.\n- For protein GearNet or ESM tasks, use `protein-workflows` for data\u002Fmodel\u002Ftask choices and `layers-and-extensions` only for graph construction internals.\n- For knowledge graph reasoning, use `knowledge-graphs` for model\u002Ftask\u002Fdataset decisions and `training-engine` for optimizer, evaluation, and checkpoint details.\n\n## Safety Boundaries\n\n- Do not run dataset downloads, long training, retrosynthesis generation, benchmark sweeps, or ESM weight downloads unless the user allows network, storage, and compute cost.\n- Do not assume `gpus=[0]` is valid. Use `gpus=None` for CPU-only work and check `torch.cuda.is_available()` before GPU examples.\n- Do not use Apple `mps`; TorchDrug documentation says Apple silicon can run on CPU but `mps` is unsupported.\n- Do not tell users to open original TorchDrug docs, tests, or examples as runtime requirements. This skill bundles the needed routes, references, and safe helpers.\n\n## Repository Scope\n\nThis skill covers public TorchDrug package usage and repo-derived workflows: source APIs under `torchdrug\u002F`, install metadata, Sphinx docs, tutorials, benchmarks, and representative tests. It intentionally does not cover maintainer release automation, full benchmark reproduction, or external dataset\u002Fmodel-weight acquisition beyond documented prerequisites.\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\u002Ftorchdrug",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 torchdrug",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill torchdrug",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill torchdrug","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftorchdrug\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Frepo-provenance.md","REFERENCE","参考文档",1588,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftorchdrug\u002Freferences\u002Frepo-provenance.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Frepo-routing-metadata.json",496,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftorchdrug\u002Freferences\u002Frepo-routing-metadata.json",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",3783,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftorchdrug\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fcheck_torchdrug_env.py","SCRIPT","脚本",1777,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftorchdrug\u002Fscripts\u002Fcheck_torchdrug_env.py",[68,75,82,89,96,103],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"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":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"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":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"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":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"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":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"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":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"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",[],[]]