[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78SH7DM4GX88DFBFXYG7TG9":3,"skill-same:01M78SH7DM4GX88DFBFXYG7TG9":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},"01M78SH7DM4GX88DFBFXYG7TG9","alphafold2",null,"Guide alphafold2-pytorch protein sequence, MSA, distogram, angle-logit, coordinate-refinement, recycling, embedding, and structure-utility workflows with version-aware troubleshooting.","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\u002Falphafold2\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: alphafold2\ndescription: \"Guide alphafold2-pytorch protein sequence, MSA, distogram,\n  angle-logit, coordinate-refinement, recycling, embedding, and\n  structure-utility workflows with version-aware troubleshooting.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# alphafold2-pytorch\n\nUse this skill when a task names `alphafold2-pytorch`, `alphafold2_pytorch`,\n`Alphafold2`, `Evoformer`, protein sequence\u002FMSA folding, distograms, angle\nlogits, residue coordinates, ESM\u002FMSA\u002FProtTrans embeddings, recycling, MDS, or\nprotein-structure metrics.\n\nThis graph targets the unofficial PyTorch implementation at distribution\nversion `0.4.32`. It is not the official DeepMind AlphaFold2 implementation.\nIts current source and README disagree in several places; prefer the verified\ncurrent API described by the linked sub-skills over older README recipes.\n\n## Install and inspect\n\nInstall the public distribution, then verify the import before building a\nmodel:\n\n```bash\npython -m pip install alphafold2-pytorch==0.4.32\npython -c \"import alphafold2_pytorch; print(alphafold2_pytorch.Alphafold2)\"\n```\n\nCoordinate and utility paths also need the scientific and geometric\nrequirements declared by the distribution, including a mutually compatible\nPyTorch\u002FPyTorch3D pair, `invariant-point-attention`, `sidechainnet`,\n`mdtraj`, `ProDy`, `mp-nerf`, and OpenMM where the selected helper imports it.\nUse [the environment checker](scripts\u002Fcheck_environment.py) for a read-only\nsummary; use [cross-cutting troubleshooting](references\u002Ftroubleshooting.md)\nwhen dependency resolution selects an incompatible backend.\n\n## Route by task\n\n- **Core sequence\u002FMSA trunk, Evoformer, distograms, angle logits, masks,\n  templates, and current constructor\u002Fforward contracts:** read\n  [core-model](sub-skills\u002Fcore-model\u002FSKILL.md).\n- **Residue coordinates, invariant-point refinement, confidence, auxiliary\n  returns, and recycling:** read\n  [structure-and-recycling](sub-skills\u002Fstructure-and-recycling\u002FSKILL.md).\n- **ESM, MSA Transformer, ProtTrans wrappers or safe precomputed\n  representations:** read [embeddings](sub-skills\u002Fembeddings\u002FSKILL.md).\n- **Distogram-to-distance conversion, MDS, atom masks, sidechain layouts,\n  Kabsch, LDDT, GDT, TM-score, and distance losses:** read\n  [utilities](sub-skills\u002Futilities\u002FSKILL.md).\n\nStart with the owning sub-skill, then follow its API reference and\ntroubleshooting file. Cross-links are deliberate: do not duplicate a sibling's\nfull API table in the root router.\n\n## Operating constraints\n\n- Use tiny synthetic tensors first. The model is quadratic in sequence length\n  for several trunk operations, and untrained outputs are not scientific\n  structure predictions.\n- At this version, normal MSA input has shape `(B, M, N)` with the same residue\n  width `N` as `seq`; masks should be boolean and on the same device.\n- CPU is the default verification backend. CUDA is an optional acceleration\n  path and must be checked on the actual host; a visible CUDA installation is\n  not proof that a shared device has enough memory.\n- Pretrained embedding wrappers may download code or weights and may require\n  caches, network access, Hugging Face\u002Ftorch.hub support, or fused operations.\n  Do not trigger those side effects without explicit approval.\n- Full training, multi-terabyte MSA acquisition, DeepSpeed sparse attention,\n  PyRosetta relaxation, and notebook-scale experiments are intentionally not\n  part of this runtime graph. See [limitations](references\u002Flimitations.md).\n\n## Provenance and refresh\n\nRead [repository provenance](references\u002Frepo-provenance.md) before treating\nthis graph as current for another checkout. Refresh it when the commit,\npackage version, public signatures, or evidence paths change. The generated\nruntime graph is self-contained and does not require the source checkout to\nremain available.\n","# alphafold2-pytorch\n\nUse this skill when a task names `alphafold2-pytorch`, `alphafold2_pytorch`,\n`Alphafold2`, `Evoformer`, protein sequence\u002FMSA folding, distograms, angle\nlogits, residue coordinates, ESM\u002FMSA\u002FProtTrans embeddings, recycling, MDS, or\nprotein-structure metrics.\n\nThis graph targets the unofficial PyTorch implementation at distribution\nversion `0.4.32`. It is not the official DeepMind AlphaFold2 implementation.\nIts current source and README disagree in several places; prefer the verified\ncurrent API described by the linked sub-skills over older README recipes.\n\n## Install and inspect\n\nInstall the public distribution, then verify the import before building a\nmodel:\n\n```bash\npython -m pip install alphafold2-pytorch==0.4.32\npython -c \"import alphafold2_pytorch; print(alphafold2_pytorch.Alphafold2)\"\n```\n\nCoordinate and utility paths also need the scientific and geometric\nrequirements declared by the distribution, including a mutually compatible\nPyTorch\u002FPyTorch3D pair, `invariant-point-attention`, `sidechainnet`,\n`mdtraj`, `ProDy`, `mp-nerf`, and OpenMM where the selected helper imports it.\nUse [the environment checker](scripts\u002Fcheck_environment.py) for a read-only\nsummary; use [cross-cutting troubleshooting](references\u002Ftroubleshooting.md)\nwhen dependency resolution selects an incompatible backend.\n\n## Route by task\n\n- **Core sequence\u002FMSA trunk, Evoformer, distograms, angle logits, masks,\n  templates, and current constructor\u002Fforward contracts:** read\n  [core-model](sub-skills\u002Fcore-model\u002FSKILL.md).\n- **Residue coordinates, invariant-point refinement, confidence, auxiliary\n  returns, and recycling:** read\n  [structure-and-recycling](sub-skills\u002Fstructure-and-recycling\u002FSKILL.md).\n- **ESM, MSA Transformer, ProtTrans wrappers or safe precomputed\n  representations:** read [embeddings](sub-skills\u002Fembeddings\u002FSKILL.md).\n- **Distogram-to-distance conversion, MDS, atom masks, sidechain layouts,\n  Kabsch, LDDT, GDT, TM-score, and distance losses:** read\n  [utilities](sub-skills\u002Futilities\u002FSKILL.md).\n\nStart with the owning sub-skill, then follow its API reference and\ntroubleshooting file. Cross-links are deliberate: do not duplicate a sibling's\nfull API table in the root router.\n\n## Operating constraints\n\n- Use tiny synthetic tensors first. The model is quadratic in sequence length\n  for several trunk operations, and untrained outputs are not scientific\n  structure predictions.\n- At this version, normal MSA input has shape `(B, M, N)` with the same residue\n  width `N` as `seq`; masks should be boolean and on the same device.\n- CPU is the default verification backend. CUDA is an optional acceleration\n  path and must be checked on the actual host; a visible CUDA installation is\n  not proof that a shared device has enough memory.\n- Pretrained embedding wrappers may download code or weights and may require\n  caches, network access, Hugging Face\u002Ftorch.hub support, or fused operations.\n  Do not trigger those side effects without explicit approval.\n- Full training, multi-terabyte MSA acquisition, DeepSpeed sparse attention,\n  PyRosetta relaxation, and notebook-scale experiments are intentionally not\n  part of this runtime graph. See [limitations](references\u002Flimitations.md).\n\n## Provenance and refresh\n\nRead [repository provenance](references\u002Frepo-provenance.md) before treating\nthis graph as current for another checkout. Refresh it when the commit,\npackage version, public signatures, or evidence paths change. The generated\nruntime graph is self-contained and does not require the source checkout to\nremain available.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Falphafold2",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 alphafold2",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill alphafold2",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill alphafold2","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Falphafold2\u002FSKILL.md",[46,52,56,60,64],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Flimitations.md","REFERENCE","参考文档",2022,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Falphafold2\u002Freferences\u002Flimitations.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Frepo-provenance.md",1747,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Falphafold2\u002Freferences\u002Frepo-provenance.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Frepo-routing-metadata.json",328,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Falphafold2\u002Freferences\u002Frepo-routing-metadata.json",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Ftroubleshooting.md",3244,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Falphafold2\u002Freferences\u002Ftroubleshooting.md",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Fcheck_environment.py","SCRIPT","脚本",1575,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Falphafold2\u002Fscripts\u002Fcheck_environment.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",[],[]]