[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78SHBYG3EJWSDF9AZBPN7PH":3,"skill-same:01M78SHBYG3EJWSDF9AZBPN7PH":66},{"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},"01M78SHBYG3EJWSDF9AZBPN7PH","embeddings",null,"Guides ESM, MSA Transformer, ProtTrans\u002FProtBERT, and precomputed sequence\u002FMSA representations for Alphafold2, including projection, masks, caches, downloads, Apex, and OOM diagnosis.","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\u002Fsub-skills\u002Fembeddings\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: embeddings\ndescription: \"Guides ESM, MSA Transformer, ProtTrans\u002FProtBERT, and precomputed\n  sequence\u002FMSA representations for Alphafold2, including projection, masks,\n  caches, downloads, Apex, and OOM diagnosis.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Embeddings\n\nUse this sub-skill for `ESMEmbedWrapper`, `MSAEmbedWrapper`,\n`ProtTranEmbedWrapper`, external sequence\u002FMSA features, precomputed\nrepresentations, projection-width checks, or failures involving model assets,\n`torch.hub`, Hugging Face, `transformers`, Apex, fused operations, caches, and\nmemory pressure.\n\n## Route the task\n\n- For exact wrapper signatures, tensor contracts, masks, projection rules, and\n  `disable_token_embed`, read [API reference](references\u002Fapi-reference.md).\n- Before constructing any pretrained wrapper, read\n  [External models](references\u002Fexternal-models.md). Construction can resolve\n  code and large weights; never trigger that acquisition without approval.\n- For missing assets, network\u002Fcache errors, source-shape defects, Apex\u002Ffused\n  failures, width mismatch, or OOM, use\n  [Troubleshooting](references\u002Ftroubleshooting.md).\n- For a safe CPU-default check, run\n  [`embedding_input_smoke.py`](scripts\u002Fembedding_input_smoke.py). It creates a\n  synthetic `(B, M, N, 1280)` tensor, checks the core projection, and consumes\n  projected representations without constructing or downloading a pretrained\n  model.\n\n## Operating sequence\n\n1. Decide between a live pretrained wrapper and already available\n   representations. Prefer precomputed inputs when model source, weights,\n   cache, network policy, fused kernels, or memory have not been approved and\n   validated.\n2. Validate `seq: (B, N)`, `msa: (B, M, N)`, boolean masks on the same residue\n   axes, and the external feature width before allocating a model.\n3. Match the external width to the correct projection: wrapper projections end\n   at `Alphafold2.dim`; the core `embedd_project` accepts `num_embedds`\n   channels (1280 by default) and also ends at `Alphafold2.dim`.\n4. Review the 0.4.32 source limitations before relying on a wrapper or on the\n   core argument spelled `embedds`. The README describes the intended workflow,\n   but several wrapper\u002Fhelper paths and the direct `embedds` branch drift from\n   that description.\n5. Run only a bounded, explicit device check. The pretrained wrapper paths are\n   not offline merely because `alphafold2_pytorch` imports successfully.\n\n## Boundaries\n\n- General `Alphafold2` trunk construction, attention, and output contracts:\n  [core-model](..\u002Fcore-model\u002FSKILL.md).\n- Coordinates, confidence, refinement, and recycling:\n  [structure-and-recycling](..\u002Fstructure-and-recycling\u002FSKILL.md).\n- Metrics and unrelated utilities: [utilities](..\u002Futilities\u002FSKILL.md).\n\nA wrapper computes `seq_embed` and `msa_embed` and forwards them to the trunk.\nThe lower-level `embedds` argument is a different interface; in 0.4.32 its\nbranch is shadowed by MSA initialization. Do not describe a successful wrapper\nor functional direct-`embedds` inference unless that exact path was validated.\n","# Embeddings\n\nUse this sub-skill for `ESMEmbedWrapper`, `MSAEmbedWrapper`,\n`ProtTranEmbedWrapper`, external sequence\u002FMSA features, precomputed\nrepresentations, projection-width checks, or failures involving model assets,\n`torch.hub`, Hugging Face, `transformers`, Apex, fused operations, caches, and\nmemory pressure.\n\n## Route the task\n\n- For exact wrapper signatures, tensor contracts, masks, projection rules, and\n  `disable_token_embed`, read [API reference](references\u002Fapi-reference.md).\n- Before constructing any pretrained wrapper, read\n  [External models](references\u002Fexternal-models.md). Construction can resolve\n  code and large weights; never trigger that acquisition without approval.\n- For missing assets, network\u002Fcache errors, source-shape defects, Apex\u002Ffused\n  failures, width mismatch, or OOM, use\n  [Troubleshooting](references\u002Ftroubleshooting.md).\n- For a safe CPU-default check, run\n  [`embedding_input_smoke.py`](scripts\u002Fembedding_input_smoke.py). It creates a\n  synthetic `(B, M, N, 1280)` tensor, checks the core projection, and consumes\n  projected representations without constructing or downloading a pretrained\n  model.\n\n## Operating sequence\n\n1. Decide between a live pretrained wrapper and already available\n   representations. Prefer precomputed inputs when model source, weights,\n   cache, network policy, fused kernels, or memory have not been approved and\n   validated.\n2. Validate `seq: (B, N)`, `msa: (B, M, N)`, boolean masks on the same residue\n   axes, and the external feature width before allocating a model.\n3. Match the external width to the correct projection: wrapper projections end\n   at `Alphafold2.dim`; the core `embedd_project` accepts `num_embedds`\n   channels (1280 by default) and also ends at `Alphafold2.dim`.\n4. Review the 0.4.32 source limitations before relying on a wrapper or on the\n   core argument spelled `embedds`. The README describes the intended workflow,\n   but several wrapper\u002Fhelper paths and the direct `embedds` branch drift from\n   that description.\n5. Run only a bounded, explicit device check. The pretrained wrapper paths are\n   not offline merely because `alphafold2_pytorch` imports successfully.\n\n## Boundaries\n\n- General `Alphafold2` trunk construction, attention, and output contracts:\n  [core-model](..\u002Fcore-model\u002FSKILL.md).\n- Coordinates, confidence, refinement, and recycling:\n  [structure-and-recycling](..\u002Fstructure-and-recycling\u002FSKILL.md).\n- Metrics and unrelated utilities: [utilities](..\u002Futilities\u002FSKILL.md).\n\nA wrapper computes `seq_embed` and `msa_embed` and forwards them to the trunk.\nThe lower-level `embedds` argument is a different interface; in 0.4.32 its\nbranch is shadowed by MSA initialization. Do not describe a successful wrapper\nor functional direct-`embedds` inference unless that exact path was validated.\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\u002Fsub-skills\u002Fembeddings",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 embeddings",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill embeddings",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill embeddings","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Falphafold2\u002Fsub-skills\u002Fembeddings\u002FSKILL.md",[46,52,56,60],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fapi-reference.md","REFERENCE","参考文档",8505,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Falphafold2\u002Fsub-skills\u002Fembeddings\u002Freferences\u002Fapi-reference.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fexternal-models.md",6766,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Falphafold2\u002Fsub-skills\u002Fembeddings\u002Freferences\u002Fexternal-models.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Ftroubleshooting.md",7173,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Falphafold2\u002Fsub-skills\u002Fembeddings\u002Freferences\u002Ftroubleshooting.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Fembedding_input_smoke.py","SCRIPT","脚本",5127,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Falphafold2\u002Fsub-skills\u002Fembeddings\u002Fscripts\u002Fembedding_input_smoke.py",[67,75,82,89,96,103],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"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.","Apache-2.0","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":71,"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":71,"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":71,"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":71,"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":71,"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",[],[]]