[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78TMA8T2X7GHJQF8THG397P":3,"skill-same:01M78TMA8T2X7GHJQF8THG397P":71},{"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},"01M78TMA8T2X7GHJQF8THG397P","msa-templates",null,"Prepare and validate Chai MSA and template inputs from aligned parquet, A3M, ColabFold server, m8, and staged ColabFold outputs.","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\u002Fchai-lab\u002Fsub-skills\u002Fmsa-templates\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: msa-templates\ndescription: \"Prepare and validate Chai MSA and template inputs from aligned\n  parquet, A3M, ColabFold server, m8, and staged ColabFold outputs.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# MSA Templates\n\nUse this sub-skill when a Chai task involves evolutionary alignments, `.aligned.pqt` files, A3M conversion, ColabFold MSA\u002Ftemplate servers, template hit `.m8` files, or reusing staged ColabFold outputs.\n\n## Route\n\n- For local MSAs, read `references\u002Fmsa-template-workflows.md` and validate each `.aligned.pqt` with `scripts\u002Fvalidate_aligned_pqt.py` before folding.\n- For A3M inputs, use `chai-lab a3m-to-pqt` for one query sequence per directory, then validate the generated filename and query row.\n- For server MSAs\u002Ftemplates, prefer explicit `--use-msa-server` and `--use-templates-server` only when network calls to the ColabFold service are acceptable.\n- For local templates, prepare a BLAST m8-style table and use `--template-hits-path`; use `CHAI_TEMPLATE_CIF_FOLDER` when template CIFs are custom or pre-cached.\n- For existing ColabFold output trees, run `scripts\u002Fstage_colabfold_outputs.py` to create Chai-ready FASTA, `msas\u002F*.aligned.pqt`, and `all_template_hits.m8` files.\n\n## Primary References\n\n- `references\u002Fmsa-template-workflows.md` covers local MSA preparation, A3M conversion, server-side generation, template inputs, and ColabFold staging.\n- `references\u002Fapi-reference.md` lists CLI\u002FAPI entry points, `.aligned.pqt` schema details, m8 columns, and mutual-exclusion rules.\n- `references\u002Ftroubleshooting.md` maps common MSA\u002Ftemplate symptoms to concrete validation and recovery steps.\n\n## Bundled Scripts\n\n- `scripts\u002Fvalidate_aligned_pqt.py --help` checks required parquet columns, strict source values, query-row placement, aligned lengths, and Chai filename hashes without running inference.\n- `scripts\u002Fstage_colabfold_outputs.py --help` adapts ColabFold output folders into a Chai-ready local input tree without calling any network service.\n\n## Boundaries\n\n- Use `..\u002Fcli-inference\u002FSKILL.md` for full `chai-lab fold` execution, GPU\u002Fruntime settings, ranking outputs, and `run_inference` result handling.\n- Use `..\u002Finput-data-formats\u002FSKILL.md` for FASTA entity syntax, entity names, and chain naming before matching local m8 query IDs.\n- Use `..\u002Frestraints-glycans\u002FSKILL.md` for contact, pocket, covalent, or glycan restraint files.\n","# MSA Templates\n\nUse this sub-skill when a Chai task involves evolutionary alignments, `.aligned.pqt` files, A3M conversion, ColabFold MSA\u002Ftemplate servers, template hit `.m8` files, or reusing staged ColabFold outputs.\n\n## Route\n\n- For local MSAs, read `references\u002Fmsa-template-workflows.md` and validate each `.aligned.pqt` with `scripts\u002Fvalidate_aligned_pqt.py` before folding.\n- For A3M inputs, use `chai-lab a3m-to-pqt` for one query sequence per directory, then validate the generated filename and query row.\n- For server MSAs\u002Ftemplates, prefer explicit `--use-msa-server` and `--use-templates-server` only when network calls to the ColabFold service are acceptable.\n- For local templates, prepare a BLAST m8-style table and use `--template-hits-path`; use `CHAI_TEMPLATE_CIF_FOLDER` when template CIFs are custom or pre-cached.\n- For existing ColabFold output trees, run `scripts\u002Fstage_colabfold_outputs.py` to create Chai-ready FASTA, `msas\u002F*.aligned.pqt`, and `all_template_hits.m8` files.\n\n## Primary References\n\n- `references\u002Fmsa-template-workflows.md` covers local MSA preparation, A3M conversion, server-side generation, template inputs, and ColabFold staging.\n- `references\u002Fapi-reference.md` lists CLI\u002FAPI entry points, `.aligned.pqt` schema details, m8 columns, and mutual-exclusion rules.\n- `references\u002Ftroubleshooting.md` maps common MSA\u002Ftemplate symptoms to concrete validation and recovery steps.\n\n## Bundled Scripts\n\n- `scripts\u002Fvalidate_aligned_pqt.py --help` checks required parquet columns, strict source values, query-row placement, aligned lengths, and Chai filename hashes without running inference.\n- `scripts\u002Fstage_colabfold_outputs.py --help` adapts ColabFold output folders into a Chai-ready local input tree without calling any network service.\n\n## Boundaries\n\n- Use `..\u002Fcli-inference\u002FSKILL.md` for full `chai-lab fold` execution, GPU\u002Fruntime settings, ranking outputs, and `run_inference` result handling.\n- Use `..\u002Finput-data-formats\u002FSKILL.md` for FASTA entity syntax, entity names, and chain naming before matching local m8 query IDs.\n- Use `..\u002Frestraints-glycans\u002FSKILL.md` for contact, pocket, covalent, or glycan restraint files.\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\u002Fchai-lab\u002Fsub-skills\u002Fmsa-templates",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 msa-templates",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill msa-templates",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill msa-templates","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fchai-lab\u002Fsub-skills\u002Fmsa-templates\u002FSKILL.md",[47,53,57,61,67],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fapi-reference.md","REFERENCE","参考文档",7369,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fchai-lab\u002Fsub-skills\u002Fmsa-templates\u002Freferences\u002Fapi-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fmsa-template-workflows.md",9178,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fchai-lab\u002Fsub-skills\u002Fmsa-templates\u002Freferences\u002Fmsa-template-workflows.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",8615,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fchai-lab\u002Fsub-skills\u002Fmsa-templates\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fstage_colabfold_outputs.py","SCRIPT","脚本",14453,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fchai-lab\u002Fsub-skills\u002Fmsa-templates\u002Fscripts\u002Fstage_colabfold_outputs.py",{"path":68,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Fvalidate_aligned_pqt.py",9290,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fchai-lab\u002Fsub-skills\u002Fmsa-templates\u002Fscripts\u002Fvalidate_aligned_pqt.py",[72,79,86,93,100,107],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"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.","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":14,"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":14,"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":14,"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":14,"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":14,"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",[],[]]