[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78TM1DFHYS05T6JWWDBT3B8":3,"skill-same:01M78TM1DFHYS05T6JWWDBT3B8":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},"01M78TM1DFHYS05T6JWWDBT3B8","chai-lab",null,"Use Chai Lab \u002F Chai-1 for molecular structure prediction, input preparation, MSA\u002Ftemplate setup, restraints, glycans, and repo-specific troubleshooting.","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\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: chai-lab\ndescription: \"Use Chai Lab \u002F Chai-1 for molecular structure prediction, input\n  preparation, MSA\u002Ftemplate setup, restraints, glycans, and repo-specific\n  troubleshooting.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Chai Lab Repo Skill\n\nUse this skill when a task mentions Chai Lab, Chai-1, `chai_lab`, `chai-lab fold`, molecular structure prediction, protein\u002Fligand\u002FDNA\u002FRNA\u002Fglycan complexes, MSA\u002Ftemplate setup, or Chai restraint files.\n\n## Start Here\n\n1. Check package availability with `scripts\u002Fcheck_chai_lab_environment.py --help`, then run the checks that are safe for the target machine.\n2. Read `references\u002Ftroubleshooting.md` if install\u002Fimport, CUDA, model download, network server, or output-directory failures are likely.\n3. Read `references\u002Frepo-provenance.md` before refreshing this skill against a newer checkout.\n4. Route to one focused sub-skill rather than trying to keep all Chai details in the root context.\n\n## Sub-Skill Routing\n\n- `sub-skills\u002Fcli-inference\u002FSKILL.md`: run or template `chai-lab fold`, call `chai_lab.chai1.run_inference`, inspect `StructureCandidates`, tune sample\u002Frecycle\u002Fdevice options, and debug inference runtime failures.\n- `sub-skills\u002Finput-data-formats\u002FSKILL.md`: author and validate Chai FASTA records for proteins, ligands, DNA, RNA, modified residues, glycan headers, entity names, and chain-name mode decisions.\n- `sub-skills\u002Fmsa-templates\u002FSKILL.md`: prepare `.aligned.pqt` files, convert A3M to Chai MSA parquet, use ColabFold server flags, prepare template m8 inputs, and stage existing ColabFold outputs.\n- `sub-skills\u002Frestraints-glycans\u002FSKILL.md`: write and validate contact, pocket, covalent, and glycan restraint CSVs, including atom notation and chain-name consistency.\n\n## Common Public Setup\n\nChai Lab publishes the Python distribution `chai_lab` and import package `chai_lab`. Prefer a pinned public release when reproducibility matters:\n\n```bash\npip install chai_lab==0.6.1\npython - \u003C\u003C'PY'\nimport chai_lab\nfrom chai_lab.chai1 import run_inference\nprint(chai_lab.__version__, run_inference)\nPY\n```\n\nFor unreleased changes, install from the public Git repository instead of mixing source files into a skill workflow:\n\n```bash\npip install git+https:\u002F\u002Fgithub.com\u002Fchaidiscovery\u002Fchai-lab.git\n```\n\nChai-1 inference is intended for Linux, Python `>=3.10`, and a CUDA GPU with bfloat16 support. The package can be imported and many input validators can run without launching a fold, but practical folding should be treated as GPU-backed and potentially memory-intensive.\n\n## High-Level Workflows\n\n- Basic CLI fold: validate the FASTA with `sub-skills\u002Finput-data-formats\u002Fscripts\u002Fvalidate_chai_fasta.py`, choose a fresh output directory, then build `chai-lab fold input.fasta output_dir` with options from `sub-skills\u002Fcli-inference\u002FSKILL.md`.\n- Python inference: use `sub-skills\u002Fcli-inference\u002Fscripts\u002Fwrite_inference_template.py` to generate a safe script template, then add MSA\u002Ftemplate\u002Frestraint options from sibling sub-skills.\n- MSA\u002Ftemplate-backed fold: validate `.aligned.pqt` files and template m8 inputs through `sub-skills\u002Fmsa-templates\u002FSKILL.md` before passing `--msa-directory`, `--use-msa-server`, `--use-templates-server`, or `--template-hits-path`.\n- Restrained fold: validate contact, pocket, covalent, and glycan CSVs through `sub-skills\u002Frestraints-glycans\u002FSKILL.md`, then pass the CSV as `constraint_path` or `--constraint-path`.\n\n## Shared Checks\n\nRun the root helper for lightweight environment and backend visibility checks:\n\n```bash\npython scripts\u002Fcheck_chai_lab_environment.py --json\npython scripts\u002Fcheck_chai_lab_environment.py --require-cuda --check-cli\n```\n\nThis helper imports Chai Lab, checks the CLI, reports PyTorch\u002FCUDA visibility when PyTorch is installed, and prints `CHAI_DOWNLOADS_DIR` status. It does not download model weights or run inference.\n\n## Important Boundaries\n\n- Do not run full Chai inference as a cheap smoke test; use CLI `--help`, parser validators, and tiny data-format checks first.\n- Do not tell future agents to open original repository examples, tests, or scripts. The useful details are distilled into this skill's references and bundled scripts.\n- Keep local machine paths, private environment prefixes, cache paths, and artifact directories out of public instructions.\n- Treat network-backed MSA\u002Ftemplate generation and first-time model downloads as explicit side effects that may need user approval in restricted environments.\n- When a repository checkout has changed, compare it with `references\u002Frepo-provenance.md` and refresh this skill instead of relying on stale API details.\n\n## Reference Map\n\n- `references\u002Ftroubleshooting.md`: cross-cutting install\u002Fimport, CUDA, download, output-directory, and network-service failure modes.\n- `references\u002Frepo-provenance.md`: source snapshot and evidence paths used to create this skill.\n- `references\u002Frepo-routing-metadata.json`: structured import metadata for `repo-skills-router`.\n","# Chai Lab Repo Skill\n\nUse this skill when a task mentions Chai Lab, Chai-1, `chai_lab`, `chai-lab fold`, molecular structure prediction, protein\u002Fligand\u002FDNA\u002FRNA\u002Fglycan complexes, MSA\u002Ftemplate setup, or Chai restraint files.\n\n## Start Here\n\n1. Check package availability with `scripts\u002Fcheck_chai_lab_environment.py --help`, then run the checks that are safe for the target machine.\n2. Read `references\u002Ftroubleshooting.md` if install\u002Fimport, CUDA, model download, network server, or output-directory failures are likely.\n3. Read `references\u002Frepo-provenance.md` before refreshing this skill against a newer checkout.\n4. Route to one focused sub-skill rather than trying to keep all Chai details in the root context.\n\n## Sub-Skill Routing\n\n- `sub-skills\u002Fcli-inference\u002FSKILL.md`: run or template `chai-lab fold`, call `chai_lab.chai1.run_inference`, inspect `StructureCandidates`, tune sample\u002Frecycle\u002Fdevice options, and debug inference runtime failures.\n- `sub-skills\u002Finput-data-formats\u002FSKILL.md`: author and validate Chai FASTA records for proteins, ligands, DNA, RNA, modified residues, glycan headers, entity names, and chain-name mode decisions.\n- `sub-skills\u002Fmsa-templates\u002FSKILL.md`: prepare `.aligned.pqt` files, convert A3M to Chai MSA parquet, use ColabFold server flags, prepare template m8 inputs, and stage existing ColabFold outputs.\n- `sub-skills\u002Frestraints-glycans\u002FSKILL.md`: write and validate contact, pocket, covalent, and glycan restraint CSVs, including atom notation and chain-name consistency.\n\n## Common Public Setup\n\nChai Lab publishes the Python distribution `chai_lab` and import package `chai_lab`. Prefer a pinned public release when reproducibility matters:\n\n```bash\npip install chai_lab==0.6.1\npython - \u003C\u003C'PY'\nimport chai_lab\nfrom chai_lab.chai1 import run_inference\nprint(chai_lab.__version__, run_inference)\nPY\n```\n\nFor unreleased changes, install from the public Git repository instead of mixing source files into a skill workflow:\n\n```bash\npip install git+https:\u002F\u002Fgithub.com\u002Fchaidiscovery\u002Fchai-lab.git\n```\n\nChai-1 inference is intended for Linux, Python `>=3.10`, and a CUDA GPU with bfloat16 support. The package can be imported and many input validators can run without launching a fold, but practical folding should be treated as GPU-backed and potentially memory-intensive.\n\n## High-Level Workflows\n\n- Basic CLI fold: validate the FASTA with `sub-skills\u002Finput-data-formats\u002Fscripts\u002Fvalidate_chai_fasta.py`, choose a fresh output directory, then build `chai-lab fold input.fasta output_dir` with options from `sub-skills\u002Fcli-inference\u002FSKILL.md`.\n- Python inference: use `sub-skills\u002Fcli-inference\u002Fscripts\u002Fwrite_inference_template.py` to generate a safe script template, then add MSA\u002Ftemplate\u002Frestraint options from sibling sub-skills.\n- MSA\u002Ftemplate-backed fold: validate `.aligned.pqt` files and template m8 inputs through `sub-skills\u002Fmsa-templates\u002FSKILL.md` before passing `--msa-directory`, `--use-msa-server`, `--use-templates-server`, or `--template-hits-path`.\n- Restrained fold: validate contact, pocket, covalent, and glycan CSVs through `sub-skills\u002Frestraints-glycans\u002FSKILL.md`, then pass the CSV as `constraint_path` or `--constraint-path`.\n\n## Shared Checks\n\nRun the root helper for lightweight environment and backend visibility checks:\n\n```bash\npython scripts\u002Fcheck_chai_lab_environment.py --json\npython scripts\u002Fcheck_chai_lab_environment.py --require-cuda --check-cli\n```\n\nThis helper imports Chai Lab, checks the CLI, reports PyTorch\u002FCUDA visibility when PyTorch is installed, and prints `CHAI_DOWNLOADS_DIR` status. It does not download model weights or run inference.\n\n## Important Boundaries\n\n- Do not run full Chai inference as a cheap smoke test; use CLI `--help`, parser validators, and tiny data-format checks first.\n- Do not tell future agents to open original repository examples, tests, or scripts. The useful details are distilled into this skill's references and bundled scripts.\n- Keep local machine paths, private environment prefixes, cache paths, and artifact directories out of public instructions.\n- Treat network-backed MSA\u002Ftemplate generation and first-time model downloads as explicit side effects that may need user approval in restricted environments.\n- When a repository checkout has changed, compare it with `references\u002Frepo-provenance.md` and refresh this skill instead of relying on stale API details.\n\n## Reference Map\n\n- `references\u002Ftroubleshooting.md`: cross-cutting install\u002Fimport, CUDA, download, output-directory, and network-service failure modes.\n- `references\u002Frepo-provenance.md`: source snapshot and evidence paths used to create this skill.\n- `references\u002Frepo-routing-metadata.json`: structured import metadata for `repo-skills-router`.\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",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 chai-lab",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill chai-lab",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill chai-lab","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fchai-lab\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",2908,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fchai-lab\u002Freferences\u002Frepo-provenance.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Frepo-routing-metadata.json",327,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fchai-lab\u002Freferences\u002Frepo-routing-metadata.json",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",3520,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fchai-lab\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fcheck_chai_lab_environment.py","SCRIPT","脚本",4723,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fchai-lab\u002Fscripts\u002Fcheck_chai_lab_environment.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",[],[]]