[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78XWH4SCRENC7DZPC85XVBJ":3,"skill-same:01M78XWH4SCRENC7DZPC85XVBJ":74},{"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},"01M78XWH4SCRENC7DZPC85XVBJ","hail",null,"Use Hail for scalable genomic Tables, MatrixTables, VariantDatasets, Hail Batch DAGs, and hailctl setup or cloud workflow 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\u002Fhail\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: hail\ndescription: \"Use Hail for scalable genomic Tables, MatrixTables,\n  VariantDatasets, Hail Batch DAGs, and hailctl setup or cloud workflow\n  troubleshooting.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Hail\n\nUse this repo skill when a task mentions Hail, `hail`, `hailtop`, `hailctl`, genomic `Table` or `MatrixTable` workflows, VCF\u002FPLINK\u002FBGEN imports, sparse GVCF or `VariantDataset` workflows, Hail Batch DAGs, or Hail backend setup and troubleshooting.\n\n## First Checks\n\n- Install the public `hail` distribution in Python 3.10 or newer, then verify `import hail as hl`, `import hailtop`, and `python -m hailtop.hailctl --help` from a neutral working directory.\n- Read `references\u002Frepo-provenance.md` before deciding whether this skill is current for a local Hail checkout.\n- Read `references\u002Fpackage-map.md` for the package layout, public APIs, and how the sub-skills divide responsibilities.\n- Read `references\u002Finspection-facts.md` for verified signatures, dependency constraints, packaged resources, and `hailctl` command families.\n- Run or adapt `scripts\u002Fcheck_hail_environment.py` for safe import, version, CLI, Java, PySpark, packaged-resource, and optional local-init diagnostics.\n- Use `references\u002Ftroubleshooting.md` for cross-cutting install\u002Fimport\u002Fbackend issues before diving into workflow-specific troubleshooting.\n\n## Route by User Goal\n\n| User goal or signal | Read |\n| --- | --- |\n| Install Hail, debug `import hail`, choose `hl.init` backend, configure logs\u002Ftmp\u002Freference\u002Frequester-pays, or fix Java\u002FSpark\u002FJAR startup failures | `sub-skills\u002Fsetup-and-backends\u002FSKILL.md` |\n| Build Hail `Table` pipelines, import delimited data, key\u002Fjoin annotations, aggregate rows, inspect schemas, or fix expression-index errors | `sub-skills\u002Ftables-and-expressions\u002FSKILL.md` |\n| Work with dense genotype `MatrixTable`s, VCF\u002FPLINK\u002FBGEN import\u002Fexport, sample\u002Fvariant QC, splitting, PCA, association tests, VEP, loci, calls, or reference genomes | `sub-skills\u002Fgenomics-analysis\u002FSKILL.md` |\n| Use `hail.vds`, sparse GVCF\u002FVariantDataset workflows, local alleles, reference blocks, VDS combiner, `to_dense_mt`, or VDS QC | `sub-skills\u002Fvariant-datasets\u002FSKILL.md` |\n| Build `hailtop.batch` DAGs, choose LocalBackend vs ServiceBackend, use `hailctl batch\u002Fconfig\u002Fauth\u002Fdataproc\u002Fhdinsight\u002Fdescribe`, or debug Batch\u002FCLI cloud configuration | `sub-skills\u002Fbatch-and-cli\u002FSKILL.md` |\n\n## Safe Workflow Defaults\n\n- Start with setup: verify the installed package, working directory, Java\u002FPySpark, `hailctl`, and backend choice before debugging workflow code.\n- For local examples, prefer `backend='local'` or `hailtop.batch.LocalBackend`; treat cloud Batch, Dataproc, HDInsight, requester-pays data, and service billing as explicit user choices.\n- Convert large external genomic inputs to Hail native formats (`.ht`, `.mt`, `.vds`) once, then iterate on native reads instead of reparsing VCF\u002FPLINK\u002FBGEN\u002FGVCF inputs.\n- Keep dense `MatrixTable` workflows and sparse VDS\u002FGVCF workflows separate until a task explicitly asks for conversion.\n- Use `describe()`, schema inspection, tiny previews, dry-run templates, and the bundled diagnostics before running expensive writes, exports, Batch submissions, or densification.\n\n## Important Boundaries\n\n- This skill covers user-facing Hail Python, Hailtop, Hail Batch, and packaged `hailctl` workflows. It does not cover Hail monorepo service deployment, release automation, Kubernetes infrastructure, or maintainer-only cloud operations.\n- Do not tell future agents to open original repository docs, tests, notebooks, or scripts. Use the bundled references and scripts in this skill.\n- Do not put credentials, billing projects, bucket names, private paths, or local environment details into reusable examples; use placeholders and ask the user for their values.\n- Native repo tests and cloud examples are verification evidence, not runtime dependencies. Run only safe, short, credential-free native checks when verifying this skill.\n\n## Bundled Helpers\n\n- `scripts\u002Fcheck_hail_environment.py` inspects installed Hail\u002FHailtop imports, version metadata, `hailctl`, Java, PySpark, and packaged resources without initializing an expensive backend by default.\n- `sub-skills\u002Ftables-and-expressions\u002Fscripts\u002Ftable_pipeline_template.py` prints or dry-runs a self-contained Table pipeline template.\n- `sub-skills\u002Fgenomics-analysis\u002Fscripts\u002Fmatrixtable_recipe_template.py` prints or dry-runs a dense MatrixTable analysis template.\n- `sub-skills\u002Fvariant-datasets\u002Fscripts\u002Fvds_recipe_template.py` prints or dry-runs a VDS workflow template.\n- `sub-skills\u002Fbatch-and-cli\u002Fscripts\u002Fbatch_local_smoke.py` constructs a local-only Batch smoke\u002Ftemplate and supports help or dry-run checks before execution.\n","# Hail\n\nUse this repo skill when a task mentions Hail, `hail`, `hailtop`, `hailctl`, genomic `Table` or `MatrixTable` workflows, VCF\u002FPLINK\u002FBGEN imports, sparse GVCF or `VariantDataset` workflows, Hail Batch DAGs, or Hail backend setup and troubleshooting.\n\n## First Checks\n\n- Install the public `hail` distribution in Python 3.10 or newer, then verify `import hail as hl`, `import hailtop`, and `python -m hailtop.hailctl --help` from a neutral working directory.\n- Read `references\u002Frepo-provenance.md` before deciding whether this skill is current for a local Hail checkout.\n- Read `references\u002Fpackage-map.md` for the package layout, public APIs, and how the sub-skills divide responsibilities.\n- Read `references\u002Finspection-facts.md` for verified signatures, dependency constraints, packaged resources, and `hailctl` command families.\n- Run or adapt `scripts\u002Fcheck_hail_environment.py` for safe import, version, CLI, Java, PySpark, packaged-resource, and optional local-init diagnostics.\n- Use `references\u002Ftroubleshooting.md` for cross-cutting install\u002Fimport\u002Fbackend issues before diving into workflow-specific troubleshooting.\n\n## Route by User Goal\n\n| User goal or signal | Read |\n| --- | --- |\n| Install Hail, debug `import hail`, choose `hl.init` backend, configure logs\u002Ftmp\u002Freference\u002Frequester-pays, or fix Java\u002FSpark\u002FJAR startup failures | `sub-skills\u002Fsetup-and-backends\u002FSKILL.md` |\n| Build Hail `Table` pipelines, import delimited data, key\u002Fjoin annotations, aggregate rows, inspect schemas, or fix expression-index errors | `sub-skills\u002Ftables-and-expressions\u002FSKILL.md` |\n| Work with dense genotype `MatrixTable`s, VCF\u002FPLINK\u002FBGEN import\u002Fexport, sample\u002Fvariant QC, splitting, PCA, association tests, VEP, loci, calls, or reference genomes | `sub-skills\u002Fgenomics-analysis\u002FSKILL.md` |\n| Use `hail.vds`, sparse GVCF\u002FVariantDataset workflows, local alleles, reference blocks, VDS combiner, `to_dense_mt`, or VDS QC | `sub-skills\u002Fvariant-datasets\u002FSKILL.md` |\n| Build `hailtop.batch` DAGs, choose LocalBackend vs ServiceBackend, use `hailctl batch\u002Fconfig\u002Fauth\u002Fdataproc\u002Fhdinsight\u002Fdescribe`, or debug Batch\u002FCLI cloud configuration | `sub-skills\u002Fbatch-and-cli\u002FSKILL.md` |\n\n## Safe Workflow Defaults\n\n- Start with setup: verify the installed package, working directory, Java\u002FPySpark, `hailctl`, and backend choice before debugging workflow code.\n- For local examples, prefer `backend='local'` or `hailtop.batch.LocalBackend`; treat cloud Batch, Dataproc, HDInsight, requester-pays data, and service billing as explicit user choices.\n- Convert large external genomic inputs to Hail native formats (`.ht`, `.mt`, `.vds`) once, then iterate on native reads instead of reparsing VCF\u002FPLINK\u002FBGEN\u002FGVCF inputs.\n- Keep dense `MatrixTable` workflows and sparse VDS\u002FGVCF workflows separate until a task explicitly asks for conversion.\n- Use `describe()`, schema inspection, tiny previews, dry-run templates, and the bundled diagnostics before running expensive writes, exports, Batch submissions, or densification.\n\n## Important Boundaries\n\n- This skill covers user-facing Hail Python, Hailtop, Hail Batch, and packaged `hailctl` workflows. It does not cover Hail monorepo service deployment, release automation, Kubernetes infrastructure, or maintainer-only cloud operations.\n- Do not tell future agents to open original repository docs, tests, notebooks, or scripts. Use the bundled references and scripts in this skill.\n- Do not put credentials, billing projects, bucket names, private paths, or local environment details into reusable examples; use placeholders and ask the user for their values.\n- Native repo tests and cloud examples are verification evidence, not runtime dependencies. Run only safe, short, credential-free native checks when verifying this skill.\n\n## Bundled Helpers\n\n- `scripts\u002Fcheck_hail_environment.py` inspects installed Hail\u002FHailtop imports, version metadata, `hailctl`, Java, PySpark, and packaged resources without initializing an expensive backend by default.\n- `sub-skills\u002Ftables-and-expressions\u002Fscripts\u002Ftable_pipeline_template.py` prints or dry-runs a self-contained Table pipeline template.\n- `sub-skills\u002Fgenomics-analysis\u002Fscripts\u002Fmatrixtable_recipe_template.py` prints or dry-runs a dense MatrixTable analysis template.\n- `sub-skills\u002Fvariant-datasets\u002Fscripts\u002Fvds_recipe_template.py` prints or dry-runs a VDS workflow template.\n- `sub-skills\u002Fbatch-and-cli\u002Fscripts\u002Fbatch_local_smoke.py` constructs a local-only Batch smoke\u002Ftemplate and supports help or dry-run checks before execution.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fhail",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 hail",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill hail",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill hail","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fhail\u002FSKILL.md",[46,52,56,60,64,68],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Finspection-facts.md","REFERENCE","参考文档",7420,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fhail\u002Freferences\u002Finspection-facts.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fpackage-map.md",3837,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fhail\u002Freferences\u002Fpackage-map.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Frepo-provenance.md",2709,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fhail\u002Freferences\u002Frepo-provenance.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Frepo-routing-metadata.json",487,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fhail\u002Freferences\u002Frepo-routing-metadata.json",{"path":65,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Ftroubleshooting.md",4433,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fhail\u002Freferences\u002Ftroubleshooting.md",{"path":69,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":72,"sourceHtmlUrl":73},"scripts\u002Fcheck_hail_environment.py","SCRIPT","脚本",8901,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fhail\u002Fscripts\u002Fcheck_hail_environment.py",[75,83,90,97,104,111],{"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":79,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"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":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"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":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"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":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"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":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"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":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"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",[],[]]