[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78XWPZASMS73JGD56GVZSBB":3,"skill-same:01M78XWPZASMS73JGD56GVZSBB":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},"01M78XWPZASMS73JGD56GVZSBB","genomics-analysis",null,"Use dense Hail MatrixTable workflows for VCF, PLINK, BGEN, variant\u002Fsample QC, multiallelic splitting, PCA, LD pruning, association tests, VEP\u002FNirvana-style annotation, and reference genome or locus\u002Fcall handling.","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\u002Fsub-skills\u002Fgenomics-analysis\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: genomics-analysis\ndescription: \"Use dense Hail MatrixTable workflows for VCF, PLINK, BGEN,\n  variant\u002Fsample QC, multiallelic splitting, PCA, LD pruning, association tests,\n  VEP\u002FNirvana-style annotation, and reference genome or locus\u002Fcall handling.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Hail Genomics Analysis\n\nUse this sub-skill when the task is about dense genotype data represented as a Hail `MatrixTable`: importing VCF, PLINK, or BGEN; reasoning about row, column, entry, and global axes; annotating samples or variants; filtering calls; running QC; splitting multiallelics; running PCA, LD pruning, relatedness, or association tests; applying VEP\u002FNirvana-style annotation; or diagnosing reference genome and contig issues.\n\n## Start Here\n\n- Read `references\u002Fmatrixtable-workflows.md` for import-to-native-cache, annotation, filtering, QC, split, PCA, association, VEP, and export recipes.\n- Read `references\u002Fgenomic-methods.md` for task-to-method selection across QC, PCA, association, relatedness, VEP\u002FNirvana boundaries, reference genomes, `Locus`, `Call`, and `Pedigree`.\n- Read `references\u002Fdata-formats.md` before choosing import\u002Fexport options or interpreting `locus`, `alleles`, `s`, `GT`, `DP`, `GQ`, `PL`, `info`, dosage, and phenotype fields.\n- Read `references\u002Ftroubleshooting.md` when imports fail, references mismatch, `split_multi_hts` produces surprising INFO fields, VEP\u002FNirvana cannot run, association covariates fail, or `collect`\u002F`entries` is too expensive.\n- Use `scripts\u002Fmatrixtable_recipe_template.py --print-template` to generate a safe, editable dense MatrixTable recipe skeleton.\n\n## Route Elsewhere\n\n- Use `..\u002Fvariant-datasets\u002FSKILL.md` for sparse GVCF, VDS, combiner, `hl.vds`, local allele fields, or VDS-to-dense conversion work.\n- Use `..\u002Ftables-and-expressions\u002FSKILL.md` for generic `Table` pipelines, one-dimensional annotations, joins, aggregations, or expression-index errors that do not depend on MatrixTable axes.\n- Use `..\u002Fsetup-and-backends\u002FSKILL.md` for `hl.init`, Spark\u002Flocal\u002FBatch backend choice, package installation, Java\u002FJAR\u002Fruntime problems, cloud credentials, logs, and storage configuration.\n- Use `..\u002Fbatch-and-cli\u002FSKILL.md` for `hailctl`, `hailtop.batch`, job DAGs, cloud Batch execution, Dataproc\u002FHDInsight command families, or CLI automation.\n\n## Core Mental Model\n\nA dense `MatrixTable` has four axes:\n\n- `row`: variant\u002Fsite fields, usually keyed by `locus` and `alleles`.\n- `column`: sample fields, usually keyed by `s`.\n- `entry`: per-row-by-column values such as `GT`, `DP`, `GQ`, `AD`, `PL`, `GP`, or `dosage`.\n- `global`: metadata shared by the full dataset.\n\nChoose axis-specific methods deliberately: `annotate_rows`, `annotate_cols`, `annotate_entries`, `annotate_globals`, `filter_rows`, `filter_cols`, `filter_entries`, `select_rows`, `select_cols`, `select_entries`, and `select_globals`. Avoid converting to `entries()` unless the task truly needs coordinate-form rows.\n\n## Verified API Anchors\n\nThe inspected package exposes these dense-genomics entry points: `hl.import_vcf`, `hl.import_plink`, `hl.import_bgen`, `hl.export_vcf`, `hl.variant_qc`, `hl.sample_qc`, `hl.split_multi_hts`, `hl.linear_regression_rows`, `hl.logistic_regression_rows`, `hl.pca`, `hl.ld_prune`, and `hl.vep`. Treat `hl.vep` and `hl.nirvana` as external annotation boundaries: Hail joins annotations back to row variants, but executables, configs, caches, schemas, and assembly compatibility are environment responsibilities.\n\n## Safe Defaults\n\n- Import external genetics formats with an explicit `reference_genome`, inspect `mt.describe()`, then write or checkpoint native `.mt` before iterative analysis.\n- Use `hl.variant_qc` and `hl.sample_qc` only when `GT` is a `call` entry field and row keys represent variant-like `locus`\u002F`alleles`.\n- Run `hl.split_multi_hts` before biallelic-only HWE-sensitive QC, LD pruning, many association workflows, and allele-specific annotations.\n- Include an intercept explicitly in association covariates, usually `covariates=[1, ...]`.\n- Keep dense workflows separate from VDS workflows; do not force sparse GVCF data into dense MatrixTables unless the task explicitly calls for densification.\n","# Hail Genomics Analysis\n\nUse this sub-skill when the task is about dense genotype data represented as a Hail `MatrixTable`: importing VCF, PLINK, or BGEN; reasoning about row, column, entry, and global axes; annotating samples or variants; filtering calls; running QC; splitting multiallelics; running PCA, LD pruning, relatedness, or association tests; applying VEP\u002FNirvana-style annotation; or diagnosing reference genome and contig issues.\n\n## Start Here\n\n- Read `references\u002Fmatrixtable-workflows.md` for import-to-native-cache, annotation, filtering, QC, split, PCA, association, VEP, and export recipes.\n- Read `references\u002Fgenomic-methods.md` for task-to-method selection across QC, PCA, association, relatedness, VEP\u002FNirvana boundaries, reference genomes, `Locus`, `Call`, and `Pedigree`.\n- Read `references\u002Fdata-formats.md` before choosing import\u002Fexport options or interpreting `locus`, `alleles`, `s`, `GT`, `DP`, `GQ`, `PL`, `info`, dosage, and phenotype fields.\n- Read `references\u002Ftroubleshooting.md` when imports fail, references mismatch, `split_multi_hts` produces surprising INFO fields, VEP\u002FNirvana cannot run, association covariates fail, or `collect`\u002F`entries` is too expensive.\n- Use `scripts\u002Fmatrixtable_recipe_template.py --print-template` to generate a safe, editable dense MatrixTable recipe skeleton.\n\n## Route Elsewhere\n\n- Use `..\u002Fvariant-datasets\u002FSKILL.md` for sparse GVCF, VDS, combiner, `hl.vds`, local allele fields, or VDS-to-dense conversion work.\n- Use `..\u002Ftables-and-expressions\u002FSKILL.md` for generic `Table` pipelines, one-dimensional annotations, joins, aggregations, or expression-index errors that do not depend on MatrixTable axes.\n- Use `..\u002Fsetup-and-backends\u002FSKILL.md` for `hl.init`, Spark\u002Flocal\u002FBatch backend choice, package installation, Java\u002FJAR\u002Fruntime problems, cloud credentials, logs, and storage configuration.\n- Use `..\u002Fbatch-and-cli\u002FSKILL.md` for `hailctl`, `hailtop.batch`, job DAGs, cloud Batch execution, Dataproc\u002FHDInsight command families, or CLI automation.\n\n## Core Mental Model\n\nA dense `MatrixTable` has four axes:\n\n- `row`: variant\u002Fsite fields, usually keyed by `locus` and `alleles`.\n- `column`: sample fields, usually keyed by `s`.\n- `entry`: per-row-by-column values such as `GT`, `DP`, `GQ`, `AD`, `PL`, `GP`, or `dosage`.\n- `global`: metadata shared by the full dataset.\n\nChoose axis-specific methods deliberately: `annotate_rows`, `annotate_cols`, `annotate_entries`, `annotate_globals`, `filter_rows`, `filter_cols`, `filter_entries`, `select_rows`, `select_cols`, `select_entries`, and `select_globals`. Avoid converting to `entries()` unless the task truly needs coordinate-form rows.\n\n## Verified API Anchors\n\nThe inspected package exposes these dense-genomics entry points: `hl.import_vcf`, `hl.import_plink`, `hl.import_bgen`, `hl.export_vcf`, `hl.variant_qc`, `hl.sample_qc`, `hl.split_multi_hts`, `hl.linear_regression_rows`, `hl.logistic_regression_rows`, `hl.pca`, `hl.ld_prune`, and `hl.vep`. Treat `hl.vep` and `hl.nirvana` as external annotation boundaries: Hail joins annotations back to row variants, but executables, configs, caches, schemas, and assembly compatibility are environment responsibilities.\n\n## Safe Defaults\n\n- Import external genetics formats with an explicit `reference_genome`, inspect `mt.describe()`, then write or checkpoint native `.mt` before iterative analysis.\n- Use `hl.variant_qc` and `hl.sample_qc` only when `GT` is a `call` entry field and row keys represent variant-like `locus`\u002F`alleles`.\n- Run `hl.split_multi_hts` before biallelic-only HWE-sensitive QC, LD pruning, many association workflows, and allele-specific annotations.\n- Include an intercept explicitly in association covariates, usually `covariates=[1, ...]`.\n- Keep dense workflows separate from VDS workflows; do not force sparse GVCF data into dense MatrixTables unless the task explicitly calls for densification.\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\u002Fsub-skills\u002Fgenomics-analysis",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 genomics-analysis",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill genomics-analysis",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill genomics-analysis","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fhail\u002Fsub-skills\u002Fgenomics-analysis\u002FSKILL.md",[46,52,56,60,64],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fdata-formats.md","REFERENCE","参考文档",8918,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fhail\u002Fsub-skills\u002Fgenomics-analysis\u002Freferences\u002Fdata-formats.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fgenomic-methods.md",10079,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fhail\u002Fsub-skills\u002Fgenomics-analysis\u002Freferences\u002Fgenomic-methods.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fmatrixtable-workflows.md",10971,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fhail\u002Fsub-skills\u002Fgenomics-analysis\u002Freferences\u002Fmatrixtable-workflows.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Ftroubleshooting.md",9143,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fhail\u002Fsub-skills\u002Fgenomics-analysis\u002Freferences\u002Ftroubleshooting.md",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Fmatrixtable_recipe_template.py","SCRIPT","脚本",10942,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fhail\u002Fsub-skills\u002Fgenomics-analysis\u002Fscripts\u002Fmatrixtable_recipe_template.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",[],[]]