[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-aws-labs-variant-calling":3,"mdc-wjnj20-key":49,"related-org-aws-labs-variant-calling":829,"related-repo-aws-labs-variant-calling":1009},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":12,"stars":26,"repoUrl":27,"updatedAt":28,"license":29,"forks":30,"topics":31,"repo":44,"sourceUrl":47,"mdContent":48},"variant-calling","run short-variant calling pipelines","Germline and somatic short-variant calling pipeline for Illumina short-read data. Use when the user mentions BWA, BWA-MEM2, GATK, HaplotypeCaller, Mutect2, VCF, GVCF, VQSR, variant calling, germline, somatic, SNV, or indel calling from FASTQ\u002FBAM.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},"aws-labs","AWS Labs","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Faws-labs.png","awslabs",[13,17,20,23],{"name":14,"slug":15,"type":16},"Life Sciences","life-sciences","tag",{"name":18,"slug":19,"type":16},"Bioinformatics","bioinformatics",{"name":21,"slug":22,"type":16},"Genetics","genetics",{"name":24,"slug":25,"type":16},"AWS","aws",4,"https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fhcls-agent-skills","2026-07-12T08:37:30.837338",null,0,[32,33,34,35,36,37,38,39,40,15,41,42,43],"agent-skills","agentcore","ai-agents","amazon-quick-desktop","claims-processing","drug-discovery","genomics","healthcare-ai","kiro","medical-imaging","risk-adjustment","strands-agents",{"repoUrl":27,"stars":26,"forks":30,"topics":45,"description":46},[32,33,34,35,36,37,38,39,40,15,41,42,43],"Agent skills for healthcare and life sciences: genomics, imaging, claims, drug discovery, and more. Works with Amazon Quick, Kiro, Amazon AgentCore, AWS Strands SDK, Claude Code, Codex, and any Agent Skills-compatible platform.","https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fhcls-agent-skills\u002Ftree\u002FHEAD\u002Fskills\u002Fvariant-calling","---\nname: variant-calling\ndescription: Germline and somatic short-variant calling pipeline for Illumina short-read data. Use when the user mentions BWA, BWA-MEM2, GATK, HaplotypeCaller, Mutect2, VCF, GVCF, VQSR, variant calling, germline, somatic, SNV, or indel calling from FASTQ\u002FBAM.\nusage: Invoke when running germline or somatic variant calling with BWA-MEM2, GATK4 HaplotypeCaller, Mutect2, or VQSR.\nversion: 1.0.0\nvalidated_against:\n  date: 2025-01-15\n  packages: {gatk: \"4.5\", bwa-mem2: \"2.2.1\", samtools: \"1.19\"}\ntags: [skill, category:pipeline, genomics, variant-calling, gatk, bwa, hcls]\n---\n\n# Variant Calling (GATK4) — Pipeline Skill (Thin Scaffold)\n\n## Overview\n\nAdds decision logic for VQSR vs hard filters, WES vs WGS parameter differences, and GATK4-specific gotchas that LLMs frequently get wrong (filter thresholds, GVCF requirements, reference consistency).\n\n## Usage\n\n- Activate when choosing between VQSR and hard filters for a given cohort size\n- Activate when setting up WES vs WGS pipeline parameters\n- Activate when running Mutect2 tumor\u002Fnormal or tumor-only somatic calling\n\n## Core Concepts\n\n## Decision Logic\n\n```\nGermline calling strategy:\n├── Single sample, no future joint calling → HaplotypeCaller direct VCF\n└── Cohort (≥2 samples) → HaplotypeCaller -ERC GVCF → GenomicsDBImport → GenotypeGVCFs\n\nFiltering strategy:\n├── ≥30 WGS samples OR ≥30 WES exomes → VQSR\n└── \u003C30 samples OR single sample → Hard filters\n\nSomatic calling:\n├── Tumor + matched normal → Mutect2 with both BAMs\n└── Tumor-only → Mutect2 + PoN (MANDATORY) + gnomAD germline resource\n```\n\n**WES vs WGS parameter differences:**\n\n| Step | WGS | WES |\n|------|-----|-----|\n| BQSR \u002F HaplotypeCaller | No `-L` | `-L capture.bed -ip 100` |\n| Known sites for BQSR | Genome-wide | Genome-wide (do NOT subset) |\n| Filtering | VQSR (≥30 samples) | Hard filters unless ≥30 exomes |\n| Joint genotyping intervals | Per-chromosome | `-L capture.bed` |\n\n## Critical Parameters\n\n**Hard filter thresholds (GATK Best Practices):**\n\n| Filter | SNP threshold | Indel threshold |\n|--------|--------------|-----------------|\n| QD | \u003C 2.0 | \u003C 2.0 |\n| FS | > 60.0 | > 200.0 |\n| MQ | \u003C 40.0 | — |\n| MQRankSum | \u003C -12.5 | — |\n| ReadPosRankSum | \u003C -8.0 | \u003C -20.0 |\n| SOR | > 3.0 | > 10.0 |\n\n**VQSR truth sensitivity levels:**\n- SNPs: 99.7\n- Indels: 99.0\n- Indel `--max-gaussians 4` (fewer training variants than SNPs)\n\n**VQSR annotations:** `-an QD -an FS -an MQ -an MQRankSum -an ReadPosRankSum -an SOR`\n\n**Mutect2 essentials:**\n- `--germline-resource af-only-gnomad.hg38.vcf.gz`\n- `--panel-of-normals pon.vcf.gz` (essential for tumor-only)\n- `--f1r2-tar-gz` → `LearnReadOrientationModel` (FFPE\u002FOxoG artifacts)\n- `GetPileupSummaries` + `CalculateContamination` before `FilterMutectCalls`\n\n## Common Mistakes\n\n- **Wrong:** Aligning without proper `@RG` headers (missing ID, SM, PL, LB)\n  **Right:** Always specify at alignment: `-R '@RG\\tID:x\\tSM:x\\tPL:ILLUMINA\\tLB:x'`\n  **Why:** GATK refuses to run or silently merges samples when SM tags are wrong\n\n- **Wrong:** Running HaplotypeCaller without `-ERC GVCF` for cohort analysis\n  **Right:** Always produce GVCFs when joint genotyping will be performed\n  **Why:** Regular VCFs cannot be joint-genotyped; must re-call from BAM\n\n- **Wrong:** Reusing SNP hard-filter thresholds for indels (e.g., `FS > 60` for indels)\n  **Right:** Use `FS > 200` for indels, `FS > 60` for SNPs\n  **Why:** Indels tolerate higher strand bias; SNP thresholds over-filter real indels\n\n- **Wrong:** Applying VQSR to \u003C30 samples\n  **Right:** Use hard filters for small cohorts\n  **Why:** VQSR needs many variants to train its Gaussian mixture model\n\n- **Wrong:** Subsetting `--known-sites` VCFs to WES capture BED for BQSR\n  **Right:** Use genome-wide known-sites; only restrict analysis intervals via `-L`\n  **Why:** BQSR needs genome-wide known sites to model base quality errors\n\n- **Wrong:** Skipping `samtools index` between GATK steps\n  **Right:** Index after every BAM-producing step\n  **Why:** GATK requires BAM indices; missing them causes immediate failure\n\n- **Wrong:** Mixing reference files from different genome builds\n  **Right:** Ensure ref.dict, ref.fa.fai, BWA index, and all VCFs match the same build\n  **Why:** Mismatched dictionaries cause silent failures or cryptic errors\n\n- **Wrong:** Running Mutect2 tumor-only without a panel of normals\n  **Right:** Always provide `--panel-of-normals` for tumor-only calling\n  **Why:** Without PoN, recurrent sequencing artifacts are called as somatic mutations\n\n## Response Format\n\n- Lead with the command or code the user needs — explain after\n- Structure as: confirm inputs → working code → key parameters explained → gotchas\n- One complete working example per task; do not show every alternative\n- Keep code comments minimal and functional (what, not why-it-exists)\n- Target: 50-100 lines of code with brief surrounding explanation\n",{"data":50,"body":65},{"name":4,"description":6,"usage":51,"version":52,"validated_against":53,"tags":59},"Invoke when running germline or somatic variant calling with BWA-MEM2, GATK4 HaplotypeCaller, Mutect2, or VQSR.","1.0.0",{"date":54,"packages":55},"2025-01-15",{"gatk":56,"bwa-mem2":57,"samtools":58},"4.5","2.2.1","1.19",[60,61,38,4,62,63,64],"skill","category:pipeline","gatk","bwa","hcls",{"type":66,"children":67},"root",[68,77,84,90,96,116,122,128,141,150,269,275,283,416,424,450,466,474,541,547,795,801],{"type":69,"tag":70,"props":71,"children":73},"element","h1",{"id":72},"variant-calling-gatk4-pipeline-skill-thin-scaffold",[74],{"type":75,"value":76},"text","Variant Calling (GATK4) — Pipeline Skill (Thin Scaffold)",{"type":69,"tag":78,"props":79,"children":81},"h2",{"id":80},"overview",[82],{"type":75,"value":83},"Overview",{"type":69,"tag":85,"props":86,"children":87},"p",{},[88],{"type":75,"value":89},"Adds decision logic for VQSR vs hard filters, WES vs WGS parameter differences, and GATK4-specific gotchas that LLMs frequently get wrong (filter thresholds, GVCF requirements, reference consistency).",{"type":69,"tag":78,"props":91,"children":93},{"id":92},"usage",[94],{"type":75,"value":95},"Usage",{"type":69,"tag":97,"props":98,"children":99},"ul",{},[100,106,111],{"type":69,"tag":101,"props":102,"children":103},"li",{},[104],{"type":75,"value":105},"Activate when choosing between VQSR and hard filters for a given cohort size",{"type":69,"tag":101,"props":107,"children":108},{},[109],{"type":75,"value":110},"Activate when setting up WES vs WGS pipeline parameters",{"type":69,"tag":101,"props":112,"children":113},{},[114],{"type":75,"value":115},"Activate when running Mutect2 tumor\u002Fnormal or tumor-only somatic calling",{"type":69,"tag":78,"props":117,"children":119},{"id":118},"core-concepts",[120],{"type":75,"value":121},"Core Concepts",{"type":69,"tag":78,"props":123,"children":125},{"id":124},"decision-logic",[126],{"type":75,"value":127},"Decision Logic",{"type":69,"tag":129,"props":130,"children":134},"pre",{"className":131,"code":133,"language":75},[132],"language-text","Germline calling strategy:\n├── Single sample, no future joint calling → HaplotypeCaller direct VCF\n└── Cohort (≥2 samples) → HaplotypeCaller -ERC GVCF → GenomicsDBImport → GenotypeGVCFs\n\nFiltering strategy:\n├── ≥30 WGS samples OR ≥30 WES exomes → VQSR\n└── \u003C30 samples OR single sample → Hard filters\n\nSomatic calling:\n├── Tumor + matched normal → Mutect2 with both BAMs\n└── Tumor-only → Mutect2 + PoN (MANDATORY) + gnomAD germline resource\n",[135],{"type":69,"tag":136,"props":137,"children":139},"code",{"__ignoreMap":138},"",[140],{"type":75,"value":133},{"type":69,"tag":85,"props":142,"children":143},{},[144],{"type":69,"tag":145,"props":146,"children":147},"strong",{},[148],{"type":75,"value":149},"WES vs WGS parameter differences:",{"type":69,"tag":151,"props":152,"children":153},"table",{},[154,178],{"type":69,"tag":155,"props":156,"children":157},"thead",{},[158],{"type":69,"tag":159,"props":160,"children":161},"tr",{},[162,168,173],{"type":69,"tag":163,"props":164,"children":165},"th",{},[166],{"type":75,"value":167},"Step",{"type":69,"tag":163,"props":169,"children":170},{},[171],{"type":75,"value":172},"WGS",{"type":69,"tag":163,"props":174,"children":175},{},[176],{"type":75,"value":177},"WES",{"type":69,"tag":179,"props":180,"children":181},"tbody",{},[182,211,229,247],{"type":69,"tag":159,"props":183,"children":184},{},[185,191,202],{"type":69,"tag":186,"props":187,"children":188},"td",{},[189],{"type":75,"value":190},"BQSR \u002F HaplotypeCaller",{"type":69,"tag":186,"props":192,"children":193},{},[194,196],{"type":75,"value":195},"No ",{"type":69,"tag":136,"props":197,"children":199},{"className":198},[],[200],{"type":75,"value":201},"-L",{"type":69,"tag":186,"props":203,"children":204},{},[205],{"type":69,"tag":136,"props":206,"children":208},{"className":207},[],[209],{"type":75,"value":210},"-L capture.bed -ip 100",{"type":69,"tag":159,"props":212,"children":213},{},[214,219,224],{"type":69,"tag":186,"props":215,"children":216},{},[217],{"type":75,"value":218},"Known sites for BQSR",{"type":69,"tag":186,"props":220,"children":221},{},[222],{"type":75,"value":223},"Genome-wide",{"type":69,"tag":186,"props":225,"children":226},{},[227],{"type":75,"value":228},"Genome-wide (do NOT subset)",{"type":69,"tag":159,"props":230,"children":231},{},[232,237,242],{"type":69,"tag":186,"props":233,"children":234},{},[235],{"type":75,"value":236},"Filtering",{"type":69,"tag":186,"props":238,"children":239},{},[240],{"type":75,"value":241},"VQSR (≥30 samples)",{"type":69,"tag":186,"props":243,"children":244},{},[245],{"type":75,"value":246},"Hard filters unless ≥30 exomes",{"type":69,"tag":159,"props":248,"children":249},{},[250,255,260],{"type":69,"tag":186,"props":251,"children":252},{},[253],{"type":75,"value":254},"Joint genotyping intervals",{"type":69,"tag":186,"props":256,"children":257},{},[258],{"type":75,"value":259},"Per-chromosome",{"type":69,"tag":186,"props":261,"children":262},{},[263],{"type":69,"tag":136,"props":264,"children":266},{"className":265},[],[267],{"type":75,"value":268},"-L capture.bed",{"type":69,"tag":78,"props":270,"children":272},{"id":271},"critical-parameters",[273],{"type":75,"value":274},"Critical Parameters",{"type":69,"tag":85,"props":276,"children":277},{},[278],{"type":69,"tag":145,"props":279,"children":280},{},[281],{"type":75,"value":282},"Hard filter thresholds (GATK Best Practices):",{"type":69,"tag":151,"props":284,"children":285},{},[286,307],{"type":69,"tag":155,"props":287,"children":288},{},[289],{"type":69,"tag":159,"props":290,"children":291},{},[292,297,302],{"type":69,"tag":163,"props":293,"children":294},{},[295],{"type":75,"value":296},"Filter",{"type":69,"tag":163,"props":298,"children":299},{},[300],{"type":75,"value":301},"SNP threshold",{"type":69,"tag":163,"props":303,"children":304},{},[305],{"type":75,"value":306},"Indel threshold",{"type":69,"tag":179,"props":308,"children":309},{},[310,327,345,363,380,398],{"type":69,"tag":159,"props":311,"children":312},{},[313,318,323],{"type":69,"tag":186,"props":314,"children":315},{},[316],{"type":75,"value":317},"QD",{"type":69,"tag":186,"props":319,"children":320},{},[321],{"type":75,"value":322},"\u003C 2.0",{"type":69,"tag":186,"props":324,"children":325},{},[326],{"type":75,"value":322},{"type":69,"tag":159,"props":328,"children":329},{},[330,335,340],{"type":69,"tag":186,"props":331,"children":332},{},[333],{"type":75,"value":334},"FS",{"type":69,"tag":186,"props":336,"children":337},{},[338],{"type":75,"value":339},"> 60.0",{"type":69,"tag":186,"props":341,"children":342},{},[343],{"type":75,"value":344},"> 200.0",{"type":69,"tag":159,"props":346,"children":347},{},[348,353,358],{"type":69,"tag":186,"props":349,"children":350},{},[351],{"type":75,"value":352},"MQ",{"type":69,"tag":186,"props":354,"children":355},{},[356],{"type":75,"value":357},"\u003C 40.0",{"type":69,"tag":186,"props":359,"children":360},{},[361],{"type":75,"value":362},"—",{"type":69,"tag":159,"props":364,"children":365},{},[366,371,376],{"type":69,"tag":186,"props":367,"children":368},{},[369],{"type":75,"value":370},"MQRankSum",{"type":69,"tag":186,"props":372,"children":373},{},[374],{"type":75,"value":375},"\u003C -12.5",{"type":69,"tag":186,"props":377,"children":378},{},[379],{"type":75,"value":362},{"type":69,"tag":159,"props":381,"children":382},{},[383,388,393],{"type":69,"tag":186,"props":384,"children":385},{},[386],{"type":75,"value":387},"ReadPosRankSum",{"type":69,"tag":186,"props":389,"children":390},{},[391],{"type":75,"value":392},"\u003C -8.0",{"type":69,"tag":186,"props":394,"children":395},{},[396],{"type":75,"value":397},"\u003C -20.0",{"type":69,"tag":159,"props":399,"children":400},{},[401,406,411],{"type":69,"tag":186,"props":402,"children":403},{},[404],{"type":75,"value":405},"SOR",{"type":69,"tag":186,"props":407,"children":408},{},[409],{"type":75,"value":410},"> 3.0",{"type":69,"tag":186,"props":412,"children":413},{},[414],{"type":75,"value":415},"> 10.0",{"type":69,"tag":85,"props":417,"children":418},{},[419],{"type":69,"tag":145,"props":420,"children":421},{},[422],{"type":75,"value":423},"VQSR truth sensitivity levels:",{"type":69,"tag":97,"props":425,"children":426},{},[427,432,437],{"type":69,"tag":101,"props":428,"children":429},{},[430],{"type":75,"value":431},"SNPs: 99.7",{"type":69,"tag":101,"props":433,"children":434},{},[435],{"type":75,"value":436},"Indels: 99.0",{"type":69,"tag":101,"props":438,"children":439},{},[440,442,448],{"type":75,"value":441},"Indel ",{"type":69,"tag":136,"props":443,"children":445},{"className":444},[],[446],{"type":75,"value":447},"--max-gaussians 4",{"type":75,"value":449}," (fewer training variants than SNPs)",{"type":69,"tag":85,"props":451,"children":452},{},[453,458,460],{"type":69,"tag":145,"props":454,"children":455},{},[456],{"type":75,"value":457},"VQSR annotations:",{"type":75,"value":459}," ",{"type":69,"tag":136,"props":461,"children":463},{"className":462},[],[464],{"type":75,"value":465},"-an QD -an FS -an MQ -an MQRankSum -an ReadPosRankSum -an SOR",{"type":69,"tag":85,"props":467,"children":468},{},[469],{"type":69,"tag":145,"props":470,"children":471},{},[472],{"type":75,"value":473},"Mutect2 essentials:",{"type":69,"tag":97,"props":475,"children":476},{},[477,486,497,516],{"type":69,"tag":101,"props":478,"children":479},{},[480],{"type":69,"tag":136,"props":481,"children":483},{"className":482},[],[484],{"type":75,"value":485},"--germline-resource af-only-gnomad.hg38.vcf.gz",{"type":69,"tag":101,"props":487,"children":488},{},[489,495],{"type":69,"tag":136,"props":490,"children":492},{"className":491},[],[493],{"type":75,"value":494},"--panel-of-normals pon.vcf.gz",{"type":75,"value":496}," (essential for tumor-only)",{"type":69,"tag":101,"props":498,"children":499},{},[500,506,508,514],{"type":69,"tag":136,"props":501,"children":503},{"className":502},[],[504],{"type":75,"value":505},"--f1r2-tar-gz",{"type":75,"value":507}," → ",{"type":69,"tag":136,"props":509,"children":511},{"className":510},[],[512],{"type":75,"value":513},"LearnReadOrientationModel",{"type":75,"value":515}," (FFPE\u002FOxoG artifacts)",{"type":69,"tag":101,"props":517,"children":518},{},[519,525,527,533,535],{"type":69,"tag":136,"props":520,"children":522},{"className":521},[],[523],{"type":75,"value":524},"GetPileupSummaries",{"type":75,"value":526}," + ",{"type":69,"tag":136,"props":528,"children":530},{"className":529},[],[531],{"type":75,"value":532},"CalculateContamination",{"type":75,"value":534}," before ",{"type":69,"tag":136,"props":536,"children":538},{"className":537},[],[539],{"type":75,"value":540},"FilterMutectCalls",{"type":69,"tag":78,"props":542,"children":544},{"id":543},"common-mistakes",[545],{"type":75,"value":546},"Common Mistakes",{"type":69,"tag":97,"props":548,"children":549},{},[550,588,617,661,682,716,745,766],{"type":69,"tag":101,"props":551,"children":552},{},[553,558,560,566,568,573,575,581,586],{"type":69,"tag":145,"props":554,"children":555},{},[556],{"type":75,"value":557},"Wrong:",{"type":75,"value":559}," Aligning without proper ",{"type":69,"tag":136,"props":561,"children":563},{"className":562},[],[564],{"type":75,"value":565},"@RG",{"type":75,"value":567}," headers (missing ID, SM, PL, LB)\n",{"type":69,"tag":145,"props":569,"children":570},{},[571],{"type":75,"value":572},"Right:",{"type":75,"value":574}," Always specify at alignment: ",{"type":69,"tag":136,"props":576,"children":578},{"className":577},[],[579],{"type":75,"value":580},"-R '@RG\\tID:x\\tSM:x\\tPL:ILLUMINA\\tLB:x'",{"type":69,"tag":145,"props":582,"children":583},{},[584],{"type":75,"value":585},"Why:",{"type":75,"value":587}," GATK refuses to run or silently merges samples when SM tags are wrong",{"type":69,"tag":101,"props":589,"children":590},{},[591,595,597,603,605,609,611,615],{"type":69,"tag":145,"props":592,"children":593},{},[594],{"type":75,"value":557},{"type":75,"value":596}," Running HaplotypeCaller without ",{"type":69,"tag":136,"props":598,"children":600},{"className":599},[],[601],{"type":75,"value":602},"-ERC GVCF",{"type":75,"value":604}," for cohort analysis\n",{"type":69,"tag":145,"props":606,"children":607},{},[608],{"type":75,"value":572},{"type":75,"value":610}," Always produce GVCFs when joint genotyping will be performed\n",{"type":69,"tag":145,"props":612,"children":613},{},[614],{"type":75,"value":585},{"type":75,"value":616}," Regular VCFs cannot be joint-genotyped; must re-call from BAM",{"type":69,"tag":101,"props":618,"children":619},{},[620,624,626,632,634,638,640,646,648,653,655,659],{"type":69,"tag":145,"props":621,"children":622},{},[623],{"type":75,"value":557},{"type":75,"value":625}," Reusing SNP hard-filter thresholds for indels (e.g., ",{"type":69,"tag":136,"props":627,"children":629},{"className":628},[],[630],{"type":75,"value":631},"FS > 60",{"type":75,"value":633}," for indels)\n",{"type":69,"tag":145,"props":635,"children":636},{},[637],{"type":75,"value":572},{"type":75,"value":639}," Use ",{"type":69,"tag":136,"props":641,"children":643},{"className":642},[],[644],{"type":75,"value":645},"FS > 200",{"type":75,"value":647}," for indels, ",{"type":69,"tag":136,"props":649,"children":651},{"className":650},[],[652],{"type":75,"value":631},{"type":75,"value":654}," for SNPs\n",{"type":69,"tag":145,"props":656,"children":657},{},[658],{"type":75,"value":585},{"type":75,"value":660}," Indels tolerate higher strand bias; SNP thresholds over-filter real indels",{"type":69,"tag":101,"props":662,"children":663},{},[664,668,670,674,676,680],{"type":69,"tag":145,"props":665,"children":666},{},[667],{"type":75,"value":557},{"type":75,"value":669}," Applying VQSR to \u003C30 samples\n",{"type":69,"tag":145,"props":671,"children":672},{},[673],{"type":75,"value":572},{"type":75,"value":675}," Use hard filters for small cohorts\n",{"type":69,"tag":145,"props":677,"children":678},{},[679],{"type":75,"value":585},{"type":75,"value":681}," VQSR needs many variants to train its Gaussian mixture model",{"type":69,"tag":101,"props":683,"children":684},{},[685,689,691,697,699,703,705,710,714],{"type":69,"tag":145,"props":686,"children":687},{},[688],{"type":75,"value":557},{"type":75,"value":690}," Subsetting ",{"type":69,"tag":136,"props":692,"children":694},{"className":693},[],[695],{"type":75,"value":696},"--known-sites",{"type":75,"value":698}," VCFs to WES capture BED for BQSR\n",{"type":69,"tag":145,"props":700,"children":701},{},[702],{"type":75,"value":572},{"type":75,"value":704}," Use genome-wide known-sites; only restrict analysis intervals via ",{"type":69,"tag":136,"props":706,"children":708},{"className":707},[],[709],{"type":75,"value":201},{"type":69,"tag":145,"props":711,"children":712},{},[713],{"type":75,"value":585},{"type":75,"value":715}," BQSR needs genome-wide known sites to model base quality errors",{"type":69,"tag":101,"props":717,"children":718},{},[719,723,725,731,733,737,739,743],{"type":69,"tag":145,"props":720,"children":721},{},[722],{"type":75,"value":557},{"type":75,"value":724}," Skipping ",{"type":69,"tag":136,"props":726,"children":728},{"className":727},[],[729],{"type":75,"value":730},"samtools index",{"type":75,"value":732}," between GATK steps\n",{"type":69,"tag":145,"props":734,"children":735},{},[736],{"type":75,"value":572},{"type":75,"value":738}," Index after every BAM-producing step\n",{"type":69,"tag":145,"props":740,"children":741},{},[742],{"type":75,"value":585},{"type":75,"value":744}," GATK requires BAM indices; missing them causes immediate failure",{"type":69,"tag":101,"props":746,"children":747},{},[748,752,754,758,760,764],{"type":69,"tag":145,"props":749,"children":750},{},[751],{"type":75,"value":557},{"type":75,"value":753}," Mixing reference files from different genome builds\n",{"type":69,"tag":145,"props":755,"children":756},{},[757],{"type":75,"value":572},{"type":75,"value":759}," Ensure ref.dict, ref.fa.fai, BWA index, and all VCFs match the same build\n",{"type":69,"tag":145,"props":761,"children":762},{},[763],{"type":75,"value":585},{"type":75,"value":765}," Mismatched dictionaries cause silent failures or cryptic errors",{"type":69,"tag":101,"props":767,"children":768},{},[769,773,775,779,781,787,789,793],{"type":69,"tag":145,"props":770,"children":771},{},[772],{"type":75,"value":557},{"type":75,"value":774}," Running Mutect2 tumor-only without a panel of normals\n",{"type":69,"tag":145,"props":776,"children":777},{},[778],{"type":75,"value":572},{"type":75,"value":780}," Always provide ",{"type":69,"tag":136,"props":782,"children":784},{"className":783},[],[785],{"type":75,"value":786},"--panel-of-normals",{"type":75,"value":788}," for tumor-only calling\n",{"type":69,"tag":145,"props":790,"children":791},{},[792],{"type":75,"value":585},{"type":75,"value":794}," Without PoN, recurrent sequencing artifacts are called as somatic mutations",{"type":69,"tag":78,"props":796,"children":798},{"id":797},"response-format",[799],{"type":75,"value":800},"Response Format",{"type":69,"tag":97,"props":802,"children":803},{},[804,809,814,819,824],{"type":69,"tag":101,"props":805,"children":806},{},[807],{"type":75,"value":808},"Lead with the command or code the user needs — explain after",{"type":69,"tag":101,"props":810,"children":811},{},[812],{"type":75,"value":813},"Structure as: confirm inputs → working code → key parameters explained → gotchas",{"type":69,"tag":101,"props":815,"children":816},{},[817],{"type":75,"value":818},"One complete working example per task; do not show every alternative",{"type":69,"tag":101,"props":820,"children":821},{},[822],{"type":75,"value":823},"Keep code comments minimal and functional (what, not why-it-exists)",{"type":69,"tag":101,"props":825,"children":826},{},[827],{"type":75,"value":828},"Target: 50-100 lines of code with brief surrounding explanation",{"items":830,"total":1008},[831,850,871,881,894,907,917,927,948,963,978,993],{"slug":832,"name":832,"fn":833,"description":834,"org":835,"tags":836,"stars":847,"repoUrl":848,"updatedAt":849},"agentcore-investigation","investigate Bedrock AgentCore runtime sessions","Investigate Bedrock AgentCore runtime sessions via CloudWatch Logs Insights — resolve session\u002Ftrace IDs, query OTEL spans, filter noise, build timelines. Use when debugging AgentCore agent sessions, tracing tool calls, or analyzing latency.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[837,838,841,844],{"name":24,"slug":25,"type":16},{"name":839,"slug":840,"type":16},"Debugging","debugging",{"name":842,"slug":843,"type":16},"Logs","logs",{"name":845,"slug":846,"type":16},"Observability","observability",9427,"https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fmcp","2026-07-12T08:37:22.601527",{"slug":851,"name":852,"fn":853,"description":854,"org":855,"tags":856,"stars":847,"repoUrl":848,"updatedAt":870},"amazon-aurora-dsql","amazon aurora dsql","build applications with Aurora DSQL","Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, load data, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL and PostgreSQL-to-DSQL schema conversion, FK replacement code generation, OCC retry patterns, ORM migration (Django\u002FHibernate\u002FRails), DDL operations, query plan explainability, SQL compatibility validation, and bulk data loading. Triggers on phrases like: DSQL, Aurora DSQL, create DSQL table, DSQL schema, migrate to DSQL, distributed SQL database, serverless PostgreSQL-compatible database, DSQL query plan, DSQL EXPLAIN ANALYZE, why is my DSQL query slow, DSQL foreign key, DSQL OCC retry, DSQL multi-region, load into DSQL, load CSV into DSQL, bulk load DSQL, aurora-dsql-loader.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[857,860,861,864,867],{"name":858,"slug":859,"type":16},"Aurora","aurora",{"name":24,"slug":25,"type":16},{"name":862,"slug":863,"type":16},"Database","database",{"name":865,"slug":866,"type":16},"Serverless","serverless",{"name":868,"slug":869,"type":16},"SQL","sql","2026-07-12T08:36:45.053393",{"slug":872,"name":873,"fn":853,"description":854,"org":874,"tags":875,"stars":847,"repoUrl":848,"updatedAt":880},"aurora-dsql","aurora dsql",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[876,877,878,879],{"name":24,"slug":25,"type":16},{"name":862,"slug":863,"type":16},{"name":865,"slug":866,"type":16},{"name":868,"slug":869,"type":16},"2026-07-12T08:36:42.694299",{"slug":882,"name":883,"fn":853,"description":854,"org":884,"tags":885,"stars":847,"repoUrl":848,"updatedAt":893},"aws-dsql","aws dsql",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[886,887,888,891,892],{"name":24,"slug":25,"type":16},{"name":862,"slug":863,"type":16},{"name":889,"slug":890,"type":16},"Migration","migration",{"name":865,"slug":866,"type":16},{"name":868,"slug":869,"type":16},"2026-07-12T08:36:38.584057",{"slug":895,"name":896,"fn":853,"description":854,"org":897,"tags":898,"stars":847,"repoUrl":848,"updatedAt":906},"distributed-postgres","distributed postgres",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[899,900,901,904,905],{"name":24,"slug":25,"type":16},{"name":862,"slug":863,"type":16},{"name":902,"slug":903,"type":16},"PostgreSQL","postgresql",{"name":865,"slug":866,"type":16},{"name":868,"slug":869,"type":16},"2026-07-12T08:36:46.530743",{"slug":908,"name":909,"fn":853,"description":854,"org":910,"tags":911,"stars":847,"repoUrl":848,"updatedAt":916},"distributed-sql","distributed sql",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[912,913,914,915],{"name":24,"slug":25,"type":16},{"name":862,"slug":863,"type":16},{"name":865,"slug":866,"type":16},{"name":868,"slug":869,"type":16},"2026-07-12T08:36:48.104182",{"slug":918,"name":918,"fn":853,"description":854,"org":919,"tags":920,"stars":847,"repoUrl":848,"updatedAt":926},"dsql",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[921,922,923,924,925],{"name":24,"slug":25,"type":16},{"name":862,"slug":863,"type":16},{"name":889,"slug":890,"type":16},{"name":865,"slug":866,"type":16},{"name":868,"slug":869,"type":16},"2026-07-12T08:36:36.374512",{"slug":928,"name":928,"fn":929,"description":930,"org":931,"tags":932,"stars":945,"repoUrl":946,"updatedAt":947},"cost-efficiency-analyzer","analyze cost efficiency and expenses","Analyzes cost structure, cost efficiency, and expense management from P&L data. Use when the user asks about costs, expenses, COGS, operating expenses, cost ratios, cost control, spending efficiency, margin compression from cost side, or wants to understand where money is going. Also use for \"are we spending too much\", \"cost breakdown\", \"expense analysis\", or \"how efficient are our operations\". NOT for revenue or top-line analysis.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[933,936,939,942],{"name":934,"slug":935,"type":16},"Accounting","accounting",{"name":937,"slug":938,"type":16},"Analytics","analytics",{"name":940,"slug":941,"type":16},"Cost Optimization","cost-optimization",{"name":943,"slug":944,"type":16},"Finance","finance",3176,"https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fagentcore-samples","2026-07-12T08:40:03.29555",{"slug":949,"name":949,"fn":950,"description":951,"org":952,"tags":953,"stars":945,"repoUrl":946,"updatedAt":962},"executive-financial-briefing","generate executive financial briefings","Generates a concise executive-level financial briefing or summary suitable for a CEO, CFO, or board presentation. Use when the user asks for a summary, briefing, executive summary, board update, financial overview, financial health check, or \"how is the business doing\". Covers the full P&L picture in one page. Also use for \"give me the highlights\", \"what do I need to know\", or \"quick financial update\".",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[954,955,956,959],{"name":24,"slug":25,"type":16},{"name":943,"slug":944,"type":16},{"name":957,"slug":958,"type":16},"Management","management",{"name":960,"slug":961,"type":16},"Reporting","reporting","2026-07-12T08:40:02.066471",{"slug":964,"name":964,"fn":965,"description":966,"org":967,"tags":968,"stars":945,"repoUrl":946,"updatedAt":977},"multi-quarter-trend-analysis","analyze multi-quarter financial trends","Analyzes financial trends across multiple quarters by comparing P&L metrics over time. Use when the user wants to see trends, patterns, trajectories, or directional movement across 3 or more quarters. Also use for \"how are we trending\", \"show me the trend\", \"track performance over time\", \"quarter over quarter comparison across all quarters\", or any multi-period longitudinal analysis.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[969,970,971,974],{"name":937,"slug":938,"type":16},{"name":943,"slug":944,"type":16},{"name":972,"slug":973,"type":16},"Financial Statements","financial-statements",{"name":975,"slug":976,"type":16},"Variance Analysis","variance-analysis","2026-07-12T08:40:00.79141",{"slug":979,"name":979,"fn":980,"description":981,"org":982,"tags":983,"stars":945,"repoUrl":946,"updatedAt":992},"pdf","process and manipulate PDF documents","Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text\u002Ftables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting\u002Fdecrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[984,987,990],{"name":985,"slug":986,"type":16},"Automation","automation",{"name":988,"slug":989,"type":16},"Documents","documents",{"name":991,"slug":979,"type":16},"PDF","2026-07-12T08:41:44.135656",{"slug":994,"name":994,"fn":995,"description":996,"org":997,"tags":998,"stars":945,"repoUrl":946,"updatedAt":1007},"quarterly-kpi-calculator","calculate quarterly financial KPIs","Calculates quarterly financial KPIs from P&L data. P&L figures can be provided directly by the user or fetched from the financial data MCP server. Use when the user wants KPI calculations such as Gross Margin %, EBITDA Margin %, Operating Expense Ratio, or Revenue Growth % QoQ. Also use for quarterly performance review, P&L analysis, or interpreting financial ratios against benchmarks.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[999,1000,1003,1004],{"name":934,"slug":935,"type":16},{"name":1001,"slug":1002,"type":16},"Data Analysis","data-analysis",{"name":943,"slug":944,"type":16},{"name":1005,"slug":1006,"type":16},"KPI","kpi","2026-07-12T08:39:59.54971",150,{"items":1010,"total":1105},[1011,1029,1042,1056,1069,1082,1095],{"slug":1012,"name":1012,"fn":1013,"description":1014,"org":1015,"tags":1016,"stars":26,"repoUrl":27,"updatedAt":1028},"aws-genai-ml-architect","design AWS GenAI and ML architectures","Reasoning skill for designing AWS GenAI and ML architectures for healthcare and life sciences workloads. Use when the user asks to choose between SageMaker and Bedrock, design a RAG system over medical literature, architect clinical NLP or medical imaging inference, plan genomics or drug discovery pipelines on AWS, address HIPAA\u002FPHI compliance in ML systems, design MLOps for regulated clinical models, or optimize cost for HCLS ML workloads. Triggers include \"AWS architecture\", \"SageMaker vs Bedrock\", \"HIPAA ML\", \"clinical RAG\", \"medical imaging inference\", \"genomics on AWS\", \"PHI training\", \"MLOps healthcare\", \"Bedrock guardrails\", \"HealthLake\", \"HCLS cloud architecture\", \"BAA compliance\", \"SageMaker endpoint\", \"Bedrock knowledge base\", \"clinical NLP on AWS\", \"FDA SaMD on AWS\".",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1017,1020,1021,1024,1025],{"name":1018,"slug":1019,"type":16},"Architecture","architecture",{"name":24,"slug":25,"type":16},{"name":1022,"slug":1023,"type":16},"Healthcare","healthcare",{"name":14,"slug":15,"type":16},{"name":1026,"slug":1027,"type":16},"LLM","llm","2026-07-12T08:38:07.975937",{"slug":1030,"name":1030,"fn":1031,"description":1032,"org":1033,"tags":1034,"stars":26,"repoUrl":27,"updatedAt":1041},"biomarker-discovery","guide biomarker discovery and validation","Reason about biomarker discovery and validation in HCLS — classifying biomarker intent, choosing feature-selection and cross-validation strategies, avoiding leakage, and planning external replication. Use when the user asks to discover, develop, or validate a biomarker; select features from high-dimensional omics or clinical data; design a validation study; choose evaluation metrics; justify sample size; combine multi-omics signals; or assess clinical utility. Triggers include \"discover a biomarker\", \"validate biomarker\", \"prognostic vs predictive\", \"feature selection\", \"LASSO vs elastic net\", \"nested cross-validation\", \"data leakage\", \"C-index\", \"time-dependent AUC\", \"decision curve analysis\", \"external validation cohort\", \"events per variable\", \"optimism-corrected\", \"multi-omics integration\", \"clinical utility of a biomarker\", \"is this biomarker ready\".",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1035,1036,1037,1038],{"name":24,"slug":25,"type":16},{"name":18,"slug":19,"type":16},{"name":14,"slug":15,"type":16},{"name":1039,"slug":1040,"type":16},"Research","research","2026-07-12T08:37:49.295301",{"slug":1043,"name":1043,"fn":1044,"description":1045,"org":1046,"tags":1047,"stars":26,"repoUrl":27,"updatedAt":1055},"cdisc-compliance","reason about CDISC SDTM and ADaM implementation","Reason about CDISC SDTM and ADaM implementation for regulatory submissions. Use when the user asks about SDTM domain mapping, ADaM dataset design, controlled terminology versioning, define.xml completeness, FDA or PMDA submission requirements, query prioritization by clinical impact, SUPPQUAL usage, or CDISC compliance review. Triggers include \"SDTM mapping\", \"ADaM dataset\", \"CDISC compliance\", \"controlled terminology\", \"define.xml\", \"FDA submission data\", \"PMDA submission\", \"SDTM domain\", \"ADSL\", \"ADAE\", \"ADLB\", \"BDS structure\", \"SUPPQUAL\", \"RELREC\", \"value-level metadata\", \"CDISC CT\", \"regulatory submission data standards\", \"eCTD datasets\", \"SDTM 3.3\", \"ADaM 1.1\", \"query prioritization\", \"clinical data review\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1048,1051,1052],{"name":1049,"slug":1050,"type":16},"Clinical Trials","clinical-trials",{"name":14,"slug":15,"type":16},{"name":1053,"slug":1054,"type":16},"Regulatory Compliance","regulatory-compliance","2026-07-12T08:37:33.35594",{"slug":1057,"name":1057,"fn":1058,"description":1059,"org":1060,"tags":1061,"stars":26,"repoUrl":27,"updatedAt":1068},"cell-type-annotation","annotate single-cell RNA-seq clusters","Generate code to assign cell type labels to single-cell RNA-seq clusters using CellTypist, SingleR, marker-based annotation, or reference label transfer (scANVI\u002Fingest). Triggers on requests to \"annotate cell types\", \"label clusters\", \"run CellTypist\", \"SingleR annotation\", \"marker gene dotplot\", \"transfer labels from reference atlas\", \"cell identity\", \"automated annotation\", \"reference mapping\", \"scANVI label transfer\", \"canonical markers\", \"immune cell types\", \"hierarchical annotation\", \"majority voting CellTypist\", \"over-clustering annotation\".",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1062,1063,1064,1065],{"name":18,"slug":19,"type":16},{"name":1001,"slug":1002,"type":16},{"name":14,"slug":15,"type":16},{"name":1066,"slug":1067,"type":16},"RNA-seq","rna-seq","2026-07-12T08:38:05.443454",{"slug":1070,"name":1070,"fn":1071,"description":1072,"org":1073,"tags":1074,"stars":26,"repoUrl":27,"updatedAt":1081},"cheminformatics","calculate molecular properties with RDKit","Cheminformatics pipeline for small-molecule property calculation, filtering, and similarity analysis using RDKit. Use when the user asks to compute molecular descriptors, filter compounds by Lipinski or Veber rules, detect PAINS, calculate fingerprint similarity, run matched molecular pair analysis, generate ADMET descriptors, or process SMILES. Triggers include \"RDKit\", \"molecular descriptors\", \"Lipinski\", \"rule of five\", \"Veber\", \"PAINS\", \"pan-assay interference\", \"Morgan fingerprint\", \"Tanimoto\", \"fingerprint similarity\", \"matched molecular pair\", \"MMP\", \"mmpdb\", \"ADMET\", \"druglikeness\", \"SMILES\", \"cheminformatics\", \"compound filtering\", \"chemical similarity\".",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1075,1076,1079,1080],{"name":18,"slug":19,"type":16},{"name":1077,"slug":1078,"type":16},"Chemistry","chemistry",{"name":1001,"slug":1002,"type":16},{"name":1039,"slug":1040,"type":16},"2026-07-12T08:37:28.334619",{"slug":1083,"name":1083,"fn":1084,"description":1085,"org":1086,"tags":1087,"stars":26,"repoUrl":27,"updatedAt":1094},"claims-analytics","analyze and parse healthcare claims data","Pipeline skill for healthcare claims data parsing, analysis, and fraud detection. Use when the user asks to parse X12 837 or 835 claim files, manipulate ICD-10 CPT or HCPCS codes, detect billing pattern anomalies, profile providers against specialty peers, identify outlier billing behavior, validate NCCI edits programmatically, detect duplicate claims, run Benford's law analysis on charges, build claims data pipelines, or analyze E&M code distributions. Triggers include \"parse X12 837\", \"parse 835\", \"claims SQL\", \"ICD-10 manipulation\", \"CPT code analysis\", \"provider profiling\", \"billing outlier\", \"NCCI validation code\", \"duplicate claim detection\", \"Benford's law charges\", \"claims ETL\", \"E&M distribution analysis\", \"claims analytics pipeline\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1088,1089,1090,1093],{"name":1001,"slug":1002,"type":16},{"name":1022,"slug":1023,"type":16},{"name":1091,"slug":1092,"type":16},"Insurance","insurance",{"name":14,"slug":15,"type":16},"2026-07-12T08:37:34.815088",{"slug":1096,"name":1096,"fn":1097,"description":1098,"org":1099,"tags":1100,"stars":26,"repoUrl":27,"updatedAt":1104},"claims-billing-rules","analyze healthcare claims billing rules","Reasoning skill for healthcare claims billing rules and fraud detection logic. Use when the user asks about CMS billing rules, place of service codes, global surgery periods, modifier usage (25 59 76 77), NCCI edit logic, column 1 column 2 code pairs, mutually exclusive procedures, modifier indicators, fraud waste and abuse patterns, E&M upcoding, unbundling, phantom billing, impossible day detection, coding error versus fraud distinction, FWA investigation methodology, or claims audit logic. Triggers include \"CMS billing rules\", \"NCCI edits\", \"modifier 25\", \"modifier 59\", \"global surgery period\", \"upcoding\", \"unbundling\", \"phantom billing\", \"impossible day\", \"FWA\", \"fraud waste abuse\", \"coding error vs fraud\", \"claims audit\", \"billing compliance\", \"E&M level selection\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1101,1102,1103],{"name":1022,"slug":1023,"type":16},{"name":1091,"slug":1092,"type":16},{"name":1053,"slug":1054,"type":16},"2026-07-12T08:38:28.210856",40]