[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-aws-labs-rna-seq-analysis":3,"mdc-ei4nyw-key":49,"related-org-aws-labs-rna-seq-analysis":816,"related-repo-aws-labs-rna-seq-analysis":996},{"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},"rna-seq-analysis","analyze bulk RNA-seq data","Bulk RNA-seq analysis pipeline covering alignment (STAR), quantification (Salmon, featureCounts), and differential expression (DESeq2). Triggers on RNA-seq, STAR, Salmon, DESeq2, differential expression, gene expression, tximport, featureCounts, transcriptomics, \"bulk RNA-seq\", \"STAR alignment\", \"Salmon quantification\", \"gene counts\", \"DESeq2 results\", \"shrinkage estimator\", \"volcano plot RNA-seq\".",{"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},"RNA-seq","rna-seq",{"name":24,"slug":25,"type":16},"AWS","aws",4,"https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fhcls-agent-skills","2026-07-12T08:38:26.929687",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\u002Frna-seq-analysis","---\nname: rna-seq-analysis\ndescription: Bulk RNA-seq analysis pipeline covering alignment (STAR), quantification (Salmon, featureCounts), and differential expression (DESeq2). Triggers on RNA-seq, STAR, Salmon, DESeq2, differential expression, gene expression, tximport, featureCounts, transcriptomics, \"bulk RNA-seq\", \"STAR alignment\", \"Salmon quantification\", \"gene counts\", \"DESeq2 results\", \"shrinkage estimator\", \"volcano plot RNA-seq\".\nusage: Invoke when running bulk RNA-seq alignment, quantification, or differential expression analysis with STAR, Salmon, or DESeq2.\nversion: 1.0.0\nvalidated_against:\n  date: 2025-01-15\n  packages: {star: \"2.7.11\", salmon: \"1.10\", deseq2: \"1.42\"}\ntags: [skill, category:pipeline, genomics, rna-seq, star, deseq2, differential-expression, hcls]\n---\n\n# RNA-seq Analysis — Pipeline Skill (Thin Scaffold)\n\n## Overview\n\nAdds decision logic for choosing quantification paths (STAR vs Salmon), strandedness determination, and DESeq2 modeling pitfalls that LLMs routinely get wrong.\n\n## Usage\n\n- Activate when choosing between alignment-based (STAR+featureCounts) vs alignment-free (Salmon) quantification\n- Activate when setting up DESeq2 from either count source\n- Activate when debugging unexpected low counts or weak DE signal\n\n## Core Concepts\n\n## Decision Logic\n\n```\nNeed BAMs? (variant calling, fusions, novel transcripts)\n├── YES → STAR two-pass + featureCounts\n└── NO → Salmon (faster, lower RAM, bias-corrected)\n\nSalmon output → DESeq2:\n└── Use DESeqDataSetFromTximport (preserves length offset)\n    └── NEVER round txi$counts and pass to DESeqDataSetFromMatrix\n\nFiltering strategy (VQSR equivalent):\n├── ≥30 samples → VQSR-like (default DESeq2 shrinkage works well)\n└── \u003C30 samples → still works, but pre-filter aggressively\n```\n\n**Strandedness determination (MUST verify before counting):**\n\n| Kit | featureCounts `-s` | Salmon `-l` |\n|-----|-------------------|-------------|\n| TruSeq Stranded \u002F dUTP | 2 | ISR (PE) \u002F SR (SE) |\n| Ligation \u002F forward | 1 | ISF \u002F SF |\n| Unstranded | 0 | IU \u002F U |\n\nVerify with: `infer_experiment.py` (RSeQC) or Salmon's `lib_format_counts.json`.\n\n## Critical Parameters\n\n| Parameter | Value | When to change |\n|-----------|-------|----------------|\n| `--sjdbOverhang` | readLength - 1 (default 100) | Non-100bp reads |\n| `--twopassMode Basic` | Always for DE | Skip only for speed in QC runs |\n| Salmon `--gcBias --seqBias` | Always on | Never skip for Illumina |\n| Salmon `--validateMappings` | Always on | Enables selective alignment |\n| featureCounts `-s` | Kit-dependent | ALWAYS verify empirically |\n| DESeq2 pre-filter | `rowSums(counts >= 10) >= smallest_group` | Adjust 10 for shallow sequencing |\n| `lfcShrink type` | `\"apeglm\"` | Use `\"ashr\"` for arbitrary contrasts |\n| Design formula | `~ batch + condition` (interest LAST) | Always put interest term last |\n\n## Common Mistakes\n\n- **Wrong:** Guessing strandedness (`-s`) instead of verifying empirically\n  **Right:** Check with `infer_experiment.py` or Salmon `lib_format_counts.json` before running featureCounts\n  **Why:** Wrong strandedness causes 2–10× lower counts and weak DE signal\n\n- **Wrong:** Passing normalized counts (TPM, FPKM, CPM) to DESeq2\n  **Right:** Always start from raw integer counts\n  **Why:** Normalized values break the negative-binomial model\n\n- **Wrong:** Rounding `txi$counts` and passing to `DESeqDataSetFromMatrix`\n  **Right:** Use `DESeqDataSetFromTximport(txi, ...)` which preserves the length offset\n  **Why:** Rounding discards per-gene length correction for transcript-length bias\n\n- **Wrong:** Placing variable of interest first in design (`~ condition + batch`)\n  **Right:** Put interest last: `~ batch + condition`\n  **Why:** DESeq2 tests the last term by default\n\n- **Wrong:** Assuming DESeq2 reorders samples to match\n  **Right:** Assert `stopifnot(all(colnames(cts) == rownames(coldata)))` before creating DESeq object\n  **Why:** DESeq2 silently mislabels samples if order doesn't match\n\n- **Wrong:** Skipping pre-filtering of low-count genes\n  **Right:** Filter with `rowSums(counts(dds) >= 10) >= smallest_group_size`\n  **Why:** Near-zero genes inflate runtime and dilute multiple-testing correction\n\n- **Wrong:** Using STAR `ReadsPerGene.out.tab` column 2 for stranded libraries\n  **Right:** Use column 3 (forward) or column 4 (reverse) matching your kit\n  **Why:** Column 2 is unstranded; using it for stranded data halves effective counts\n\n- **Wrong:** Including samples with \u003C10M mapped reads or \u003C70% mapping rate\n  **Right:** Exclude or flag before fitting\n  **Why:** Low-quality samples distort size factors and dispersion estimates\n\n- **Wrong:** Modeling when batch is perfectly confounded with condition\n  **Right:** Check `table(coldata$batch, coldata$condition)` first\n  **Why:** No statistical model can separate perfectly correlated effects\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":66},{"name":4,"description":6,"usage":51,"version":52,"validated_against":53,"tags":59},"Invoke when running bulk RNA-seq alignment, quantification, or differential expression analysis with STAR, Salmon, or DESeq2.","1.0.0",{"date":54,"packages":55},"2025-01-15",{"star":56,"salmon":57,"deseq2":58},"2.7.11","1.10","1.42",[60,61,38,22,62,63,64,65],"skill","category:pipeline","star","deseq2","differential-expression","hcls",{"type":67,"children":68},"root",[69,78,85,91,97,117,123,129,142,151,250,271,277,495,501,782,788],{"type":70,"tag":71,"props":72,"children":74},"element","h1",{"id":73},"rna-seq-analysis-pipeline-skill-thin-scaffold",[75],{"type":76,"value":77},"text","RNA-seq Analysis — Pipeline Skill (Thin Scaffold)",{"type":70,"tag":79,"props":80,"children":82},"h2",{"id":81},"overview",[83],{"type":76,"value":84},"Overview",{"type":70,"tag":86,"props":87,"children":88},"p",{},[89],{"type":76,"value":90},"Adds decision logic for choosing quantification paths (STAR vs Salmon), strandedness determination, and DESeq2 modeling pitfalls that LLMs routinely get wrong.",{"type":70,"tag":79,"props":92,"children":94},{"id":93},"usage",[95],{"type":76,"value":96},"Usage",{"type":70,"tag":98,"props":99,"children":100},"ul",{},[101,107,112],{"type":70,"tag":102,"props":103,"children":104},"li",{},[105],{"type":76,"value":106},"Activate when choosing between alignment-based (STAR+featureCounts) vs alignment-free (Salmon) quantification",{"type":70,"tag":102,"props":108,"children":109},{},[110],{"type":76,"value":111},"Activate when setting up DESeq2 from either count source",{"type":70,"tag":102,"props":113,"children":114},{},[115],{"type":76,"value":116},"Activate when debugging unexpected low counts or weak DE signal",{"type":70,"tag":79,"props":118,"children":120},{"id":119},"core-concepts",[121],{"type":76,"value":122},"Core Concepts",{"type":70,"tag":79,"props":124,"children":126},{"id":125},"decision-logic",[127],{"type":76,"value":128},"Decision Logic",{"type":70,"tag":130,"props":131,"children":135},"pre",{"className":132,"code":134,"language":76},[133],"language-text","Need BAMs? (variant calling, fusions, novel transcripts)\n├── YES → STAR two-pass + featureCounts\n└── NO → Salmon (faster, lower RAM, bias-corrected)\n\nSalmon output → DESeq2:\n└── Use DESeqDataSetFromTximport (preserves length offset)\n    └── NEVER round txi$counts and pass to DESeqDataSetFromMatrix\n\nFiltering strategy (VQSR equivalent):\n├── ≥30 samples → VQSR-like (default DESeq2 shrinkage works well)\n└── \u003C30 samples → still works, but pre-filter aggressively\n",[136],{"type":70,"tag":137,"props":138,"children":140},"code",{"__ignoreMap":139},"",[141],{"type":76,"value":134},{"type":70,"tag":86,"props":143,"children":144},{},[145],{"type":70,"tag":146,"props":147,"children":148},"strong",{},[149],{"type":76,"value":150},"Strandedness determination (MUST verify before counting):",{"type":70,"tag":152,"props":153,"children":154},"table",{},[155,191],{"type":70,"tag":156,"props":157,"children":158},"thead",{},[159],{"type":70,"tag":160,"props":161,"children":162},"tr",{},[163,169,180],{"type":70,"tag":164,"props":165,"children":166},"th",{},[167],{"type":76,"value":168},"Kit",{"type":70,"tag":164,"props":170,"children":171},{},[172,174],{"type":76,"value":173},"featureCounts ",{"type":70,"tag":137,"props":175,"children":177},{"className":176},[],[178],{"type":76,"value":179},"-s",{"type":70,"tag":164,"props":181,"children":182},{},[183,185],{"type":76,"value":184},"Salmon ",{"type":70,"tag":137,"props":186,"children":188},{"className":187},[],[189],{"type":76,"value":190},"-l",{"type":70,"tag":192,"props":193,"children":194},"tbody",{},[195,214,232],{"type":70,"tag":160,"props":196,"children":197},{},[198,204,209],{"type":70,"tag":199,"props":200,"children":201},"td",{},[202],{"type":76,"value":203},"TruSeq Stranded \u002F dUTP",{"type":70,"tag":199,"props":205,"children":206},{},[207],{"type":76,"value":208},"2",{"type":70,"tag":199,"props":210,"children":211},{},[212],{"type":76,"value":213},"ISR (PE) \u002F SR (SE)",{"type":70,"tag":160,"props":215,"children":216},{},[217,222,227],{"type":70,"tag":199,"props":218,"children":219},{},[220],{"type":76,"value":221},"Ligation \u002F forward",{"type":70,"tag":199,"props":223,"children":224},{},[225],{"type":76,"value":226},"1",{"type":70,"tag":199,"props":228,"children":229},{},[230],{"type":76,"value":231},"ISF \u002F SF",{"type":70,"tag":160,"props":233,"children":234},{},[235,240,245],{"type":70,"tag":199,"props":236,"children":237},{},[238],{"type":76,"value":239},"Unstranded",{"type":70,"tag":199,"props":241,"children":242},{},[243],{"type":76,"value":244},"0",{"type":70,"tag":199,"props":246,"children":247},{},[248],{"type":76,"value":249},"IU \u002F U",{"type":70,"tag":86,"props":251,"children":252},{},[253,255,261,263,269],{"type":76,"value":254},"Verify with: ",{"type":70,"tag":137,"props":256,"children":258},{"className":257},[],[259],{"type":76,"value":260},"infer_experiment.py",{"type":76,"value":262}," (RSeQC) or Salmon's ",{"type":70,"tag":137,"props":264,"children":266},{"className":265},[],[267],{"type":76,"value":268},"lib_format_counts.json",{"type":76,"value":270},".",{"type":70,"tag":79,"props":272,"children":274},{"id":273},"critical-parameters",[275],{"type":76,"value":276},"Critical Parameters",{"type":70,"tag":152,"props":278,"children":279},{},[280,301],{"type":70,"tag":156,"props":281,"children":282},{},[283],{"type":70,"tag":160,"props":284,"children":285},{},[286,291,296],{"type":70,"tag":164,"props":287,"children":288},{},[289],{"type":76,"value":290},"Parameter",{"type":70,"tag":164,"props":292,"children":293},{},[294],{"type":76,"value":295},"Value",{"type":70,"tag":164,"props":297,"children":298},{},[299],{"type":76,"value":300},"When to change",{"type":70,"tag":192,"props":302,"children":303},{},[304,326,348,371,393,415,437,471],{"type":70,"tag":160,"props":305,"children":306},{},[307,316,321],{"type":70,"tag":199,"props":308,"children":309},{},[310],{"type":70,"tag":137,"props":311,"children":313},{"className":312},[],[314],{"type":76,"value":315},"--sjdbOverhang",{"type":70,"tag":199,"props":317,"children":318},{},[319],{"type":76,"value":320},"readLength - 1 (default 100)",{"type":70,"tag":199,"props":322,"children":323},{},[324],{"type":76,"value":325},"Non-100bp reads",{"type":70,"tag":160,"props":327,"children":328},{},[329,338,343],{"type":70,"tag":199,"props":330,"children":331},{},[332],{"type":70,"tag":137,"props":333,"children":335},{"className":334},[],[336],{"type":76,"value":337},"--twopassMode Basic",{"type":70,"tag":199,"props":339,"children":340},{},[341],{"type":76,"value":342},"Always for DE",{"type":70,"tag":199,"props":344,"children":345},{},[346],{"type":76,"value":347},"Skip only for speed in QC runs",{"type":70,"tag":160,"props":349,"children":350},{},[351,361,366],{"type":70,"tag":199,"props":352,"children":353},{},[354,355],{"type":76,"value":184},{"type":70,"tag":137,"props":356,"children":358},{"className":357},[],[359],{"type":76,"value":360},"--gcBias --seqBias",{"type":70,"tag":199,"props":362,"children":363},{},[364],{"type":76,"value":365},"Always on",{"type":70,"tag":199,"props":367,"children":368},{},[369],{"type":76,"value":370},"Never skip for Illumina",{"type":70,"tag":160,"props":372,"children":373},{},[374,384,388],{"type":70,"tag":199,"props":375,"children":376},{},[377,378],{"type":76,"value":184},{"type":70,"tag":137,"props":379,"children":381},{"className":380},[],[382],{"type":76,"value":383},"--validateMappings",{"type":70,"tag":199,"props":385,"children":386},{},[387],{"type":76,"value":365},{"type":70,"tag":199,"props":389,"children":390},{},[391],{"type":76,"value":392},"Enables selective alignment",{"type":70,"tag":160,"props":394,"children":395},{},[396,405,410],{"type":70,"tag":199,"props":397,"children":398},{},[399,400],{"type":76,"value":173},{"type":70,"tag":137,"props":401,"children":403},{"className":402},[],[404],{"type":76,"value":179},{"type":70,"tag":199,"props":406,"children":407},{},[408],{"type":76,"value":409},"Kit-dependent",{"type":70,"tag":199,"props":411,"children":412},{},[413],{"type":76,"value":414},"ALWAYS verify empirically",{"type":70,"tag":160,"props":416,"children":417},{},[418,423,432],{"type":70,"tag":199,"props":419,"children":420},{},[421],{"type":76,"value":422},"DESeq2 pre-filter",{"type":70,"tag":199,"props":424,"children":425},{},[426],{"type":70,"tag":137,"props":427,"children":429},{"className":428},[],[430],{"type":76,"value":431},"rowSums(counts >= 10) >= smallest_group",{"type":70,"tag":199,"props":433,"children":434},{},[435],{"type":76,"value":436},"Adjust 10 for shallow sequencing",{"type":70,"tag":160,"props":438,"children":439},{},[440,449,458],{"type":70,"tag":199,"props":441,"children":442},{},[443],{"type":70,"tag":137,"props":444,"children":446},{"className":445},[],[447],{"type":76,"value":448},"lfcShrink type",{"type":70,"tag":199,"props":450,"children":451},{},[452],{"type":70,"tag":137,"props":453,"children":455},{"className":454},[],[456],{"type":76,"value":457},"\"apeglm\"",{"type":70,"tag":199,"props":459,"children":460},{},[461,463,469],{"type":76,"value":462},"Use ",{"type":70,"tag":137,"props":464,"children":466},{"className":465},[],[467],{"type":76,"value":468},"\"ashr\"",{"type":76,"value":470}," for arbitrary contrasts",{"type":70,"tag":160,"props":472,"children":473},{},[474,479,490],{"type":70,"tag":199,"props":475,"children":476},{},[477],{"type":76,"value":478},"Design formula",{"type":70,"tag":199,"props":480,"children":481},{},[482,488],{"type":70,"tag":137,"props":483,"children":485},{"className":484},[],[486],{"type":76,"value":487},"~ batch + condition",{"type":76,"value":489}," (interest LAST)",{"type":70,"tag":199,"props":491,"children":492},{},[493],{"type":76,"value":494},"Always put interest term last",{"type":70,"tag":79,"props":496,"children":498},{"id":497},"common-mistakes",[499],{"type":76,"value":500},"Common Mistakes",{"type":70,"tag":98,"props":502,"children":503},{},[504,549,570,613,647,676,703,732,753],{"type":70,"tag":102,"props":505,"children":506},{},[507,512,514,519,521,526,528,533,535,540,542,547],{"type":70,"tag":146,"props":508,"children":509},{},[510],{"type":76,"value":511},"Wrong:",{"type":76,"value":513}," Guessing strandedness (",{"type":70,"tag":137,"props":515,"children":517},{"className":516},[],[518],{"type":76,"value":179},{"type":76,"value":520},") instead of verifying empirically\n",{"type":70,"tag":146,"props":522,"children":523},{},[524],{"type":76,"value":525},"Right:",{"type":76,"value":527}," Check with ",{"type":70,"tag":137,"props":529,"children":531},{"className":530},[],[532],{"type":76,"value":260},{"type":76,"value":534}," or Salmon ",{"type":70,"tag":137,"props":536,"children":538},{"className":537},[],[539],{"type":76,"value":268},{"type":76,"value":541}," before running featureCounts\n",{"type":70,"tag":146,"props":543,"children":544},{},[545],{"type":76,"value":546},"Why:",{"type":76,"value":548}," Wrong strandedness causes 2–10× lower counts and weak DE signal",{"type":70,"tag":102,"props":550,"children":551},{},[552,556,558,562,564,568],{"type":70,"tag":146,"props":553,"children":554},{},[555],{"type":76,"value":511},{"type":76,"value":557}," Passing normalized counts (TPM, FPKM, CPM) to DESeq2\n",{"type":70,"tag":146,"props":559,"children":560},{},[561],{"type":76,"value":525},{"type":76,"value":563}," Always start from raw integer counts\n",{"type":70,"tag":146,"props":565,"children":566},{},[567],{"type":76,"value":546},{"type":76,"value":569}," Normalized values break the negative-binomial model",{"type":70,"tag":102,"props":571,"children":572},{},[573,577,579,585,587,593,597,599,605,607,611],{"type":70,"tag":146,"props":574,"children":575},{},[576],{"type":76,"value":511},{"type":76,"value":578}," Rounding ",{"type":70,"tag":137,"props":580,"children":582},{"className":581},[],[583],{"type":76,"value":584},"txi$counts",{"type":76,"value":586}," and passing to ",{"type":70,"tag":137,"props":588,"children":590},{"className":589},[],[591],{"type":76,"value":592},"DESeqDataSetFromMatrix",{"type":70,"tag":146,"props":594,"children":595},{},[596],{"type":76,"value":525},{"type":76,"value":598}," Use ",{"type":70,"tag":137,"props":600,"children":602},{"className":601},[],[603],{"type":76,"value":604},"DESeqDataSetFromTximport(txi, ...)",{"type":76,"value":606}," which preserves the length offset\n",{"type":70,"tag":146,"props":608,"children":609},{},[610],{"type":76,"value":546},{"type":76,"value":612}," Rounding discards per-gene length correction for transcript-length bias",{"type":70,"tag":102,"props":614,"children":615},{},[616,620,622,628,630,634,636,641,645],{"type":70,"tag":146,"props":617,"children":618},{},[619],{"type":76,"value":511},{"type":76,"value":621}," Placing variable of interest first in design (",{"type":70,"tag":137,"props":623,"children":625},{"className":624},[],[626],{"type":76,"value":627},"~ condition + batch",{"type":76,"value":629},")\n",{"type":70,"tag":146,"props":631,"children":632},{},[633],{"type":76,"value":525},{"type":76,"value":635}," Put interest last: ",{"type":70,"tag":137,"props":637,"children":639},{"className":638},[],[640],{"type":76,"value":487},{"type":70,"tag":146,"props":642,"children":643},{},[644],{"type":76,"value":546},{"type":76,"value":646}," DESeq2 tests the last term by default",{"type":70,"tag":102,"props":648,"children":649},{},[650,654,656,660,662,668,670,674],{"type":70,"tag":146,"props":651,"children":652},{},[653],{"type":76,"value":511},{"type":76,"value":655}," Assuming DESeq2 reorders samples to match\n",{"type":70,"tag":146,"props":657,"children":658},{},[659],{"type":76,"value":525},{"type":76,"value":661}," Assert ",{"type":70,"tag":137,"props":663,"children":665},{"className":664},[],[666],{"type":76,"value":667},"stopifnot(all(colnames(cts) == rownames(coldata)))",{"type":76,"value":669}," before creating DESeq object\n",{"type":70,"tag":146,"props":671,"children":672},{},[673],{"type":76,"value":546},{"type":76,"value":675}," DESeq2 silently mislabels samples if order doesn't match",{"type":70,"tag":102,"props":677,"children":678},{},[679,683,685,689,691,697,701],{"type":70,"tag":146,"props":680,"children":681},{},[682],{"type":76,"value":511},{"type":76,"value":684}," Skipping pre-filtering of low-count genes\n",{"type":70,"tag":146,"props":686,"children":687},{},[688],{"type":76,"value":525},{"type":76,"value":690}," Filter with ",{"type":70,"tag":137,"props":692,"children":694},{"className":693},[],[695],{"type":76,"value":696},"rowSums(counts(dds) >= 10) >= smallest_group_size",{"type":70,"tag":146,"props":698,"children":699},{},[700],{"type":76,"value":546},{"type":76,"value":702}," Near-zero genes inflate runtime and dilute multiple-testing correction",{"type":70,"tag":102,"props":704,"children":705},{},[706,710,712,718,720,724,726,730],{"type":70,"tag":146,"props":707,"children":708},{},[709],{"type":76,"value":511},{"type":76,"value":711}," Using STAR ",{"type":70,"tag":137,"props":713,"children":715},{"className":714},[],[716],{"type":76,"value":717},"ReadsPerGene.out.tab",{"type":76,"value":719}," column 2 for stranded libraries\n",{"type":70,"tag":146,"props":721,"children":722},{},[723],{"type":76,"value":525},{"type":76,"value":725}," Use column 3 (forward) or column 4 (reverse) matching your kit\n",{"type":70,"tag":146,"props":727,"children":728},{},[729],{"type":76,"value":546},{"type":76,"value":731}," Column 2 is unstranded; using it for stranded data halves effective counts",{"type":70,"tag":102,"props":733,"children":734},{},[735,739,741,745,747,751],{"type":70,"tag":146,"props":736,"children":737},{},[738],{"type":76,"value":511},{"type":76,"value":740}," Including samples with \u003C10M mapped reads or \u003C70% mapping rate\n",{"type":70,"tag":146,"props":742,"children":743},{},[744],{"type":76,"value":525},{"type":76,"value":746}," Exclude or flag before fitting\n",{"type":70,"tag":146,"props":748,"children":749},{},[750],{"type":76,"value":546},{"type":76,"value":752}," Low-quality samples distort size factors and dispersion estimates",{"type":70,"tag":102,"props":754,"children":755},{},[756,760,762,766,768,774,776,780],{"type":70,"tag":146,"props":757,"children":758},{},[759],{"type":76,"value":511},{"type":76,"value":761}," Modeling when batch is perfectly confounded with condition\n",{"type":70,"tag":146,"props":763,"children":764},{},[765],{"type":76,"value":525},{"type":76,"value":767}," Check ",{"type":70,"tag":137,"props":769,"children":771},{"className":770},[],[772],{"type":76,"value":773},"table(coldata$batch, coldata$condition)",{"type":76,"value":775}," first\n",{"type":70,"tag":146,"props":777,"children":778},{},[779],{"type":76,"value":546},{"type":76,"value":781}," No statistical model can separate perfectly correlated effects",{"type":70,"tag":79,"props":783,"children":785},{"id":784},"response-format",[786],{"type":76,"value":787},"Response Format",{"type":70,"tag":98,"props":789,"children":790},{},[791,796,801,806,811],{"type":70,"tag":102,"props":792,"children":793},{},[794],{"type":76,"value":795},"Lead with the command or code the user needs — explain after",{"type":70,"tag":102,"props":797,"children":798},{},[799],{"type":76,"value":800},"Structure as: confirm inputs → working code → key parameters explained → gotchas",{"type":70,"tag":102,"props":802,"children":803},{},[804],{"type":76,"value":805},"One complete working example per task; do not show every alternative",{"type":70,"tag":102,"props":807,"children":808},{},[809],{"type":76,"value":810},"Keep code comments minimal and functional (what, not why-it-exists)",{"type":70,"tag":102,"props":812,"children":813},{},[814],{"type":76,"value":815},"Target: 50-100 lines of code with brief surrounding explanation",{"items":817,"total":995},[818,837,858,868,881,894,904,914,935,950,965,980],{"slug":819,"name":819,"fn":820,"description":821,"org":822,"tags":823,"stars":834,"repoUrl":835,"updatedAt":836},"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},[824,825,828,831],{"name":24,"slug":25,"type":16},{"name":826,"slug":827,"type":16},"Debugging","debugging",{"name":829,"slug":830,"type":16},"Logs","logs",{"name":832,"slug":833,"type":16},"Observability","observability",9427,"https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fmcp","2026-07-12T08:37:22.601527",{"slug":838,"name":839,"fn":840,"description":841,"org":842,"tags":843,"stars":834,"repoUrl":835,"updatedAt":857},"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},[844,847,848,851,854],{"name":845,"slug":846,"type":16},"Aurora","aurora",{"name":24,"slug":25,"type":16},{"name":849,"slug":850,"type":16},"Database","database",{"name":852,"slug":853,"type":16},"Serverless","serverless",{"name":855,"slug":856,"type":16},"SQL","sql","2026-07-12T08:36:45.053393",{"slug":859,"name":860,"fn":840,"description":841,"org":861,"tags":862,"stars":834,"repoUrl":835,"updatedAt":867},"aurora-dsql","aurora dsql",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[863,864,865,866],{"name":24,"slug":25,"type":16},{"name":849,"slug":850,"type":16},{"name":852,"slug":853,"type":16},{"name":855,"slug":856,"type":16},"2026-07-12T08:36:42.694299",{"slug":869,"name":870,"fn":840,"description":841,"org":871,"tags":872,"stars":834,"repoUrl":835,"updatedAt":880},"aws-dsql","aws dsql",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[873,874,875,878,879],{"name":24,"slug":25,"type":16},{"name":849,"slug":850,"type":16},{"name":876,"slug":877,"type":16},"Migration","migration",{"name":852,"slug":853,"type":16},{"name":855,"slug":856,"type":16},"2026-07-12T08:36:38.584057",{"slug":882,"name":883,"fn":840,"description":841,"org":884,"tags":885,"stars":834,"repoUrl":835,"updatedAt":893},"distributed-postgres","distributed postgres",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[886,887,888,891,892],{"name":24,"slug":25,"type":16},{"name":849,"slug":850,"type":16},{"name":889,"slug":890,"type":16},"PostgreSQL","postgresql",{"name":852,"slug":853,"type":16},{"name":855,"slug":856,"type":16},"2026-07-12T08:36:46.530743",{"slug":895,"name":896,"fn":840,"description":841,"org":897,"tags":898,"stars":834,"repoUrl":835,"updatedAt":903},"distributed-sql","distributed sql",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[899,900,901,902],{"name":24,"slug":25,"type":16},{"name":849,"slug":850,"type":16},{"name":852,"slug":853,"type":16},{"name":855,"slug":856,"type":16},"2026-07-12T08:36:48.104182",{"slug":905,"name":905,"fn":840,"description":841,"org":906,"tags":907,"stars":834,"repoUrl":835,"updatedAt":913},"dsql",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[908,909,910,911,912],{"name":24,"slug":25,"type":16},{"name":849,"slug":850,"type":16},{"name":876,"slug":877,"type":16},{"name":852,"slug":853,"type":16},{"name":855,"slug":856,"type":16},"2026-07-12T08:36:36.374512",{"slug":915,"name":915,"fn":916,"description":917,"org":918,"tags":919,"stars":932,"repoUrl":933,"updatedAt":934},"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},[920,923,926,929],{"name":921,"slug":922,"type":16},"Accounting","accounting",{"name":924,"slug":925,"type":16},"Analytics","analytics",{"name":927,"slug":928,"type":16},"Cost Optimization","cost-optimization",{"name":930,"slug":931,"type":16},"Finance","finance",3176,"https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fagentcore-samples","2026-07-12T08:40:03.29555",{"slug":936,"name":936,"fn":937,"description":938,"org":939,"tags":940,"stars":932,"repoUrl":933,"updatedAt":949},"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},[941,942,943,946],{"name":24,"slug":25,"type":16},{"name":930,"slug":931,"type":16},{"name":944,"slug":945,"type":16},"Management","management",{"name":947,"slug":948,"type":16},"Reporting","reporting","2026-07-12T08:40:02.066471",{"slug":951,"name":951,"fn":952,"description":953,"org":954,"tags":955,"stars":932,"repoUrl":933,"updatedAt":964},"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},[956,957,958,961],{"name":924,"slug":925,"type":16},{"name":930,"slug":931,"type":16},{"name":959,"slug":960,"type":16},"Financial Statements","financial-statements",{"name":962,"slug":963,"type":16},"Variance Analysis","variance-analysis","2026-07-12T08:40:00.79141",{"slug":966,"name":966,"fn":967,"description":968,"org":969,"tags":970,"stars":932,"repoUrl":933,"updatedAt":979},"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},[971,974,977],{"name":972,"slug":973,"type":16},"Automation","automation",{"name":975,"slug":976,"type":16},"Documents","documents",{"name":978,"slug":966,"type":16},"PDF","2026-07-12T08:41:44.135656",{"slug":981,"name":981,"fn":982,"description":983,"org":984,"tags":985,"stars":932,"repoUrl":933,"updatedAt":994},"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},[986,987,990,991],{"name":921,"slug":922,"type":16},{"name":988,"slug":989,"type":16},"Data Analysis","data-analysis",{"name":930,"slug":931,"type":16},{"name":992,"slug":993,"type":16},"KPI","kpi","2026-07-12T08:39:59.54971",150,{"items":997,"total":1090},[998,1016,1029,1043,1054,1067,1080],{"slug":999,"name":999,"fn":1000,"description":1001,"org":1002,"tags":1003,"stars":26,"repoUrl":27,"updatedAt":1015},"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},[1004,1007,1008,1011,1012],{"name":1005,"slug":1006,"type":16},"Architecture","architecture",{"name":24,"slug":25,"type":16},{"name":1009,"slug":1010,"type":16},"Healthcare","healthcare",{"name":14,"slug":15,"type":16},{"name":1013,"slug":1014,"type":16},"LLM","llm","2026-07-12T08:38:07.975937",{"slug":1017,"name":1017,"fn":1018,"description":1019,"org":1020,"tags":1021,"stars":26,"repoUrl":27,"updatedAt":1028},"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},[1022,1023,1024,1025],{"name":24,"slug":25,"type":16},{"name":18,"slug":19,"type":16},{"name":14,"slug":15,"type":16},{"name":1026,"slug":1027,"type":16},"Research","research","2026-07-12T08:37:49.295301",{"slug":1030,"name":1030,"fn":1031,"description":1032,"org":1033,"tags":1034,"stars":26,"repoUrl":27,"updatedAt":1042},"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},[1035,1038,1039],{"name":1036,"slug":1037,"type":16},"Clinical Trials","clinical-trials",{"name":14,"slug":15,"type":16},{"name":1040,"slug":1041,"type":16},"Regulatory Compliance","regulatory-compliance","2026-07-12T08:37:33.35594",{"slug":1044,"name":1044,"fn":1045,"description":1046,"org":1047,"tags":1048,"stars":26,"repoUrl":27,"updatedAt":1053},"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},[1049,1050,1051,1052],{"name":18,"slug":19,"type":16},{"name":988,"slug":989,"type":16},{"name":14,"slug":15,"type":16},{"name":21,"slug":22,"type":16},"2026-07-12T08:38:05.443454",{"slug":1055,"name":1055,"fn":1056,"description":1057,"org":1058,"tags":1059,"stars":26,"repoUrl":27,"updatedAt":1066},"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},[1060,1061,1064,1065],{"name":18,"slug":19,"type":16},{"name":1062,"slug":1063,"type":16},"Chemistry","chemistry",{"name":988,"slug":989,"type":16},{"name":1026,"slug":1027,"type":16},"2026-07-12T08:37:28.334619",{"slug":1068,"name":1068,"fn":1069,"description":1070,"org":1071,"tags":1072,"stars":26,"repoUrl":27,"updatedAt":1079},"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},[1073,1074,1075,1078],{"name":988,"slug":989,"type":16},{"name":1009,"slug":1010,"type":16},{"name":1076,"slug":1077,"type":16},"Insurance","insurance",{"name":14,"slug":15,"type":16},"2026-07-12T08:37:34.815088",{"slug":1081,"name":1081,"fn":1082,"description":1083,"org":1084,"tags":1085,"stars":26,"repoUrl":27,"updatedAt":1089},"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},[1086,1087,1088],{"name":1009,"slug":1010,"type":16},{"name":1076,"slug":1077,"type":16},{"name":1040,"slug":1041,"type":16},"2026-07-12T08:38:28.210856",40]