[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-aws-labs-risk-stratification-indices":3,"mdc--my9dkd-key":50,"related-org-aws-labs-risk-stratification-indices":789,"related-repo-aws-labs-risk-stratification-indices":969},{"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":45,"sourceUrl":48,"mdContent":49},"risk-stratification-indices","calculate clinical risk stratification indices","Reasoning skill for clinical risk stratification index selection and interpretation. Use when the user asks about LACE scores, Charlson Comorbidity Index, Elixhauser Index, readmission risk scoring, comorbidity weighting, SDOH Z-codes, Area Deprivation Index, or population health stratification methods.\n",{"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},"Healthcare","healthcare","tag",{"name":18,"slug":19,"type":16},"Clinical Trials","clinical-trials",{"name":21,"slug":22,"type":16},"Data Analysis","data-analysis",{"name":24,"slug":25,"type":16},"Statistics","statistics",4,"https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fhcls-agent-skills","2026-07-12T08:38:31.693663",null,0,[32,33,34,35,36,37,38,39,40,41,42,43,44],"agent-skills","agentcore","ai-agents","amazon-quick-desktop","claims-processing","drug-discovery","genomics","healthcare-ai","kiro","life-sciences","medical-imaging","risk-adjustment","strands-agents",{"repoUrl":27,"stars":26,"forks":30,"topics":46,"description":47},[32,33,34,35,36,37,38,39,40,41,42,43,44],"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\u002Frisk-stratification-indices","---\nname: risk-stratification-indices\ndescription: >\n  Reasoning skill for clinical risk stratification index selection and interpretation. Use when\n  the user asks about LACE scores, Charlson Comorbidity Index, Elixhauser Index, readmission\n  risk scoring, comorbidity weighting, SDOH Z-codes, Area Deprivation Index, or population\n  health stratification methods.\nusage: Use when selecting, calculating, or interpreting clinical risk stratification indices or incorporating SDOH factors.\nversion: 1.0.0\ntags: [skill, category:reasoning, risk-stratification, comorbidity, hcls]\ntriggers:\n  - LACE score\n  - Charlson\n  - Elixhauser\n  - risk stratification\n  - SDOH Z-codes\n  - ADI\n  - readmission risk\n  - comorbidity index\n  - risk score\n  - population health stratification\n---\n\n# Risk Stratification Indices Reasoning\n\n## Overview\n\nGuide selection and interpretation of clinical risk stratification indices (LACE, Charlson, Elixhauser) and SDOH factors (Z-codes, ADI) for population health management. Based on validated scoring systems from peer-reviewed literature.\n\n## Usage\n\n- Activate when selecting a risk stratification index for a specific use case (readmission, mortality, utilization)\n- Activate when interpreting LACE, Charlson, or Elixhauser scores\n- Activate when incorporating SDOH factors (Z-codes, ADI) into population health stratification\n\n## Core Concepts\n\n## Response Format\n\nApply scoring logic internally. Present the recommended index with justification, scoring interpretation, and risk tier. Do not narrate the full scoring calculation unless asked.\n\n## 1. Choosing a Risk Stratification Method\n\n```\nWhat is the use case?\n├── 30-day readmission prediction\n│   └── Use LACE index (designed for readmission)\n├── Long-term mortality risk adjustment\n│   └── Use Charlson Comorbidity Index\n├── Hospital resource utilization \u002F cost prediction\n│   └── Use Elixhauser Comorbidity Index\n├── Medicare risk adjustment (payment)\n│   └── Use CMS-HCC (Hierarchical Condition Categories)\n└── Population health stratification\n    └── Combine clinical risk (Charlson\u002FElixhauser) + SDOH factors\n```\n\n## 2. LACE Index (Readmission Risk)\n\n| Component | Scoring | Range |\n|-----------|---------|-------|\n| **L** — Length of stay | 1d=1, 2d=2, 3d=3, 4–6d=4, 7–13d=5, ≥14d=7 | 0–7 |\n| **A** — Acuity of admission | Emergent=3, Urgent=2, Elective=0 | 0–3 |\n| **C** — Comorbidity (Charlson) | 0=0, 1=1, 2=2, 3=3, ≥4=5 | 0–5 |\n| **E** — ED visits (prior 6 months) | 0=0, 1=1, 2=2, 3=3, ≥4=4 | 0–4 |\n| **Total** | Sum of L+A+C+E | 0–19 |\n\n**Risk tiers:** Low (0–4), Moderate (5–9), High (10+)\n\n## 3. Charlson Comorbidity Index\n\n17 conditions with integer weights:\n\n- **Weight 1:** MI, CHF, PVD, CVD, dementia, COPD, connective tissue disease, peptic ulcer, mild liver disease, uncomplicated diabetes\n- **Weight 2:** complicated diabetes, hemiplegia, renal disease, non-metastatic cancer\n- **Weight 3:** moderate\u002Fsevere liver disease\n- **Weight 6:** metastatic tumor, AIDS\u002FHIV\n\nTotal score = sum of all applicable weights.\n\n## 4. Elixhauser Comorbidity Index\n\n| Attribute | Charlson | Elixhauser |\n|-----------|----------|------------|\n| Conditions | 17 | 31 |\n| Weighting | Fixed integer | Varies by model (van Walraven common) |\n| Scope | Mortality prediction | Mortality + resource use |\n| Mental health | Limited (dementia only) | Depression, psychoses, substance use |\n| Best for | Long-term mortality | Hospital utilization, readmission |\n\n## 5. SDOH Risk Factors\n\n### ICD-10 Z-Codes for SDOH\n\nKey ranges: Z55 (education\u002Fliteracy), Z56 (employment), Z57 (occupational exposure), Z59 (housing\u002Feconomic — Z59.0 homelessness, Z59.41 food insecurity), Z60 (social environment), Z62 (upbringing\u002Fabuse), Z63 (family circumstances), Z65 (psychosocial\u002Flegal).\n\n### Area Deprivation Index (ADI)\n\n| ADI Percentile | Risk Level | Implication |\n|---------------|------------|-------------|\n| 1–25 | Low deprivation | Standard outreach sufficient |\n| 26–50 | Moderate | Enhanced reminder systems |\n| 51–75 | High | Care coordination, transportation assistance |\n| 76–100 | Very high | Intensive outreach, community health workers |\n\n### Incorporating SDOH into Stratification\n\nWeight members higher when:\n1. Any SDOH Z-code documented in claims\n2. High ADI score (≥51st percentile)\n3. Dual-eligible status (Medicare + Medicaid)\n4. Language barrier (non-English preferred)\n5. No PCP visit in 12 months (care disengagement)\n\n## Common Mistakes\n\n- **Wrong:** Using Charlson for readmission prediction → **Right:** Use LACE (purpose-built for 30-day readmission)\n- **Wrong:** Using Elixhauser for long-term mortality → **Right:** Use Charlson (validated for mortality prediction)\n- **Wrong:** Ignoring SDOH factors in population stratification → **Right:** Combine clinical index + SDOH for actionable tiers\n- **Wrong:** Applying same outreach to all risk tiers → **Right:** Tailor interventions by barrier type (transportation, literacy, engagement)\n- **Wrong:** Using ADI alone without clinical risk → **Right:** ADI indicates access barriers; combine with clinical severity for full picture\n- **Wrong:** Treating all Z-codes as equivalent risk signals → **Right:** Weight by relevance to the specific outcome (e.g., Z59.0 homelessness is higher barrier than Z56 employment)\n\n## When to Escalate\n\n- When risk scores drive reimbursement or payment decisions (requires validated, audited implementation)\n- When stratification results will determine resource allocation across populations\n- When combining indices in novel ways not validated in literature\n",{"data":51,"body":71},{"name":4,"description":6,"usage":52,"version":53,"tags":54,"triggers":60},"Use when selecting, calculating, or interpreting clinical risk stratification indices or incorporating SDOH factors.","1.0.0",[55,56,57,58,59],"skill","category:reasoning","risk-stratification","comorbidity","hcls",[61,62,63,64,65,66,67,68,69,70],"LACE score","Charlson","Elixhauser","risk stratification","SDOH Z-codes","ADI","readmission risk","comorbidity index","risk score","population health stratification",{"type":72,"children":73},"root",[74,83,90,96,102,122,128,134,139,145,158,164,311,321,327,332,375,380,386,501,507,514,519,525,624,630,635,664,670,765,771],{"type":75,"tag":76,"props":77,"children":79},"element","h1",{"id":78},"risk-stratification-indices-reasoning",[80],{"type":81,"value":82},"text","Risk Stratification Indices Reasoning",{"type":75,"tag":84,"props":85,"children":87},"h2",{"id":86},"overview",[88],{"type":81,"value":89},"Overview",{"type":75,"tag":91,"props":92,"children":93},"p",{},[94],{"type":81,"value":95},"Guide selection and interpretation of clinical risk stratification indices (LACE, Charlson, Elixhauser) and SDOH factors (Z-codes, ADI) for population health management. Based on validated scoring systems from peer-reviewed literature.",{"type":75,"tag":84,"props":97,"children":99},{"id":98},"usage",[100],{"type":81,"value":101},"Usage",{"type":75,"tag":103,"props":104,"children":105},"ul",{},[106,112,117],{"type":75,"tag":107,"props":108,"children":109},"li",{},[110],{"type":81,"value":111},"Activate when selecting a risk stratification index for a specific use case (readmission, mortality, utilization)",{"type":75,"tag":107,"props":113,"children":114},{},[115],{"type":81,"value":116},"Activate when interpreting LACE, Charlson, or Elixhauser scores",{"type":75,"tag":107,"props":118,"children":119},{},[120],{"type":81,"value":121},"Activate when incorporating SDOH factors (Z-codes, ADI) into population health stratification",{"type":75,"tag":84,"props":123,"children":125},{"id":124},"core-concepts",[126],{"type":81,"value":127},"Core Concepts",{"type":75,"tag":84,"props":129,"children":131},{"id":130},"response-format",[132],{"type":81,"value":133},"Response Format",{"type":75,"tag":91,"props":135,"children":136},{},[137],{"type":81,"value":138},"Apply scoring logic internally. Present the recommended index with justification, scoring interpretation, and risk tier. Do not narrate the full scoring calculation unless asked.",{"type":75,"tag":84,"props":140,"children":142},{"id":141},"_1-choosing-a-risk-stratification-method",[143],{"type":81,"value":144},"1. Choosing a Risk Stratification Method",{"type":75,"tag":146,"props":147,"children":151},"pre",{"className":148,"code":150,"language":81},[149],"language-text","What is the use case?\n├── 30-day readmission prediction\n│   └── Use LACE index (designed for readmission)\n├── Long-term mortality risk adjustment\n│   └── Use Charlson Comorbidity Index\n├── Hospital resource utilization \u002F cost prediction\n│   └── Use Elixhauser Comorbidity Index\n├── Medicare risk adjustment (payment)\n│   └── Use CMS-HCC (Hierarchical Condition Categories)\n└── Population health stratification\n    └── Combine clinical risk (Charlson\u002FElixhauser) + SDOH factors\n",[152],{"type":75,"tag":153,"props":154,"children":156},"code",{"__ignoreMap":155},"",[157],{"type":81,"value":150},{"type":75,"tag":84,"props":159,"children":161},{"id":160},"_2-lace-index-readmission-risk",[162],{"type":81,"value":163},"2. LACE Index (Readmission Risk)",{"type":75,"tag":165,"props":166,"children":167},"table",{},[168,192],{"type":75,"tag":169,"props":170,"children":171},"thead",{},[172],{"type":75,"tag":173,"props":174,"children":175},"tr",{},[176,182,187],{"type":75,"tag":177,"props":178,"children":179},"th",{},[180],{"type":81,"value":181},"Component",{"type":75,"tag":177,"props":183,"children":184},{},[185],{"type":81,"value":186},"Scoring",{"type":75,"tag":177,"props":188,"children":189},{},[190],{"type":81,"value":191},"Range",{"type":75,"tag":193,"props":194,"children":195},"tbody",{},[196,221,244,267,290],{"type":75,"tag":173,"props":197,"children":198},{},[199,211,216],{"type":75,"tag":200,"props":201,"children":202},"td",{},[203,209],{"type":75,"tag":204,"props":205,"children":206},"strong",{},[207],{"type":81,"value":208},"L",{"type":81,"value":210}," — Length of stay",{"type":75,"tag":200,"props":212,"children":213},{},[214],{"type":81,"value":215},"1d=1, 2d=2, 3d=3, 4–6d=4, 7–13d=5, ≥14d=7",{"type":75,"tag":200,"props":217,"children":218},{},[219],{"type":81,"value":220},"0–7",{"type":75,"tag":173,"props":222,"children":223},{},[224,234,239],{"type":75,"tag":200,"props":225,"children":226},{},[227,232],{"type":75,"tag":204,"props":228,"children":229},{},[230],{"type":81,"value":231},"A",{"type":81,"value":233}," — Acuity of admission",{"type":75,"tag":200,"props":235,"children":236},{},[237],{"type":81,"value":238},"Emergent=3, Urgent=2, Elective=0",{"type":75,"tag":200,"props":240,"children":241},{},[242],{"type":81,"value":243},"0–3",{"type":75,"tag":173,"props":245,"children":246},{},[247,257,262],{"type":75,"tag":200,"props":248,"children":249},{},[250,255],{"type":75,"tag":204,"props":251,"children":252},{},[253],{"type":81,"value":254},"C",{"type":81,"value":256}," — Comorbidity (Charlson)",{"type":75,"tag":200,"props":258,"children":259},{},[260],{"type":81,"value":261},"0=0, 1=1, 2=2, 3=3, ≥4=5",{"type":75,"tag":200,"props":263,"children":264},{},[265],{"type":81,"value":266},"0–5",{"type":75,"tag":173,"props":268,"children":269},{},[270,280,285],{"type":75,"tag":200,"props":271,"children":272},{},[273,278],{"type":75,"tag":204,"props":274,"children":275},{},[276],{"type":81,"value":277},"E",{"type":81,"value":279}," — ED visits (prior 6 months)",{"type":75,"tag":200,"props":281,"children":282},{},[283],{"type":81,"value":284},"0=0, 1=1, 2=2, 3=3, ≥4=4",{"type":75,"tag":200,"props":286,"children":287},{},[288],{"type":81,"value":289},"0–4",{"type":75,"tag":173,"props":291,"children":292},{},[293,301,306],{"type":75,"tag":200,"props":294,"children":295},{},[296],{"type":75,"tag":204,"props":297,"children":298},{},[299],{"type":81,"value":300},"Total",{"type":75,"tag":200,"props":302,"children":303},{},[304],{"type":81,"value":305},"Sum of L+A+C+E",{"type":75,"tag":200,"props":307,"children":308},{},[309],{"type":81,"value":310},"0–19",{"type":75,"tag":91,"props":312,"children":313},{},[314,319],{"type":75,"tag":204,"props":315,"children":316},{},[317],{"type":81,"value":318},"Risk tiers:",{"type":81,"value":320}," Low (0–4), Moderate (5–9), High (10+)",{"type":75,"tag":84,"props":322,"children":324},{"id":323},"_3-charlson-comorbidity-index",[325],{"type":81,"value":326},"3. Charlson Comorbidity Index",{"type":75,"tag":91,"props":328,"children":329},{},[330],{"type":81,"value":331},"17 conditions with integer weights:",{"type":75,"tag":103,"props":333,"children":334},{},[335,345,355,365],{"type":75,"tag":107,"props":336,"children":337},{},[338,343],{"type":75,"tag":204,"props":339,"children":340},{},[341],{"type":81,"value":342},"Weight 1:",{"type":81,"value":344}," MI, CHF, PVD, CVD, dementia, COPD, connective tissue disease, peptic ulcer, mild liver disease, uncomplicated diabetes",{"type":75,"tag":107,"props":346,"children":347},{},[348,353],{"type":75,"tag":204,"props":349,"children":350},{},[351],{"type":81,"value":352},"Weight 2:",{"type":81,"value":354}," complicated diabetes, hemiplegia, renal disease, non-metastatic cancer",{"type":75,"tag":107,"props":356,"children":357},{},[358,363],{"type":75,"tag":204,"props":359,"children":360},{},[361],{"type":81,"value":362},"Weight 3:",{"type":81,"value":364}," moderate\u002Fsevere liver disease",{"type":75,"tag":107,"props":366,"children":367},{},[368,373],{"type":75,"tag":204,"props":369,"children":370},{},[371],{"type":81,"value":372},"Weight 6:",{"type":81,"value":374}," metastatic tumor, AIDS\u002FHIV",{"type":75,"tag":91,"props":376,"children":377},{},[378],{"type":81,"value":379},"Total score = sum of all applicable weights.",{"type":75,"tag":84,"props":381,"children":383},{"id":382},"_4-elixhauser-comorbidity-index",[384],{"type":81,"value":385},"4. Elixhauser Comorbidity Index",{"type":75,"tag":165,"props":387,"children":388},{},[389,408],{"type":75,"tag":169,"props":390,"children":391},{},[392],{"type":75,"tag":173,"props":393,"children":394},{},[395,400,404],{"type":75,"tag":177,"props":396,"children":397},{},[398],{"type":81,"value":399},"Attribute",{"type":75,"tag":177,"props":401,"children":402},{},[403],{"type":81,"value":62},{"type":75,"tag":177,"props":405,"children":406},{},[407],{"type":81,"value":63},{"type":75,"tag":193,"props":409,"children":410},{},[411,429,447,465,483],{"type":75,"tag":173,"props":412,"children":413},{},[414,419,424],{"type":75,"tag":200,"props":415,"children":416},{},[417],{"type":81,"value":418},"Conditions",{"type":75,"tag":200,"props":420,"children":421},{},[422],{"type":81,"value":423},"17",{"type":75,"tag":200,"props":425,"children":426},{},[427],{"type":81,"value":428},"31",{"type":75,"tag":173,"props":430,"children":431},{},[432,437,442],{"type":75,"tag":200,"props":433,"children":434},{},[435],{"type":81,"value":436},"Weighting",{"type":75,"tag":200,"props":438,"children":439},{},[440],{"type":81,"value":441},"Fixed integer",{"type":75,"tag":200,"props":443,"children":444},{},[445],{"type":81,"value":446},"Varies by model (van Walraven common)",{"type":75,"tag":173,"props":448,"children":449},{},[450,455,460],{"type":75,"tag":200,"props":451,"children":452},{},[453],{"type":81,"value":454},"Scope",{"type":75,"tag":200,"props":456,"children":457},{},[458],{"type":81,"value":459},"Mortality prediction",{"type":75,"tag":200,"props":461,"children":462},{},[463],{"type":81,"value":464},"Mortality + resource use",{"type":75,"tag":173,"props":466,"children":467},{},[468,473,478],{"type":75,"tag":200,"props":469,"children":470},{},[471],{"type":81,"value":472},"Mental health",{"type":75,"tag":200,"props":474,"children":475},{},[476],{"type":81,"value":477},"Limited (dementia only)",{"type":75,"tag":200,"props":479,"children":480},{},[481],{"type":81,"value":482},"Depression, psychoses, substance use",{"type":75,"tag":173,"props":484,"children":485},{},[486,491,496],{"type":75,"tag":200,"props":487,"children":488},{},[489],{"type":81,"value":490},"Best for",{"type":75,"tag":200,"props":492,"children":493},{},[494],{"type":81,"value":495},"Long-term mortality",{"type":75,"tag":200,"props":497,"children":498},{},[499],{"type":81,"value":500},"Hospital utilization, readmission",{"type":75,"tag":84,"props":502,"children":504},{"id":503},"_5-sdoh-risk-factors",[505],{"type":81,"value":506},"5. SDOH Risk Factors",{"type":75,"tag":508,"props":509,"children":511},"h3",{"id":510},"icd-10-z-codes-for-sdoh",[512],{"type":81,"value":513},"ICD-10 Z-Codes for SDOH",{"type":75,"tag":91,"props":515,"children":516},{},[517],{"type":81,"value":518},"Key ranges: Z55 (education\u002Fliteracy), Z56 (employment), Z57 (occupational exposure), Z59 (housing\u002Feconomic — Z59.0 homelessness, Z59.41 food insecurity), Z60 (social environment), Z62 (upbringing\u002Fabuse), Z63 (family circumstances), Z65 (psychosocial\u002Flegal).",{"type":75,"tag":508,"props":520,"children":522},{"id":521},"area-deprivation-index-adi",[523],{"type":81,"value":524},"Area Deprivation Index (ADI)",{"type":75,"tag":165,"props":526,"children":527},{},[528,549],{"type":75,"tag":169,"props":529,"children":530},{},[531],{"type":75,"tag":173,"props":532,"children":533},{},[534,539,544],{"type":75,"tag":177,"props":535,"children":536},{},[537],{"type":81,"value":538},"ADI Percentile",{"type":75,"tag":177,"props":540,"children":541},{},[542],{"type":81,"value":543},"Risk Level",{"type":75,"tag":177,"props":545,"children":546},{},[547],{"type":81,"value":548},"Implication",{"type":75,"tag":193,"props":550,"children":551},{},[552,570,588,606],{"type":75,"tag":173,"props":553,"children":554},{},[555,560,565],{"type":75,"tag":200,"props":556,"children":557},{},[558],{"type":81,"value":559},"1–25",{"type":75,"tag":200,"props":561,"children":562},{},[563],{"type":81,"value":564},"Low deprivation",{"type":75,"tag":200,"props":566,"children":567},{},[568],{"type":81,"value":569},"Standard outreach sufficient",{"type":75,"tag":173,"props":571,"children":572},{},[573,578,583],{"type":75,"tag":200,"props":574,"children":575},{},[576],{"type":81,"value":577},"26–50",{"type":75,"tag":200,"props":579,"children":580},{},[581],{"type":81,"value":582},"Moderate",{"type":75,"tag":200,"props":584,"children":585},{},[586],{"type":81,"value":587},"Enhanced reminder systems",{"type":75,"tag":173,"props":589,"children":590},{},[591,596,601],{"type":75,"tag":200,"props":592,"children":593},{},[594],{"type":81,"value":595},"51–75",{"type":75,"tag":200,"props":597,"children":598},{},[599],{"type":81,"value":600},"High",{"type":75,"tag":200,"props":602,"children":603},{},[604],{"type":81,"value":605},"Care coordination, transportation assistance",{"type":75,"tag":173,"props":607,"children":608},{},[609,614,619],{"type":75,"tag":200,"props":610,"children":611},{},[612],{"type":81,"value":613},"76–100",{"type":75,"tag":200,"props":615,"children":616},{},[617],{"type":81,"value":618},"Very high",{"type":75,"tag":200,"props":620,"children":621},{},[622],{"type":81,"value":623},"Intensive outreach, community health workers",{"type":75,"tag":508,"props":625,"children":627},{"id":626},"incorporating-sdoh-into-stratification",[628],{"type":81,"value":629},"Incorporating SDOH into Stratification",{"type":75,"tag":91,"props":631,"children":632},{},[633],{"type":81,"value":634},"Weight members higher when:",{"type":75,"tag":636,"props":637,"children":638},"ol",{},[639,644,649,654,659],{"type":75,"tag":107,"props":640,"children":641},{},[642],{"type":81,"value":643},"Any SDOH Z-code documented in claims",{"type":75,"tag":107,"props":645,"children":646},{},[647],{"type":81,"value":648},"High ADI score (≥51st percentile)",{"type":75,"tag":107,"props":650,"children":651},{},[652],{"type":81,"value":653},"Dual-eligible status (Medicare + Medicaid)",{"type":75,"tag":107,"props":655,"children":656},{},[657],{"type":81,"value":658},"Language barrier (non-English preferred)",{"type":75,"tag":107,"props":660,"children":661},{},[662],{"type":81,"value":663},"No PCP visit in 12 months (care disengagement)",{"type":75,"tag":84,"props":665,"children":667},{"id":666},"common-mistakes",[668],{"type":81,"value":669},"Common Mistakes",{"type":75,"tag":103,"props":671,"children":672},{},[673,690,705,720,735,750],{"type":75,"tag":107,"props":674,"children":675},{},[676,681,683,688],{"type":75,"tag":204,"props":677,"children":678},{},[679],{"type":81,"value":680},"Wrong:",{"type":81,"value":682}," Using Charlson for readmission prediction → ",{"type":75,"tag":204,"props":684,"children":685},{},[686],{"type":81,"value":687},"Right:",{"type":81,"value":689}," Use LACE (purpose-built for 30-day readmission)",{"type":75,"tag":107,"props":691,"children":692},{},[693,697,699,703],{"type":75,"tag":204,"props":694,"children":695},{},[696],{"type":81,"value":680},{"type":81,"value":698}," Using Elixhauser for long-term mortality → ",{"type":75,"tag":204,"props":700,"children":701},{},[702],{"type":81,"value":687},{"type":81,"value":704}," Use Charlson (validated for mortality prediction)",{"type":75,"tag":107,"props":706,"children":707},{},[708,712,714,718],{"type":75,"tag":204,"props":709,"children":710},{},[711],{"type":81,"value":680},{"type":81,"value":713}," Ignoring SDOH factors in population stratification → ",{"type":75,"tag":204,"props":715,"children":716},{},[717],{"type":81,"value":687},{"type":81,"value":719}," Combine clinical index + SDOH for actionable tiers",{"type":75,"tag":107,"props":721,"children":722},{},[723,727,729,733],{"type":75,"tag":204,"props":724,"children":725},{},[726],{"type":81,"value":680},{"type":81,"value":728}," Applying same outreach to all risk tiers → ",{"type":75,"tag":204,"props":730,"children":731},{},[732],{"type":81,"value":687},{"type":81,"value":734}," Tailor interventions by barrier type (transportation, literacy, engagement)",{"type":75,"tag":107,"props":736,"children":737},{},[738,742,744,748],{"type":75,"tag":204,"props":739,"children":740},{},[741],{"type":81,"value":680},{"type":81,"value":743}," Using ADI alone without clinical risk → ",{"type":75,"tag":204,"props":745,"children":746},{},[747],{"type":81,"value":687},{"type":81,"value":749}," ADI indicates access barriers; combine with clinical severity for full picture",{"type":75,"tag":107,"props":751,"children":752},{},[753,757,759,763],{"type":75,"tag":204,"props":754,"children":755},{},[756],{"type":81,"value":680},{"type":81,"value":758}," Treating all Z-codes as equivalent risk signals → ",{"type":75,"tag":204,"props":760,"children":761},{},[762],{"type":81,"value":687},{"type":81,"value":764}," Weight by relevance to the specific outcome (e.g., Z59.0 homelessness is higher barrier than Z56 employment)",{"type":75,"tag":84,"props":766,"children":768},{"id":767},"when-to-escalate",[769],{"type":81,"value":770},"When to Escalate",{"type":75,"tag":103,"props":772,"children":773},{},[774,779,784],{"type":75,"tag":107,"props":775,"children":776},{},[777],{"type":81,"value":778},"When risk scores drive reimbursement or payment decisions (requires validated, audited implementation)",{"type":75,"tag":107,"props":780,"children":781},{},[782],{"type":81,"value":783},"When stratification results will determine resource allocation across populations",{"type":75,"tag":107,"props":785,"children":786},{},[787],{"type":81,"value":788},"When combining indices in novel ways not validated in literature",{"items":790,"total":968},[791,812,833,843,856,869,879,889,910,925,940,955],{"slug":792,"name":792,"fn":793,"description":794,"org":795,"tags":796,"stars":809,"repoUrl":810,"updatedAt":811},"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},[797,800,803,806],{"name":798,"slug":799,"type":16},"AWS","aws",{"name":801,"slug":802,"type":16},"Debugging","debugging",{"name":804,"slug":805,"type":16},"Logs","logs",{"name":807,"slug":808,"type":16},"Observability","observability",9427,"https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fmcp","2026-07-12T08:37:22.601527",{"slug":813,"name":814,"fn":815,"description":816,"org":817,"tags":818,"stars":809,"repoUrl":810,"updatedAt":832},"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},[819,822,823,826,829],{"name":820,"slug":821,"type":16},"Aurora","aurora",{"name":798,"slug":799,"type":16},{"name":824,"slug":825,"type":16},"Database","database",{"name":827,"slug":828,"type":16},"Serverless","serverless",{"name":830,"slug":831,"type":16},"SQL","sql","2026-07-12T08:36:45.053393",{"slug":834,"name":835,"fn":815,"description":816,"org":836,"tags":837,"stars":809,"repoUrl":810,"updatedAt":842},"aurora-dsql","aurora dsql",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[838,839,840,841],{"name":798,"slug":799,"type":16},{"name":824,"slug":825,"type":16},{"name":827,"slug":828,"type":16},{"name":830,"slug":831,"type":16},"2026-07-12T08:36:42.694299",{"slug":844,"name":845,"fn":815,"description":816,"org":846,"tags":847,"stars":809,"repoUrl":810,"updatedAt":855},"aws-dsql","aws dsql",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[848,849,850,853,854],{"name":798,"slug":799,"type":16},{"name":824,"slug":825,"type":16},{"name":851,"slug":852,"type":16},"Migration","migration",{"name":827,"slug":828,"type":16},{"name":830,"slug":831,"type":16},"2026-07-12T08:36:38.584057",{"slug":857,"name":858,"fn":815,"description":816,"org":859,"tags":860,"stars":809,"repoUrl":810,"updatedAt":868},"distributed-postgres","distributed postgres",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[861,862,863,866,867],{"name":798,"slug":799,"type":16},{"name":824,"slug":825,"type":16},{"name":864,"slug":865,"type":16},"PostgreSQL","postgresql",{"name":827,"slug":828,"type":16},{"name":830,"slug":831,"type":16},"2026-07-12T08:36:46.530743",{"slug":870,"name":871,"fn":815,"description":816,"org":872,"tags":873,"stars":809,"repoUrl":810,"updatedAt":878},"distributed-sql","distributed sql",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[874,875,876,877],{"name":798,"slug":799,"type":16},{"name":824,"slug":825,"type":16},{"name":827,"slug":828,"type":16},{"name":830,"slug":831,"type":16},"2026-07-12T08:36:48.104182",{"slug":880,"name":880,"fn":815,"description":816,"org":881,"tags":882,"stars":809,"repoUrl":810,"updatedAt":888},"dsql",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[883,884,885,886,887],{"name":798,"slug":799,"type":16},{"name":824,"slug":825,"type":16},{"name":851,"slug":852,"type":16},{"name":827,"slug":828,"type":16},{"name":830,"slug":831,"type":16},"2026-07-12T08:36:36.374512",{"slug":890,"name":890,"fn":891,"description":892,"org":893,"tags":894,"stars":907,"repoUrl":908,"updatedAt":909},"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},[895,898,901,904],{"name":896,"slug":897,"type":16},"Accounting","accounting",{"name":899,"slug":900,"type":16},"Analytics","analytics",{"name":902,"slug":903,"type":16},"Cost Optimization","cost-optimization",{"name":905,"slug":906,"type":16},"Finance","finance",3176,"https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fagentcore-samples","2026-07-12T08:40:03.29555",{"slug":911,"name":911,"fn":912,"description":913,"org":914,"tags":915,"stars":907,"repoUrl":908,"updatedAt":924},"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},[916,917,918,921],{"name":798,"slug":799,"type":16},{"name":905,"slug":906,"type":16},{"name":919,"slug":920,"type":16},"Management","management",{"name":922,"slug":923,"type":16},"Reporting","reporting","2026-07-12T08:40:02.066471",{"slug":926,"name":926,"fn":927,"description":928,"org":929,"tags":930,"stars":907,"repoUrl":908,"updatedAt":939},"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},[931,932,933,936],{"name":899,"slug":900,"type":16},{"name":905,"slug":906,"type":16},{"name":934,"slug":935,"type":16},"Financial Statements","financial-statements",{"name":937,"slug":938,"type":16},"Variance Analysis","variance-analysis","2026-07-12T08:40:00.79141",{"slug":941,"name":941,"fn":942,"description":943,"org":944,"tags":945,"stars":907,"repoUrl":908,"updatedAt":954},"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},[946,949,952],{"name":947,"slug":948,"type":16},"Automation","automation",{"name":950,"slug":951,"type":16},"Documents","documents",{"name":953,"slug":941,"type":16},"PDF","2026-07-12T08:41:44.135656",{"slug":956,"name":956,"fn":957,"description":958,"org":959,"tags":960,"stars":907,"repoUrl":908,"updatedAt":967},"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},[961,962,963,964],{"name":896,"slug":897,"type":16},{"name":21,"slug":22,"type":16},{"name":905,"slug":906,"type":16},{"name":965,"slug":966,"type":16},"KPI","kpi","2026-07-12T08:39:59.54971",150,{"items":970,"total":1064},[971,988,1003,1015,1028,1041,1054],{"slug":972,"name":972,"fn":973,"description":974,"org":975,"tags":976,"stars":26,"repoUrl":27,"updatedAt":987},"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},[977,980,981,982,984],{"name":978,"slug":979,"type":16},"Architecture","architecture",{"name":798,"slug":799,"type":16},{"name":14,"slug":15,"type":16},{"name":983,"slug":41,"type":16},"Life Sciences",{"name":985,"slug":986,"type":16},"LLM","llm","2026-07-12T08:38:07.975937",{"slug":989,"name":989,"fn":990,"description":991,"org":992,"tags":993,"stars":26,"repoUrl":27,"updatedAt":1002},"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},[994,995,998,999],{"name":798,"slug":799,"type":16},{"name":996,"slug":997,"type":16},"Bioinformatics","bioinformatics",{"name":983,"slug":41,"type":16},{"name":1000,"slug":1001,"type":16},"Research","research","2026-07-12T08:37:49.295301",{"slug":1004,"name":1004,"fn":1005,"description":1006,"org":1007,"tags":1008,"stars":26,"repoUrl":27,"updatedAt":1014},"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},[1009,1010,1011],{"name":18,"slug":19,"type":16},{"name":983,"slug":41,"type":16},{"name":1012,"slug":1013,"type":16},"Regulatory Compliance","regulatory-compliance","2026-07-12T08:37:33.35594",{"slug":1016,"name":1016,"fn":1017,"description":1018,"org":1019,"tags":1020,"stars":26,"repoUrl":27,"updatedAt":1027},"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},[1021,1022,1023,1024],{"name":996,"slug":997,"type":16},{"name":21,"slug":22,"type":16},{"name":983,"slug":41,"type":16},{"name":1025,"slug":1026,"type":16},"RNA-seq","rna-seq","2026-07-12T08:38:05.443454",{"slug":1029,"name":1029,"fn":1030,"description":1031,"org":1032,"tags":1033,"stars":26,"repoUrl":27,"updatedAt":1040},"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},[1034,1035,1038,1039],{"name":996,"slug":997,"type":16},{"name":1036,"slug":1037,"type":16},"Chemistry","chemistry",{"name":21,"slug":22,"type":16},{"name":1000,"slug":1001,"type":16},"2026-07-12T08:37:28.334619",{"slug":1042,"name":1042,"fn":1043,"description":1044,"org":1045,"tags":1046,"stars":26,"repoUrl":27,"updatedAt":1053},"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},[1047,1048,1049,1052],{"name":21,"slug":22,"type":16},{"name":14,"slug":15,"type":16},{"name":1050,"slug":1051,"type":16},"Insurance","insurance",{"name":983,"slug":41,"type":16},"2026-07-12T08:37:34.815088",{"slug":1055,"name":1055,"fn":1056,"description":1057,"org":1058,"tags":1059,"stars":26,"repoUrl":27,"updatedAt":1063},"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},[1060,1061,1062],{"name":14,"slug":15,"type":16},{"name":1050,"slug":1051,"type":16},{"name":1012,"slug":1013,"type":16},"2026-07-12T08:38:28.210856",40]