[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-aws-labs-cdisc-compliance":3,"mdc--kvpvlg-key":46,"related-org-aws-labs-cdisc-compliance":1668,"related-repo-aws-labs-cdisc-compliance":1850},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":12,"stars":23,"repoUrl":24,"updatedAt":25,"license":26,"forks":27,"topics":28,"repo":41,"sourceUrl":44,"mdContent":45},"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},"aws-labs","AWS Labs","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Faws-labs.png","awslabs",[13,17,20],{"name":14,"slug":15,"type":16},"Clinical Trials","clinical-trials","tag",{"name":18,"slug":19,"type":16},"Life Sciences","life-sciences",{"name":21,"slug":22,"type":16},"Regulatory Compliance","regulatory-compliance",4,"https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fhcls-agent-skills","2026-07-12T08:37:33.35594",null,0,[29,30,31,32,33,34,35,36,37,19,38,39,40],"agent-skills","agentcore","ai-agents","amazon-quick-desktop","claims-processing","drug-discovery","genomics","healthcare-ai","kiro","medical-imaging","risk-adjustment","strands-agents",{"repoUrl":24,"stars":23,"forks":27,"topics":42,"description":43},[29,30,31,32,33,34,35,36,37,19,38,39,40],"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\u002Fcdisc-compliance","---\nname: cdisc-compliance\ndescription: >\n  Reason about CDISC SDTM and ADaM implementation for regulatory submissions. Use when\n  the user asks about SDTM domain mapping, ADaM dataset design, controlled terminology\n  versioning, define.xml completeness, FDA or PMDA submission requirements, query\n  prioritization by clinical impact, SUPPQUAL usage, or CDISC compliance review. Triggers\n  include \"SDTM mapping\", \"ADaM dataset\", \"CDISC compliance\", \"controlled terminology\",\n  \"define.xml\", \"FDA submission data\", \"PMDA submission\", \"SDTM domain\", \"ADSL\", \"ADAE\",\n  \"ADLB\", \"BDS structure\", \"SUPPQUAL\", \"RELREC\", \"value-level metadata\", \"CDISC CT\",\n  \"regulatory submission data standards\", \"eCTD datasets\", \"SDTM 3.3\", \"ADaM 1.1\",\n  \"query prioritization\", \"clinical data review\".\nusage: Invoke when evaluating CDISC compliance or planning regulatory submission datasets.\nversion: 1.0.0\ntags: [skill, category:reasoning, cdisc, sdtm, adam, regulatory, clinical-data, fda, hcls]\n---\n\n# CDISC Compliance — Reasoning Skill\n\n## Overview\n\nYou are an expert in CDISC data standards for regulatory submissions. When the user\nasks about SDTM\u002FADaM implementation, controlled terminology, define.xml, or submission\nrequirements, apply the decision frameworks below.\n\n## Usage\n\n- Invoke when evaluating CDISC SDTM or ADaM compliance for regulatory submissions\n- Use when planning define.xml content, SUPPQUAL decisions, or domain mapping\n- Activate for FDA\u002FPMDA submission data standards questions or Pinnacle 21 triage\n\n---\n\n## Core Concepts\n\n## Response Format\n\n- Lead with the direct recommendation or classification (≤3 sentences)\n- Structure as: recommendation → justification (citing specific criteria\u002Fthresholds) → caveats\n- Use tables for comparisons; bullet points for criteria lists\n- Omit background the user already knows — they asked the question\n- Target: 200-400 words unless the user requests exhaustive detail\nThe decision trees and frameworks in this skill are for internal reasoning only. Apply them to reach your conclusion, but do not reproduce them in your response. Present only the final recommendation with supporting evidence.\n\n\n## 1. Tricky Domain Mapping Decision Tree\n\nThese are the non-obvious mappings where teams make mistakes:\n\n```\nOncology tumor data?\n├─ Identifying tumor location\u002Fcharacteristics → TU (one record per identified lesion)\n├─ Measuring a lesion (diameter, volume) → TR (one record per measurement per visit)\n└─ Evaluating overall response (CR\u002FPR\u002FSD\u002FPD) → RS (one record per assessment per visit)\n    Rule: TU identifies it, TR measures it, RS evaluates the patient.\n\nMedication data?\n├─ Is it the study drug or protocol-mandated therapy? → EX (Exposure)\n├─ Is it a non-study medication taken during the study? → CM\n└─ Ambiguous (e.g., rescue medication specified in protocol)?\n   ├─ Protocol-required with dosing rules → EX\n   └─ Taken at investigator\u002Fsubject discretion → CM\n\nPre-existing condition that worsens on study?\n├─ Record in MH (with MHENDTC = blank or ongoing)\n├─ ALSO record in AE (with AEPRESP = \"Y\" to flag pre-existing)\n└─ Link via RELREC if needed for traceability\n\nQuestionnaire \u002F PRO \u002F scale data?\n├─ Uses a published validated instrument (e.g., EQ-5D, PHQ-9) → QS\n├─ Sponsor-designed assessment with scoring → QS (with sponsor-defined TESTCDs)\n└─ Single ad-hoc question not part of a scale → FA (Findings About)\n```\n\n## 2. SUPPQUAL Anti-Pattern Checklist\n\n### NEVER put in SUPPQUAL (move to parent domain or use standard variable):\n- Timing variables (--STDTC, --ENDTC, --DUR, --VISITNUM)\n- Result qualifiers (--LOC, --LAT, --DIR, --METHOD)\n- Standard identifiers (--GRPID, --REFID, --SPID)\n- Any variable defined in the current SDTM IG for that domain\n\n### ALWAYS appropriate for SUPPQUAL:\n- Free-text verbatim fields not fitting standard variables\n- Site-specific or country-specific collected fields\n- Non-standard data collected on CRF with no IG slot\n- Sponsor-defined flags needed for analysis traceability\n\n### Red flags indicating domain redesign needed:\n- **>5 SUPPQUAL records per subject per domain** → consider a custom domain or FA\n- **SUPPQUAL variable used in derivations** → promote to parent domain\n- **Same QNAM across >80% of subjects** → this is a standard variable in disguise\n\n### SUPPQUAL rules:\n- QNAM ≤8 characters, unique within parent domain\n- QLABEL ≤40 characters\n- QORIG: CRF | DERIVED | ASSIGNED | PROTOCOL\n\n## 3. SDTM Version Requirements\n\n| Agency | Minimum SDTM | Minimum IG | Notes |\n|---|---|---|---|\n| FDA | 3.3 | 3.3 | Required for NDA\u002FBLA since 2017 |\n| PMDA | 3.2 | 3.2 | Accepts 3.3; 3.4 encouraged |\n| EMA | 3.2 | 3.2 | Not yet mandatory but recommended |\n| Health Canada | 3.3 | 3.3 | Aligned with FDA |\n\n## 4. ADaM Rules (Non-Obvious)\n\n1. **Traceability is mandatory.** Every derived variable must trace to SDTM via SRCDOM\u002FSRCVAR\u002FSRCSEQ.\n2. **DTYPE flags derived records.** Imputed\u002Fderived records (LOCF, WOCF) require DTYPE.\n3. **AVAL and BASE must share units.** CHG = AVAL − BASE is meaningless otherwise.\n4. **Value-level metadata required for BDS** where variable attributes differ by PARAMCD — define.xml must include where clauses for each parameter.\n5. **Computational methods required** for every derived variable in define.xml.\n\n## 5. define.xml Value-Level Metadata\n\nFor BDS datasets, define.xml must specify per-PARAMCD:\n- **Origin** (CRF vs Derived) — may differ by parameter\n- **Data type and length** — AVAL is always numeric, but AVALC length varies\n- **Codelist reference** — only for parameters with categorical AVALC\n- **Computational method** — derivation algorithm specific to that PARAMCD\n- **Where clause** — the condition identifying which records the metadata applies to\n\nMissing value-level metadata is a **P21 Error** for any BDS dataset with >1 PARAMCD.\n\n## 6. Query Prioritization by Clinical Impact\n\n| Priority | Data Category | Examples | Resolution SLA |\n|---|---|---|---|\n| P1 — Critical | Safety data | SAE dates, AE causality, death records | 24–48 hours |\n| P2 — High | Efficacy endpoints | Primary\u002Fsecondary endpoint values, visit dates | 3–5 business days |\n| P3 — Medium | Key demographics | Randomization data, stratification factors | 5–7 business days |\n| P4 — Low | Administrative | Informed consent dates, site identifiers | 10 business days |\n\n**Escalation rules:**\n- Queries affecting **multiple subjects** → escalate one priority level\n- **Systematic errors** (wrong unit for all subjects at a site) → P1 regardless of data type\n- Safety queries **block database lock** — resolve before anything else\n\n## 7. FDA vs PMDA Submission Differences\n\n| Aspect | FDA | PMDA |\n|---|---|---|\n| SDTM required | Yes (NDA\u002FBLA) | Yes (since 2020 for new drugs) |\n| ADaM required | Yes | Recommended, not mandatory |\n| define.xml | 2.0+ required | 2.0+ required |\n| CT version policy | Latest at time of submission | Pin at study start |\n| Dataset size limit | 5 GB per dataset (eCTD) | No explicit limit |\n| Blanking rules | Permissible null | Prefer explicit \"NOT DONE\" |\n| Reviewer's Guide | Required (cSDRG, aSDRG) | Required |\n\n**Key gotcha:** FDA accepts null for \"not done\" assessments; PMDA expects --STAT = \"NOT DONE\" with --REASND populated. Plan for PMDA requirements upfront if dual submission.\n\n## When NOT to Use This Skill\n- Pre-clinical or discovery-phase data not destined for regulatory submission — CDISC standards add overhead without value\n- Non-regulatory submissions (e.g., internal research databases, publications) — use domain-appropriate formats instead\n- eCTD module assembly or submission gateway mechanics — this skill covers data standards, not submission logistics\n\n## When to Escalate to Human Expert\n- Ambiguous domain mapping where the variable could legitimately belong to two SDTM domains — requires sponsor standards team decision\n- Novel endpoint types not covered by existing CDISC controlled terminology — requires CDISC SHARE consultation or sponsor extension request\n- Regulatory agency feedback contradicts CDISC Implementation Guide — requires regulatory affairs interpretation\n\n## 8. Common Compliance Mistakes (Severity-Ranked)\n\n1. **Wrong:** Submitting a dataset without USUBJID\n   **Right:** Include USUBJID as a required variable in every SDTM and ADaM dataset\n   **Why:** Missing USUBJID breaks all cross-dataset joins — Critical severity\n\n2. **Wrong:** Creating DM domain without populating RFSTDTC\n   **Right:** Always populate RFSTDTC (reference start date) in DM from the first dose or randomization date\n   **Why:** All study day (--DY) calculations depend on RFSTDTC — Critical severity\n\n3. **Wrong:** Building ADSL without TRT01A\u002FTRT01P variables\n   **Right:** Always include TRT01A (actual treatment) and TRT01P (planned treatment) in ADSL\n   **Why:** No treatment assignment means no analysis population can be defined — Critical severity\n\n4. **Wrong:** Creating a non-standard (custom) domain without documenting it in define.xml and the Reviewer's Guide\n   **Right:** Document all non-standard domains with full metadata in define.xml and explain rationale in cSDRG\n   **Why:** Reviewers cannot interpret undocumented domains, causing review delays — High severity\n\n5. **Wrong:** Placing standard SDTM variables (timing, result qualifiers, identifiers) in SUPPQUAL\n   **Right:** Use the parent domain's standard variables (--STDTC, --LOC, --METHOD, --GRPID, etc.) as defined in the IG\n   **Why:** Triggers P21 Error and signals poor domain mapping knowledge — High severity\n\n6. **Wrong:** Omitting value-level metadata for BDS datasets with multiple PARAMCDs\n   **Right:** Include where-clause-based value-level metadata in define.xml for every PARAMCD in BDS datasets\n   **Why:** Missing value-level metadata is a P21 Error; define.xml is incomplete without it — High severity\n\n7. **Wrong:** Using codelist values not present in the pinned controlled terminology version\n   **Right:** Pin one CT version at study start and use only values from that version (or document sponsor extensions for extensible codelists)\n   **Why:** Triggers P21 Warning CT2003 and may delay regulatory review — Medium severity\n\n8. **Wrong:** Recording dates with inconsistent precision across records (mixing full dates with partial dates without clear rules)\n   **Right:** Define date precision rules in the SAP and apply consistent imputation logic documented in define.xml\n   **Why:** Inconsistent precision complicates imputation and introduces errors in study day calculations — Medium severity\n\n## 9. Date Handling Gotchas\n\n### Study Day Calculation\n\n```\n--DY = date − RFSTDTC + 1  (if date ≥ RFSTDTC)\n--DY = date − RFSTDTC      (if date \u003C RFSTDTC)\n```\n\n**There is no Day 0.** Day −1 is the day before RFSTDTC; Day 1 is RFSTDTC itself. This off-by-one is the #1 date calculation error in submissions.\n\n### Date Imputation Rules for ADaM\n\n| Scenario | Imputation Rule | DTYPE Flag |\n|---|---|---|\n| Missing day, AE start | Impute to 1st of month | Set ASTDT, document imputation |\n| Missing month and day | Impute to January 1st | Document in define.xml |\n| Missing end date, ongoing AE | Use data cutoff date | Flag as ongoing (AENDY missing) |\n| Partial date comparison | Conservative: earliest for start, latest for end | Document algorithm |\n\n**Rule:** Every imputed date requires a corresponding imputation flag variable (e.g., ASTDTF, AENDTF) with values Y (imputed) or blank (not imputed).\n\n## 10. Pinnacle 21 Triage Decision Tree\n\n```\nP21 finding received\n├─ Severity = Error\n│  └─ MUST fix before submission (no exceptions)\n├─ Severity = Warning\n│  ├─ Affects safety\u002Fefficacy data? → Fix\n│  ├─ Cosmetic or structural only? → Document justification in Reviewer's Guide\n│  └─ Systematic across all subjects? → Fix (reviewer will notice)\n└─ Severity = Notice\n   ├─ Easy fix (\u003C1 hour)? → Fix\n   └─ Complex or low-impact? → Skip, document if asked\n```\n\n### Top P21 Rules by Fix Priority\n\n| Rule ID | Description | Severity | Action |\n|---|---|---|---|\n| SD0009 | USUBJID not consistent with DM | Error | Fix immediately — breaks traceability |\n| SD0083 | Missing required variable | Error | Fix — submission will be rejected |\n| SD1001 | Invalid date\u002Ftime format | Error | Fix — ISO 8601 non-negotiable |\n| CT2001 | CT mismatch (value not in codelist) | Warning | Fix if non-extensible codelist; document if sponsor extension |\n| CT2003 | CT version inconsistency | Warning | Usually fix — indicates mixed CT versions |\n| SD1020 | Value not found in external codelist | Warning | Fix if standard term exists; extend if legitimate |\n| AD0252 | ADSL missing required variables | Error | Fix — ADSL completeness is critical |\n| AD0322 | BDS record without PARAMCD | Error | Fix — BDS is unusable without PARAMCD |\n| SD0070 | Duplicate records | Warning | Investigate — may be valid (e.g., bilateral findings) |\n| SD1015 | Inconsistent values across datasets | Warning | Fix if traceability broken; document if by design |\n\n## 11. Controlled Terminology Rules\n\n| Rule | Description |\n|---|---|\n| Pin CT version at study start | One CT version for entire study |\n| Document in define.xml | Specify package version (e.g., 2024-03-29) |\n| Never mix versions | Mixing CT within a study → P21 Warning CT2003 |\n| Non-extensible codelists | Use ONLY CDISC-defined values (e.g., SEX, AEOUT) |\n| Extensible codelists | Sponsor values allowed but must be documented |\n| Map legacy terms on upgrade | Create mapping table; never silently change coded values |\n",{"data":47,"body":60},{"name":4,"description":6,"usage":48,"version":49,"tags":50},"Invoke when evaluating CDISC compliance or planning regulatory submission datasets.","1.0.0",[51,52,53,54,55,56,57,58,59],"skill","category:reasoning","cdisc","sdtm","adam","regulatory","clinical-data","fda","hcls",{"type":61,"children":62},"root",[63,72,79,85,91,111,115,121,127,155,161,166,179,185,192,215,221,244,250,284,290,308,314,438,444,498,504,509,562,574,580,704,712,749,755,905,915,921,939,945,963,969,1143,1149,1155,1164,1174,1180,1279,1289,1295,1304,1310,1564,1570],{"type":64,"tag":65,"props":66,"children":68},"element","h1",{"id":67},"cdisc-compliance-reasoning-skill",[69],{"type":70,"value":71},"text","CDISC Compliance — Reasoning Skill",{"type":64,"tag":73,"props":74,"children":76},"h2",{"id":75},"overview",[77],{"type":70,"value":78},"Overview",{"type":64,"tag":80,"props":81,"children":82},"p",{},[83],{"type":70,"value":84},"You are an expert in CDISC data standards for regulatory submissions. When the user\nasks about SDTM\u002FADaM implementation, controlled terminology, define.xml, or submission\nrequirements, apply the decision frameworks below.",{"type":64,"tag":73,"props":86,"children":88},{"id":87},"usage",[89],{"type":70,"value":90},"Usage",{"type":64,"tag":92,"props":93,"children":94},"ul",{},[95,101,106],{"type":64,"tag":96,"props":97,"children":98},"li",{},[99],{"type":70,"value":100},"Invoke when evaluating CDISC SDTM or ADaM compliance for regulatory submissions",{"type":64,"tag":96,"props":102,"children":103},{},[104],{"type":70,"value":105},"Use when planning define.xml content, SUPPQUAL decisions, or domain mapping",{"type":64,"tag":96,"props":107,"children":108},{},[109],{"type":70,"value":110},"Activate for FDA\u002FPMDA submission data standards questions or Pinnacle 21 triage",{"type":64,"tag":112,"props":113,"children":114},"hr",{},[],{"type":64,"tag":73,"props":116,"children":118},{"id":117},"core-concepts",[119],{"type":70,"value":120},"Core Concepts",{"type":64,"tag":73,"props":122,"children":124},{"id":123},"response-format",[125],{"type":70,"value":126},"Response Format",{"type":64,"tag":92,"props":128,"children":129},{},[130,135,140,145,150],{"type":64,"tag":96,"props":131,"children":132},{},[133],{"type":70,"value":134},"Lead with the direct recommendation or classification (≤3 sentences)",{"type":64,"tag":96,"props":136,"children":137},{},[138],{"type":70,"value":139},"Structure as: recommendation → justification (citing specific criteria\u002Fthresholds) → caveats",{"type":64,"tag":96,"props":141,"children":142},{},[143],{"type":70,"value":144},"Use tables for comparisons; bullet points for criteria lists",{"type":64,"tag":96,"props":146,"children":147},{},[148],{"type":70,"value":149},"Omit background the user already knows — they asked the question",{"type":64,"tag":96,"props":151,"children":152},{},[153],{"type":70,"value":154},"Target: 200-400 words unless the user requests exhaustive detail\nThe decision trees and frameworks in this skill are for internal reasoning only. Apply them to reach your conclusion, but do not reproduce them in your response. Present only the final recommendation with supporting evidence.",{"type":64,"tag":73,"props":156,"children":158},{"id":157},"_1-tricky-domain-mapping-decision-tree",[159],{"type":70,"value":160},"1. Tricky Domain Mapping Decision Tree",{"type":64,"tag":80,"props":162,"children":163},{},[164],{"type":70,"value":165},"These are the non-obvious mappings where teams make mistakes:",{"type":64,"tag":167,"props":168,"children":172},"pre",{"className":169,"code":171,"language":70},[170],"language-text","Oncology tumor data?\n├─ Identifying tumor location\u002Fcharacteristics → TU (one record per identified lesion)\n├─ Measuring a lesion (diameter, volume) → TR (one record per measurement per visit)\n└─ Evaluating overall response (CR\u002FPR\u002FSD\u002FPD) → RS (one record per assessment per visit)\n    Rule: TU identifies it, TR measures it, RS evaluates the patient.\n\nMedication data?\n├─ Is it the study drug or protocol-mandated therapy? → EX (Exposure)\n├─ Is it a non-study medication taken during the study? → CM\n└─ Ambiguous (e.g., rescue medication specified in protocol)?\n   ├─ Protocol-required with dosing rules → EX\n   └─ Taken at investigator\u002Fsubject discretion → CM\n\nPre-existing condition that worsens on study?\n├─ Record in MH (with MHENDTC = blank or ongoing)\n├─ ALSO record in AE (with AEPRESP = \"Y\" to flag pre-existing)\n└─ Link via RELREC if needed for traceability\n\nQuestionnaire \u002F PRO \u002F scale data?\n├─ Uses a published validated instrument (e.g., EQ-5D, PHQ-9) → QS\n├─ Sponsor-designed assessment with scoring → QS (with sponsor-defined TESTCDs)\n└─ Single ad-hoc question not part of a scale → FA (Findings About)\n",[173],{"type":64,"tag":174,"props":175,"children":177},"code",{"__ignoreMap":176},"",[178],{"type":70,"value":171},{"type":64,"tag":73,"props":180,"children":182},{"id":181},"_2-suppqual-anti-pattern-checklist",[183],{"type":70,"value":184},"2. SUPPQUAL Anti-Pattern Checklist",{"type":64,"tag":186,"props":187,"children":189},"h3",{"id":188},"never-put-in-suppqual-move-to-parent-domain-or-use-standard-variable",[190],{"type":70,"value":191},"NEVER put in SUPPQUAL (move to parent domain or use standard variable):",{"type":64,"tag":92,"props":193,"children":194},{},[195,200,205,210],{"type":64,"tag":96,"props":196,"children":197},{},[198],{"type":70,"value":199},"Timing variables (--STDTC, --ENDTC, --DUR, --VISITNUM)",{"type":64,"tag":96,"props":201,"children":202},{},[203],{"type":70,"value":204},"Result qualifiers (--LOC, --LAT, --DIR, --METHOD)",{"type":64,"tag":96,"props":206,"children":207},{},[208],{"type":70,"value":209},"Standard identifiers (--GRPID, --REFID, --SPID)",{"type":64,"tag":96,"props":211,"children":212},{},[213],{"type":70,"value":214},"Any variable defined in the current SDTM IG for that domain",{"type":64,"tag":186,"props":216,"children":218},{"id":217},"always-appropriate-for-suppqual",[219],{"type":70,"value":220},"ALWAYS appropriate for SUPPQUAL:",{"type":64,"tag":92,"props":222,"children":223},{},[224,229,234,239],{"type":64,"tag":96,"props":225,"children":226},{},[227],{"type":70,"value":228},"Free-text verbatim fields not fitting standard variables",{"type":64,"tag":96,"props":230,"children":231},{},[232],{"type":70,"value":233},"Site-specific or country-specific collected fields",{"type":64,"tag":96,"props":235,"children":236},{},[237],{"type":70,"value":238},"Non-standard data collected on CRF with no IG slot",{"type":64,"tag":96,"props":240,"children":241},{},[242],{"type":70,"value":243},"Sponsor-defined flags needed for analysis traceability",{"type":64,"tag":186,"props":245,"children":247},{"id":246},"red-flags-indicating-domain-redesign-needed",[248],{"type":70,"value":249},"Red flags indicating domain redesign needed:",{"type":64,"tag":92,"props":251,"children":252},{},[253,264,274],{"type":64,"tag":96,"props":254,"children":255},{},[256,262],{"type":64,"tag":257,"props":258,"children":259},"strong",{},[260],{"type":70,"value":261},">5 SUPPQUAL records per subject per domain",{"type":70,"value":263}," → consider a custom domain or FA",{"type":64,"tag":96,"props":265,"children":266},{},[267,272],{"type":64,"tag":257,"props":268,"children":269},{},[270],{"type":70,"value":271},"SUPPQUAL variable used in derivations",{"type":70,"value":273}," → promote to parent domain",{"type":64,"tag":96,"props":275,"children":276},{},[277,282],{"type":64,"tag":257,"props":278,"children":279},{},[280],{"type":70,"value":281},"Same QNAM across >80% of subjects",{"type":70,"value":283}," → this is a standard variable in disguise",{"type":64,"tag":186,"props":285,"children":287},{"id":286},"suppqual-rules",[288],{"type":70,"value":289},"SUPPQUAL rules:",{"type":64,"tag":92,"props":291,"children":292},{},[293,298,303],{"type":64,"tag":96,"props":294,"children":295},{},[296],{"type":70,"value":297},"QNAM ≤8 characters, unique within parent domain",{"type":64,"tag":96,"props":299,"children":300},{},[301],{"type":70,"value":302},"QLABEL ≤40 characters",{"type":64,"tag":96,"props":304,"children":305},{},[306],{"type":70,"value":307},"QORIG: CRF | DERIVED | ASSIGNED | PROTOCOL",{"type":64,"tag":73,"props":309,"children":311},{"id":310},"_3-sdtm-version-requirements",[312],{"type":70,"value":313},"3. SDTM Version Requirements",{"type":64,"tag":315,"props":316,"children":317},"table",{},[318,347],{"type":64,"tag":319,"props":320,"children":321},"thead",{},[322],{"type":64,"tag":323,"props":324,"children":325},"tr",{},[326,332,337,342],{"type":64,"tag":327,"props":328,"children":329},"th",{},[330],{"type":70,"value":331},"Agency",{"type":64,"tag":327,"props":333,"children":334},{},[335],{"type":70,"value":336},"Minimum SDTM",{"type":64,"tag":327,"props":338,"children":339},{},[340],{"type":70,"value":341},"Minimum IG",{"type":64,"tag":327,"props":343,"children":344},{},[345],{"type":70,"value":346},"Notes",{"type":64,"tag":348,"props":349,"children":350},"tbody",{},[351,374,396,417],{"type":64,"tag":323,"props":352,"children":353},{},[354,360,365,369],{"type":64,"tag":355,"props":356,"children":357},"td",{},[358],{"type":70,"value":359},"FDA",{"type":64,"tag":355,"props":361,"children":362},{},[363],{"type":70,"value":364},"3.3",{"type":64,"tag":355,"props":366,"children":367},{},[368],{"type":70,"value":364},{"type":64,"tag":355,"props":370,"children":371},{},[372],{"type":70,"value":373},"Required for NDA\u002FBLA since 2017",{"type":64,"tag":323,"props":375,"children":376},{},[377,382,387,391],{"type":64,"tag":355,"props":378,"children":379},{},[380],{"type":70,"value":381},"PMDA",{"type":64,"tag":355,"props":383,"children":384},{},[385],{"type":70,"value":386},"3.2",{"type":64,"tag":355,"props":388,"children":389},{},[390],{"type":70,"value":386},{"type":64,"tag":355,"props":392,"children":393},{},[394],{"type":70,"value":395},"Accepts 3.3; 3.4 encouraged",{"type":64,"tag":323,"props":397,"children":398},{},[399,404,408,412],{"type":64,"tag":355,"props":400,"children":401},{},[402],{"type":70,"value":403},"EMA",{"type":64,"tag":355,"props":405,"children":406},{},[407],{"type":70,"value":386},{"type":64,"tag":355,"props":409,"children":410},{},[411],{"type":70,"value":386},{"type":64,"tag":355,"props":413,"children":414},{},[415],{"type":70,"value":416},"Not yet mandatory but recommended",{"type":64,"tag":323,"props":418,"children":419},{},[420,425,429,433],{"type":64,"tag":355,"props":421,"children":422},{},[423],{"type":70,"value":424},"Health Canada",{"type":64,"tag":355,"props":426,"children":427},{},[428],{"type":70,"value":364},{"type":64,"tag":355,"props":430,"children":431},{},[432],{"type":70,"value":364},{"type":64,"tag":355,"props":434,"children":435},{},[436],{"type":70,"value":437},"Aligned with FDA",{"type":64,"tag":73,"props":439,"children":441},{"id":440},"_4-adam-rules-non-obvious",[442],{"type":70,"value":443},"4. ADaM Rules (Non-Obvious)",{"type":64,"tag":445,"props":446,"children":447},"ol",{},[448,458,468,478,488],{"type":64,"tag":96,"props":449,"children":450},{},[451,456],{"type":64,"tag":257,"props":452,"children":453},{},[454],{"type":70,"value":455},"Traceability is mandatory.",{"type":70,"value":457}," Every derived variable must trace to SDTM via SRCDOM\u002FSRCVAR\u002FSRCSEQ.",{"type":64,"tag":96,"props":459,"children":460},{},[461,466],{"type":64,"tag":257,"props":462,"children":463},{},[464],{"type":70,"value":465},"DTYPE flags derived records.",{"type":70,"value":467}," Imputed\u002Fderived records (LOCF, WOCF) require DTYPE.",{"type":64,"tag":96,"props":469,"children":470},{},[471,476],{"type":64,"tag":257,"props":472,"children":473},{},[474],{"type":70,"value":475},"AVAL and BASE must share units.",{"type":70,"value":477}," CHG = AVAL − BASE is meaningless otherwise.",{"type":64,"tag":96,"props":479,"children":480},{},[481,486],{"type":64,"tag":257,"props":482,"children":483},{},[484],{"type":70,"value":485},"Value-level metadata required for BDS",{"type":70,"value":487}," where variable attributes differ by PARAMCD — define.xml must include where clauses for each parameter.",{"type":64,"tag":96,"props":489,"children":490},{},[491,496],{"type":64,"tag":257,"props":492,"children":493},{},[494],{"type":70,"value":495},"Computational methods required",{"type":70,"value":497}," for every derived variable in define.xml.",{"type":64,"tag":73,"props":499,"children":501},{"id":500},"_5-definexml-value-level-metadata",[502],{"type":70,"value":503},"5. define.xml Value-Level Metadata",{"type":64,"tag":80,"props":505,"children":506},{},[507],{"type":70,"value":508},"For BDS datasets, define.xml must specify per-PARAMCD:",{"type":64,"tag":92,"props":510,"children":511},{},[512,522,532,542,552],{"type":64,"tag":96,"props":513,"children":514},{},[515,520],{"type":64,"tag":257,"props":516,"children":517},{},[518],{"type":70,"value":519},"Origin",{"type":70,"value":521}," (CRF vs Derived) — may differ by parameter",{"type":64,"tag":96,"props":523,"children":524},{},[525,530],{"type":64,"tag":257,"props":526,"children":527},{},[528],{"type":70,"value":529},"Data type and length",{"type":70,"value":531}," — AVAL is always numeric, but AVALC length varies",{"type":64,"tag":96,"props":533,"children":534},{},[535,540],{"type":64,"tag":257,"props":536,"children":537},{},[538],{"type":70,"value":539},"Codelist reference",{"type":70,"value":541}," — only for parameters with categorical AVALC",{"type":64,"tag":96,"props":543,"children":544},{},[545,550],{"type":64,"tag":257,"props":546,"children":547},{},[548],{"type":70,"value":549},"Computational method",{"type":70,"value":551}," — derivation algorithm specific to that PARAMCD",{"type":64,"tag":96,"props":553,"children":554},{},[555,560],{"type":64,"tag":257,"props":556,"children":557},{},[558],{"type":70,"value":559},"Where clause",{"type":70,"value":561}," — the condition identifying which records the metadata applies to",{"type":64,"tag":80,"props":563,"children":564},{},[565,567,572],{"type":70,"value":566},"Missing value-level metadata is a ",{"type":64,"tag":257,"props":568,"children":569},{},[570],{"type":70,"value":571},"P21 Error",{"type":70,"value":573}," for any BDS dataset with >1 PARAMCD.",{"type":64,"tag":73,"props":575,"children":577},{"id":576},"_6-query-prioritization-by-clinical-impact",[578],{"type":70,"value":579},"6. Query Prioritization by Clinical Impact",{"type":64,"tag":315,"props":581,"children":582},{},[583,609],{"type":64,"tag":319,"props":584,"children":585},{},[586],{"type":64,"tag":323,"props":587,"children":588},{},[589,594,599,604],{"type":64,"tag":327,"props":590,"children":591},{},[592],{"type":70,"value":593},"Priority",{"type":64,"tag":327,"props":595,"children":596},{},[597],{"type":70,"value":598},"Data Category",{"type":64,"tag":327,"props":600,"children":601},{},[602],{"type":70,"value":603},"Examples",{"type":64,"tag":327,"props":605,"children":606},{},[607],{"type":70,"value":608},"Resolution SLA",{"type":64,"tag":348,"props":610,"children":611},{},[612,635,658,681],{"type":64,"tag":323,"props":613,"children":614},{},[615,620,625,630],{"type":64,"tag":355,"props":616,"children":617},{},[618],{"type":70,"value":619},"P1 — Critical",{"type":64,"tag":355,"props":621,"children":622},{},[623],{"type":70,"value":624},"Safety data",{"type":64,"tag":355,"props":626,"children":627},{},[628],{"type":70,"value":629},"SAE dates, AE causality, death records",{"type":64,"tag":355,"props":631,"children":632},{},[633],{"type":70,"value":634},"24–48 hours",{"type":64,"tag":323,"props":636,"children":637},{},[638,643,648,653],{"type":64,"tag":355,"props":639,"children":640},{},[641],{"type":70,"value":642},"P2 — High",{"type":64,"tag":355,"props":644,"children":645},{},[646],{"type":70,"value":647},"Efficacy endpoints",{"type":64,"tag":355,"props":649,"children":650},{},[651],{"type":70,"value":652},"Primary\u002Fsecondary endpoint values, visit dates",{"type":64,"tag":355,"props":654,"children":655},{},[656],{"type":70,"value":657},"3–5 business days",{"type":64,"tag":323,"props":659,"children":660},{},[661,666,671,676],{"type":64,"tag":355,"props":662,"children":663},{},[664],{"type":70,"value":665},"P3 — Medium",{"type":64,"tag":355,"props":667,"children":668},{},[669],{"type":70,"value":670},"Key demographics",{"type":64,"tag":355,"props":672,"children":673},{},[674],{"type":70,"value":675},"Randomization data, stratification factors",{"type":64,"tag":355,"props":677,"children":678},{},[679],{"type":70,"value":680},"5–7 business days",{"type":64,"tag":323,"props":682,"children":683},{},[684,689,694,699],{"type":64,"tag":355,"props":685,"children":686},{},[687],{"type":70,"value":688},"P4 — Low",{"type":64,"tag":355,"props":690,"children":691},{},[692],{"type":70,"value":693},"Administrative",{"type":64,"tag":355,"props":695,"children":696},{},[697],{"type":70,"value":698},"Informed consent dates, site identifiers",{"type":64,"tag":355,"props":700,"children":701},{},[702],{"type":70,"value":703},"10 business days",{"type":64,"tag":80,"props":705,"children":706},{},[707],{"type":64,"tag":257,"props":708,"children":709},{},[710],{"type":70,"value":711},"Escalation rules:",{"type":64,"tag":92,"props":713,"children":714},{},[715,727,737],{"type":64,"tag":96,"props":716,"children":717},{},[718,720,725],{"type":70,"value":719},"Queries affecting ",{"type":64,"tag":257,"props":721,"children":722},{},[723],{"type":70,"value":724},"multiple subjects",{"type":70,"value":726}," → escalate one priority level",{"type":64,"tag":96,"props":728,"children":729},{},[730,735],{"type":64,"tag":257,"props":731,"children":732},{},[733],{"type":70,"value":734},"Systematic errors",{"type":70,"value":736}," (wrong unit for all subjects at a site) → P1 regardless of data type",{"type":64,"tag":96,"props":738,"children":739},{},[740,742,747],{"type":70,"value":741},"Safety queries ",{"type":64,"tag":257,"props":743,"children":744},{},[745],{"type":70,"value":746},"block database lock",{"type":70,"value":748}," — resolve before anything else",{"type":64,"tag":73,"props":750,"children":752},{"id":751},"_7-fda-vs-pmda-submission-differences",[753],{"type":70,"value":754},"7. FDA vs PMDA Submission Differences",{"type":64,"tag":315,"props":756,"children":757},{},[758,777],{"type":64,"tag":319,"props":759,"children":760},{},[761],{"type":64,"tag":323,"props":762,"children":763},{},[764,769,773],{"type":64,"tag":327,"props":765,"children":766},{},[767],{"type":70,"value":768},"Aspect",{"type":64,"tag":327,"props":770,"children":771},{},[772],{"type":70,"value":359},{"type":64,"tag":327,"props":774,"children":775},{},[776],{"type":70,"value":381},{"type":64,"tag":348,"props":778,"children":779},{},[780,798,816,833,851,869,887],{"type":64,"tag":323,"props":781,"children":782},{},[783,788,793],{"type":64,"tag":355,"props":784,"children":785},{},[786],{"type":70,"value":787},"SDTM required",{"type":64,"tag":355,"props":789,"children":790},{},[791],{"type":70,"value":792},"Yes (NDA\u002FBLA)",{"type":64,"tag":355,"props":794,"children":795},{},[796],{"type":70,"value":797},"Yes (since 2020 for new drugs)",{"type":64,"tag":323,"props":799,"children":800},{},[801,806,811],{"type":64,"tag":355,"props":802,"children":803},{},[804],{"type":70,"value":805},"ADaM required",{"type":64,"tag":355,"props":807,"children":808},{},[809],{"type":70,"value":810},"Yes",{"type":64,"tag":355,"props":812,"children":813},{},[814],{"type":70,"value":815},"Recommended, not mandatory",{"type":64,"tag":323,"props":817,"children":818},{},[819,824,829],{"type":64,"tag":355,"props":820,"children":821},{},[822],{"type":70,"value":823},"define.xml",{"type":64,"tag":355,"props":825,"children":826},{},[827],{"type":70,"value":828},"2.0+ required",{"type":64,"tag":355,"props":830,"children":831},{},[832],{"type":70,"value":828},{"type":64,"tag":323,"props":834,"children":835},{},[836,841,846],{"type":64,"tag":355,"props":837,"children":838},{},[839],{"type":70,"value":840},"CT version policy",{"type":64,"tag":355,"props":842,"children":843},{},[844],{"type":70,"value":845},"Latest at time of submission",{"type":64,"tag":355,"props":847,"children":848},{},[849],{"type":70,"value":850},"Pin at study start",{"type":64,"tag":323,"props":852,"children":853},{},[854,859,864],{"type":64,"tag":355,"props":855,"children":856},{},[857],{"type":70,"value":858},"Dataset size limit",{"type":64,"tag":355,"props":860,"children":861},{},[862],{"type":70,"value":863},"5 GB per dataset (eCTD)",{"type":64,"tag":355,"props":865,"children":866},{},[867],{"type":70,"value":868},"No explicit limit",{"type":64,"tag":323,"props":870,"children":871},{},[872,877,882],{"type":64,"tag":355,"props":873,"children":874},{},[875],{"type":70,"value":876},"Blanking rules",{"type":64,"tag":355,"props":878,"children":879},{},[880],{"type":70,"value":881},"Permissible null",{"type":64,"tag":355,"props":883,"children":884},{},[885],{"type":70,"value":886},"Prefer explicit \"NOT DONE\"",{"type":64,"tag":323,"props":888,"children":889},{},[890,895,900],{"type":64,"tag":355,"props":891,"children":892},{},[893],{"type":70,"value":894},"Reviewer's Guide",{"type":64,"tag":355,"props":896,"children":897},{},[898],{"type":70,"value":899},"Required (cSDRG, aSDRG)",{"type":64,"tag":355,"props":901,"children":902},{},[903],{"type":70,"value":904},"Required",{"type":64,"tag":80,"props":906,"children":907},{},[908,913],{"type":64,"tag":257,"props":909,"children":910},{},[911],{"type":70,"value":912},"Key gotcha:",{"type":70,"value":914}," FDA accepts null for \"not done\" assessments; PMDA expects --STAT = \"NOT DONE\" with --REASND populated. Plan for PMDA requirements upfront if dual submission.",{"type":64,"tag":73,"props":916,"children":918},{"id":917},"when-not-to-use-this-skill",[919],{"type":70,"value":920},"When NOT to Use This Skill",{"type":64,"tag":92,"props":922,"children":923},{},[924,929,934],{"type":64,"tag":96,"props":925,"children":926},{},[927],{"type":70,"value":928},"Pre-clinical or discovery-phase data not destined for regulatory submission — CDISC standards add overhead without value",{"type":64,"tag":96,"props":930,"children":931},{},[932],{"type":70,"value":933},"Non-regulatory submissions (e.g., internal research databases, publications) — use domain-appropriate formats instead",{"type":64,"tag":96,"props":935,"children":936},{},[937],{"type":70,"value":938},"eCTD module assembly or submission gateway mechanics — this skill covers data standards, not submission logistics",{"type":64,"tag":73,"props":940,"children":942},{"id":941},"when-to-escalate-to-human-expert",[943],{"type":70,"value":944},"When to Escalate to Human Expert",{"type":64,"tag":92,"props":946,"children":947},{},[948,953,958],{"type":64,"tag":96,"props":949,"children":950},{},[951],{"type":70,"value":952},"Ambiguous domain mapping where the variable could legitimately belong to two SDTM domains — requires sponsor standards team decision",{"type":64,"tag":96,"props":954,"children":955},{},[956],{"type":70,"value":957},"Novel endpoint types not covered by existing CDISC controlled terminology — requires CDISC SHARE consultation or sponsor extension request",{"type":64,"tag":96,"props":959,"children":960},{},[961],{"type":70,"value":962},"Regulatory agency feedback contradicts CDISC Implementation Guide — requires regulatory affairs interpretation",{"type":64,"tag":73,"props":964,"children":966},{"id":965},"_8-common-compliance-mistakes-severity-ranked",[967],{"type":70,"value":968},"8. Common Compliance Mistakes (Severity-Ranked)",{"type":64,"tag":445,"props":970,"children":971},{},[972,996,1017,1038,1059,1080,1101,1122],{"type":64,"tag":96,"props":973,"children":974},{},[975,980,982,987,989,994],{"type":64,"tag":257,"props":976,"children":977},{},[978],{"type":70,"value":979},"Wrong:",{"type":70,"value":981}," Submitting a dataset without USUBJID\n",{"type":64,"tag":257,"props":983,"children":984},{},[985],{"type":70,"value":986},"Right:",{"type":70,"value":988}," Include USUBJID as a required variable in every SDTM and ADaM dataset\n",{"type":64,"tag":257,"props":990,"children":991},{},[992],{"type":70,"value":993},"Why:",{"type":70,"value":995}," Missing USUBJID breaks all cross-dataset joins — Critical severity",{"type":64,"tag":96,"props":997,"children":998},{},[999,1003,1005,1009,1011,1015],{"type":64,"tag":257,"props":1000,"children":1001},{},[1002],{"type":70,"value":979},{"type":70,"value":1004}," Creating DM domain without populating RFSTDTC\n",{"type":64,"tag":257,"props":1006,"children":1007},{},[1008],{"type":70,"value":986},{"type":70,"value":1010}," Always populate RFSTDTC (reference start date) in DM from the first dose or randomization date\n",{"type":64,"tag":257,"props":1012,"children":1013},{},[1014],{"type":70,"value":993},{"type":70,"value":1016}," All study day (--DY) calculations depend on RFSTDTC — Critical severity",{"type":64,"tag":96,"props":1018,"children":1019},{},[1020,1024,1026,1030,1032,1036],{"type":64,"tag":257,"props":1021,"children":1022},{},[1023],{"type":70,"value":979},{"type":70,"value":1025}," Building ADSL without TRT01A\u002FTRT01P variables\n",{"type":64,"tag":257,"props":1027,"children":1028},{},[1029],{"type":70,"value":986},{"type":70,"value":1031}," Always include TRT01A (actual treatment) and TRT01P (planned treatment) in ADSL\n",{"type":64,"tag":257,"props":1033,"children":1034},{},[1035],{"type":70,"value":993},{"type":70,"value":1037}," No treatment assignment means no analysis population can be defined — Critical severity",{"type":64,"tag":96,"props":1039,"children":1040},{},[1041,1045,1047,1051,1053,1057],{"type":64,"tag":257,"props":1042,"children":1043},{},[1044],{"type":70,"value":979},{"type":70,"value":1046}," Creating a non-standard (custom) domain without documenting it in define.xml and the Reviewer's Guide\n",{"type":64,"tag":257,"props":1048,"children":1049},{},[1050],{"type":70,"value":986},{"type":70,"value":1052}," Document all non-standard domains with full metadata in define.xml and explain rationale in cSDRG\n",{"type":64,"tag":257,"props":1054,"children":1055},{},[1056],{"type":70,"value":993},{"type":70,"value":1058}," Reviewers cannot interpret undocumented domains, causing review delays — High severity",{"type":64,"tag":96,"props":1060,"children":1061},{},[1062,1066,1068,1072,1074,1078],{"type":64,"tag":257,"props":1063,"children":1064},{},[1065],{"type":70,"value":979},{"type":70,"value":1067}," Placing standard SDTM variables (timing, result qualifiers, identifiers) in SUPPQUAL\n",{"type":64,"tag":257,"props":1069,"children":1070},{},[1071],{"type":70,"value":986},{"type":70,"value":1073}," Use the parent domain's standard variables (--STDTC, --LOC, --METHOD, --GRPID, etc.) as defined in the IG\n",{"type":64,"tag":257,"props":1075,"children":1076},{},[1077],{"type":70,"value":993},{"type":70,"value":1079}," Triggers P21 Error and signals poor domain mapping knowledge — High severity",{"type":64,"tag":96,"props":1081,"children":1082},{},[1083,1087,1089,1093,1095,1099],{"type":64,"tag":257,"props":1084,"children":1085},{},[1086],{"type":70,"value":979},{"type":70,"value":1088}," Omitting value-level metadata for BDS datasets with multiple PARAMCDs\n",{"type":64,"tag":257,"props":1090,"children":1091},{},[1092],{"type":70,"value":986},{"type":70,"value":1094}," Include where-clause-based value-level metadata in define.xml for every PARAMCD in BDS datasets\n",{"type":64,"tag":257,"props":1096,"children":1097},{},[1098],{"type":70,"value":993},{"type":70,"value":1100}," Missing value-level metadata is a P21 Error; define.xml is incomplete without it — High severity",{"type":64,"tag":96,"props":1102,"children":1103},{},[1104,1108,1110,1114,1116,1120],{"type":64,"tag":257,"props":1105,"children":1106},{},[1107],{"type":70,"value":979},{"type":70,"value":1109}," Using codelist values not present in the pinned controlled terminology version\n",{"type":64,"tag":257,"props":1111,"children":1112},{},[1113],{"type":70,"value":986},{"type":70,"value":1115}," Pin one CT version at study start and use only values from that version (or document sponsor extensions for extensible codelists)\n",{"type":64,"tag":257,"props":1117,"children":1118},{},[1119],{"type":70,"value":993},{"type":70,"value":1121}," Triggers P21 Warning CT2003 and may delay regulatory review — Medium severity",{"type":64,"tag":96,"props":1123,"children":1124},{},[1125,1129,1131,1135,1137,1141],{"type":64,"tag":257,"props":1126,"children":1127},{},[1128],{"type":70,"value":979},{"type":70,"value":1130}," Recording dates with inconsistent precision across records (mixing full dates with partial dates without clear rules)\n",{"type":64,"tag":257,"props":1132,"children":1133},{},[1134],{"type":70,"value":986},{"type":70,"value":1136}," Define date precision rules in the SAP and apply consistent imputation logic documented in define.xml\n",{"type":64,"tag":257,"props":1138,"children":1139},{},[1140],{"type":70,"value":993},{"type":70,"value":1142}," Inconsistent precision complicates imputation and introduces errors in study day calculations — Medium severity",{"type":64,"tag":73,"props":1144,"children":1146},{"id":1145},"_9-date-handling-gotchas",[1147],{"type":70,"value":1148},"9. Date Handling Gotchas",{"type":64,"tag":186,"props":1150,"children":1152},{"id":1151},"study-day-calculation",[1153],{"type":70,"value":1154},"Study Day Calculation",{"type":64,"tag":167,"props":1156,"children":1159},{"className":1157,"code":1158,"language":70},[170],"--DY = date − RFSTDTC + 1  (if date ≥ RFSTDTC)\n--DY = date − RFSTDTC      (if date \u003C RFSTDTC)\n",[1160],{"type":64,"tag":174,"props":1161,"children":1162},{"__ignoreMap":176},[1163],{"type":70,"value":1158},{"type":64,"tag":80,"props":1165,"children":1166},{},[1167,1172],{"type":64,"tag":257,"props":1168,"children":1169},{},[1170],{"type":70,"value":1171},"There is no Day 0.",{"type":70,"value":1173}," Day −1 is the day before RFSTDTC; Day 1 is RFSTDTC itself. This off-by-one is the #1 date calculation error in submissions.",{"type":64,"tag":186,"props":1175,"children":1177},{"id":1176},"date-imputation-rules-for-adam",[1178],{"type":70,"value":1179},"Date Imputation Rules for ADaM",{"type":64,"tag":315,"props":1181,"children":1182},{},[1183,1204],{"type":64,"tag":319,"props":1184,"children":1185},{},[1186],{"type":64,"tag":323,"props":1187,"children":1188},{},[1189,1194,1199],{"type":64,"tag":327,"props":1190,"children":1191},{},[1192],{"type":70,"value":1193},"Scenario",{"type":64,"tag":327,"props":1195,"children":1196},{},[1197],{"type":70,"value":1198},"Imputation Rule",{"type":64,"tag":327,"props":1200,"children":1201},{},[1202],{"type":70,"value":1203},"DTYPE Flag",{"type":64,"tag":348,"props":1205,"children":1206},{},[1207,1225,1243,1261],{"type":64,"tag":323,"props":1208,"children":1209},{},[1210,1215,1220],{"type":64,"tag":355,"props":1211,"children":1212},{},[1213],{"type":70,"value":1214},"Missing day, AE start",{"type":64,"tag":355,"props":1216,"children":1217},{},[1218],{"type":70,"value":1219},"Impute to 1st of month",{"type":64,"tag":355,"props":1221,"children":1222},{},[1223],{"type":70,"value":1224},"Set ASTDT, document imputation",{"type":64,"tag":323,"props":1226,"children":1227},{},[1228,1233,1238],{"type":64,"tag":355,"props":1229,"children":1230},{},[1231],{"type":70,"value":1232},"Missing month and day",{"type":64,"tag":355,"props":1234,"children":1235},{},[1236],{"type":70,"value":1237},"Impute to January 1st",{"type":64,"tag":355,"props":1239,"children":1240},{},[1241],{"type":70,"value":1242},"Document in define.xml",{"type":64,"tag":323,"props":1244,"children":1245},{},[1246,1251,1256],{"type":64,"tag":355,"props":1247,"children":1248},{},[1249],{"type":70,"value":1250},"Missing end date, ongoing AE",{"type":64,"tag":355,"props":1252,"children":1253},{},[1254],{"type":70,"value":1255},"Use data cutoff date",{"type":64,"tag":355,"props":1257,"children":1258},{},[1259],{"type":70,"value":1260},"Flag as ongoing (AENDY missing)",{"type":64,"tag":323,"props":1262,"children":1263},{},[1264,1269,1274],{"type":64,"tag":355,"props":1265,"children":1266},{},[1267],{"type":70,"value":1268},"Partial date comparison",{"type":64,"tag":355,"props":1270,"children":1271},{},[1272],{"type":70,"value":1273},"Conservative: earliest for start, latest for end",{"type":64,"tag":355,"props":1275,"children":1276},{},[1277],{"type":70,"value":1278},"Document algorithm",{"type":64,"tag":80,"props":1280,"children":1281},{},[1282,1287],{"type":64,"tag":257,"props":1283,"children":1284},{},[1285],{"type":70,"value":1286},"Rule:",{"type":70,"value":1288}," Every imputed date requires a corresponding imputation flag variable (e.g., ASTDTF, AENDTF) with values Y (imputed) or blank (not imputed).",{"type":64,"tag":73,"props":1290,"children":1292},{"id":1291},"_10-pinnacle-21-triage-decision-tree",[1293],{"type":70,"value":1294},"10. Pinnacle 21 Triage Decision Tree",{"type":64,"tag":167,"props":1296,"children":1299},{"className":1297,"code":1298,"language":70},[170],"P21 finding received\n├─ Severity = Error\n│  └─ MUST fix before submission (no exceptions)\n├─ Severity = Warning\n│  ├─ Affects safety\u002Fefficacy data? → Fix\n│  ├─ Cosmetic or structural only? → Document justification in Reviewer's Guide\n│  └─ Systematic across all subjects? → Fix (reviewer will notice)\n└─ Severity = Notice\n   ├─ Easy fix (\u003C1 hour)? → Fix\n   └─ Complex or low-impact? → Skip, document if asked\n",[1300],{"type":64,"tag":174,"props":1301,"children":1302},{"__ignoreMap":176},[1303],{"type":70,"value":1298},{"type":64,"tag":186,"props":1305,"children":1307},{"id":1306},"top-p21-rules-by-fix-priority",[1308],{"type":70,"value":1309},"Top P21 Rules by Fix Priority",{"type":64,"tag":315,"props":1311,"children":1312},{},[1313,1339],{"type":64,"tag":319,"props":1314,"children":1315},{},[1316],{"type":64,"tag":323,"props":1317,"children":1318},{},[1319,1324,1329,1334],{"type":64,"tag":327,"props":1320,"children":1321},{},[1322],{"type":70,"value":1323},"Rule ID",{"type":64,"tag":327,"props":1325,"children":1326},{},[1327],{"type":70,"value":1328},"Description",{"type":64,"tag":327,"props":1330,"children":1331},{},[1332],{"type":70,"value":1333},"Severity",{"type":64,"tag":327,"props":1335,"children":1336},{},[1337],{"type":70,"value":1338},"Action",{"type":64,"tag":348,"props":1340,"children":1341},{},[1342,1365,1387,1409,1432,1454,1476,1498,1520,1542],{"type":64,"tag":323,"props":1343,"children":1344},{},[1345,1350,1355,1360],{"type":64,"tag":355,"props":1346,"children":1347},{},[1348],{"type":70,"value":1349},"SD0009",{"type":64,"tag":355,"props":1351,"children":1352},{},[1353],{"type":70,"value":1354},"USUBJID not consistent with DM",{"type":64,"tag":355,"props":1356,"children":1357},{},[1358],{"type":70,"value":1359},"Error",{"type":64,"tag":355,"props":1361,"children":1362},{},[1363],{"type":70,"value":1364},"Fix immediately — breaks traceability",{"type":64,"tag":323,"props":1366,"children":1367},{},[1368,1373,1378,1382],{"type":64,"tag":355,"props":1369,"children":1370},{},[1371],{"type":70,"value":1372},"SD0083",{"type":64,"tag":355,"props":1374,"children":1375},{},[1376],{"type":70,"value":1377},"Missing required variable",{"type":64,"tag":355,"props":1379,"children":1380},{},[1381],{"type":70,"value":1359},{"type":64,"tag":355,"props":1383,"children":1384},{},[1385],{"type":70,"value":1386},"Fix — submission will be rejected",{"type":64,"tag":323,"props":1388,"children":1389},{},[1390,1395,1400,1404],{"type":64,"tag":355,"props":1391,"children":1392},{},[1393],{"type":70,"value":1394},"SD1001",{"type":64,"tag":355,"props":1396,"children":1397},{},[1398],{"type":70,"value":1399},"Invalid date\u002Ftime format",{"type":64,"tag":355,"props":1401,"children":1402},{},[1403],{"type":70,"value":1359},{"type":64,"tag":355,"props":1405,"children":1406},{},[1407],{"type":70,"value":1408},"Fix — ISO 8601 non-negotiable",{"type":64,"tag":323,"props":1410,"children":1411},{},[1412,1417,1422,1427],{"type":64,"tag":355,"props":1413,"children":1414},{},[1415],{"type":70,"value":1416},"CT2001",{"type":64,"tag":355,"props":1418,"children":1419},{},[1420],{"type":70,"value":1421},"CT mismatch (value not in codelist)",{"type":64,"tag":355,"props":1423,"children":1424},{},[1425],{"type":70,"value":1426},"Warning",{"type":64,"tag":355,"props":1428,"children":1429},{},[1430],{"type":70,"value":1431},"Fix if non-extensible codelist; document if sponsor extension",{"type":64,"tag":323,"props":1433,"children":1434},{},[1435,1440,1445,1449],{"type":64,"tag":355,"props":1436,"children":1437},{},[1438],{"type":70,"value":1439},"CT2003",{"type":64,"tag":355,"props":1441,"children":1442},{},[1443],{"type":70,"value":1444},"CT version inconsistency",{"type":64,"tag":355,"props":1446,"children":1447},{},[1448],{"type":70,"value":1426},{"type":64,"tag":355,"props":1450,"children":1451},{},[1452],{"type":70,"value":1453},"Usually fix — indicates mixed CT versions",{"type":64,"tag":323,"props":1455,"children":1456},{},[1457,1462,1467,1471],{"type":64,"tag":355,"props":1458,"children":1459},{},[1460],{"type":70,"value":1461},"SD1020",{"type":64,"tag":355,"props":1463,"children":1464},{},[1465],{"type":70,"value":1466},"Value not found in external codelist",{"type":64,"tag":355,"props":1468,"children":1469},{},[1470],{"type":70,"value":1426},{"type":64,"tag":355,"props":1472,"children":1473},{},[1474],{"type":70,"value":1475},"Fix if standard term exists; extend if legitimate",{"type":64,"tag":323,"props":1477,"children":1478},{},[1479,1484,1489,1493],{"type":64,"tag":355,"props":1480,"children":1481},{},[1482],{"type":70,"value":1483},"AD0252",{"type":64,"tag":355,"props":1485,"children":1486},{},[1487],{"type":70,"value":1488},"ADSL missing required variables",{"type":64,"tag":355,"props":1490,"children":1491},{},[1492],{"type":70,"value":1359},{"type":64,"tag":355,"props":1494,"children":1495},{},[1496],{"type":70,"value":1497},"Fix — ADSL completeness is critical",{"type":64,"tag":323,"props":1499,"children":1500},{},[1501,1506,1511,1515],{"type":64,"tag":355,"props":1502,"children":1503},{},[1504],{"type":70,"value":1505},"AD0322",{"type":64,"tag":355,"props":1507,"children":1508},{},[1509],{"type":70,"value":1510},"BDS record without PARAMCD",{"type":64,"tag":355,"props":1512,"children":1513},{},[1514],{"type":70,"value":1359},{"type":64,"tag":355,"props":1516,"children":1517},{},[1518],{"type":70,"value":1519},"Fix — BDS is unusable without PARAMCD",{"type":64,"tag":323,"props":1521,"children":1522},{},[1523,1528,1533,1537],{"type":64,"tag":355,"props":1524,"children":1525},{},[1526],{"type":70,"value":1527},"SD0070",{"type":64,"tag":355,"props":1529,"children":1530},{},[1531],{"type":70,"value":1532},"Duplicate records",{"type":64,"tag":355,"props":1534,"children":1535},{},[1536],{"type":70,"value":1426},{"type":64,"tag":355,"props":1538,"children":1539},{},[1540],{"type":70,"value":1541},"Investigate — may be valid (e.g., bilateral findings)",{"type":64,"tag":323,"props":1543,"children":1544},{},[1545,1550,1555,1559],{"type":64,"tag":355,"props":1546,"children":1547},{},[1548],{"type":70,"value":1549},"SD1015",{"type":64,"tag":355,"props":1551,"children":1552},{},[1553],{"type":70,"value":1554},"Inconsistent values across datasets",{"type":64,"tag":355,"props":1556,"children":1557},{},[1558],{"type":70,"value":1426},{"type":64,"tag":355,"props":1560,"children":1561},{},[1562],{"type":70,"value":1563},"Fix if traceability broken; document if by design",{"type":64,"tag":73,"props":1565,"children":1567},{"id":1566},"_11-controlled-terminology-rules",[1568],{"type":70,"value":1569},"11. Controlled Terminology Rules",{"type":64,"tag":315,"props":1571,"children":1572},{},[1573,1588],{"type":64,"tag":319,"props":1574,"children":1575},{},[1576],{"type":64,"tag":323,"props":1577,"children":1578},{},[1579,1584],{"type":64,"tag":327,"props":1580,"children":1581},{},[1582],{"type":70,"value":1583},"Rule",{"type":64,"tag":327,"props":1585,"children":1586},{},[1587],{"type":70,"value":1328},{"type":64,"tag":348,"props":1589,"children":1590},{},[1591,1604,1616,1629,1642,1655],{"type":64,"tag":323,"props":1592,"children":1593},{},[1594,1599],{"type":64,"tag":355,"props":1595,"children":1596},{},[1597],{"type":70,"value":1598},"Pin CT version at study start",{"type":64,"tag":355,"props":1600,"children":1601},{},[1602],{"type":70,"value":1603},"One CT version for entire study",{"type":64,"tag":323,"props":1605,"children":1606},{},[1607,1611],{"type":64,"tag":355,"props":1608,"children":1609},{},[1610],{"type":70,"value":1242},{"type":64,"tag":355,"props":1612,"children":1613},{},[1614],{"type":70,"value":1615},"Specify package version (e.g., 2024-03-29)",{"type":64,"tag":323,"props":1617,"children":1618},{},[1619,1624],{"type":64,"tag":355,"props":1620,"children":1621},{},[1622],{"type":70,"value":1623},"Never mix versions",{"type":64,"tag":355,"props":1625,"children":1626},{},[1627],{"type":70,"value":1628},"Mixing CT within a study → P21 Warning CT2003",{"type":64,"tag":323,"props":1630,"children":1631},{},[1632,1637],{"type":64,"tag":355,"props":1633,"children":1634},{},[1635],{"type":70,"value":1636},"Non-extensible codelists",{"type":64,"tag":355,"props":1638,"children":1639},{},[1640],{"type":70,"value":1641},"Use ONLY CDISC-defined values (e.g., SEX, AEOUT)",{"type":64,"tag":323,"props":1643,"children":1644},{},[1645,1650],{"type":64,"tag":355,"props":1646,"children":1647},{},[1648],{"type":70,"value":1649},"Extensible codelists",{"type":64,"tag":355,"props":1651,"children":1652},{},[1653],{"type":70,"value":1654},"Sponsor values allowed but must be documented",{"type":64,"tag":323,"props":1656,"children":1657},{},[1658,1663],{"type":64,"tag":355,"props":1659,"children":1660},{},[1661],{"type":70,"value":1662},"Map legacy terms on upgrade",{"type":64,"tag":355,"props":1664,"children":1665},{},[1666],{"type":70,"value":1667},"Create mapping table; never silently change coded values",{"items":1669,"total":1849},[1670,1691,1712,1722,1735,1748,1758,1768,1789,1804,1819,1834],{"slug":1671,"name":1671,"fn":1672,"description":1673,"org":1674,"tags":1675,"stars":1688,"repoUrl":1689,"updatedAt":1690},"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},[1676,1679,1682,1685],{"name":1677,"slug":1678,"type":16},"AWS","aws",{"name":1680,"slug":1681,"type":16},"Debugging","debugging",{"name":1683,"slug":1684,"type":16},"Logs","logs",{"name":1686,"slug":1687,"type":16},"Observability","observability",9427,"https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fmcp","2026-07-12T08:37:22.601527",{"slug":1692,"name":1693,"fn":1694,"description":1695,"org":1696,"tags":1697,"stars":1688,"repoUrl":1689,"updatedAt":1711},"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},[1698,1701,1702,1705,1708],{"name":1699,"slug":1700,"type":16},"Aurora","aurora",{"name":1677,"slug":1678,"type":16},{"name":1703,"slug":1704,"type":16},"Database","database",{"name":1706,"slug":1707,"type":16},"Serverless","serverless",{"name":1709,"slug":1710,"type":16},"SQL","sql","2026-07-12T08:36:45.053393",{"slug":1713,"name":1714,"fn":1694,"description":1695,"org":1715,"tags":1716,"stars":1688,"repoUrl":1689,"updatedAt":1721},"aurora-dsql","aurora dsql",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1717,1718,1719,1720],{"name":1677,"slug":1678,"type":16},{"name":1703,"slug":1704,"type":16},{"name":1706,"slug":1707,"type":16},{"name":1709,"slug":1710,"type":16},"2026-07-12T08:36:42.694299",{"slug":1723,"name":1724,"fn":1694,"description":1695,"org":1725,"tags":1726,"stars":1688,"repoUrl":1689,"updatedAt":1734},"aws-dsql","aws dsql",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1727,1728,1729,1732,1733],{"name":1677,"slug":1678,"type":16},{"name":1703,"slug":1704,"type":16},{"name":1730,"slug":1731,"type":16},"Migration","migration",{"name":1706,"slug":1707,"type":16},{"name":1709,"slug":1710,"type":16},"2026-07-12T08:36:38.584057",{"slug":1736,"name":1737,"fn":1694,"description":1695,"org":1738,"tags":1739,"stars":1688,"repoUrl":1689,"updatedAt":1747},"distributed-postgres","distributed postgres",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1740,1741,1742,1745,1746],{"name":1677,"slug":1678,"type":16},{"name":1703,"slug":1704,"type":16},{"name":1743,"slug":1744,"type":16},"PostgreSQL","postgresql",{"name":1706,"slug":1707,"type":16},{"name":1709,"slug":1710,"type":16},"2026-07-12T08:36:46.530743",{"slug":1749,"name":1750,"fn":1694,"description":1695,"org":1751,"tags":1752,"stars":1688,"repoUrl":1689,"updatedAt":1757},"distributed-sql","distributed sql",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1753,1754,1755,1756],{"name":1677,"slug":1678,"type":16},{"name":1703,"slug":1704,"type":16},{"name":1706,"slug":1707,"type":16},{"name":1709,"slug":1710,"type":16},"2026-07-12T08:36:48.104182",{"slug":1759,"name":1759,"fn":1694,"description":1695,"org":1760,"tags":1761,"stars":1688,"repoUrl":1689,"updatedAt":1767},"dsql",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1762,1763,1764,1765,1766],{"name":1677,"slug":1678,"type":16},{"name":1703,"slug":1704,"type":16},{"name":1730,"slug":1731,"type":16},{"name":1706,"slug":1707,"type":16},{"name":1709,"slug":1710,"type":16},"2026-07-12T08:36:36.374512",{"slug":1769,"name":1769,"fn":1770,"description":1771,"org":1772,"tags":1773,"stars":1786,"repoUrl":1787,"updatedAt":1788},"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},[1774,1777,1780,1783],{"name":1775,"slug":1776,"type":16},"Accounting","accounting",{"name":1778,"slug":1779,"type":16},"Analytics","analytics",{"name":1781,"slug":1782,"type":16},"Cost Optimization","cost-optimization",{"name":1784,"slug":1785,"type":16},"Finance","finance",3176,"https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fagentcore-samples","2026-07-12T08:40:03.29555",{"slug":1790,"name":1790,"fn":1791,"description":1792,"org":1793,"tags":1794,"stars":1786,"repoUrl":1787,"updatedAt":1803},"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},[1795,1796,1797,1800],{"name":1677,"slug":1678,"type":16},{"name":1784,"slug":1785,"type":16},{"name":1798,"slug":1799,"type":16},"Management","management",{"name":1801,"slug":1802,"type":16},"Reporting","reporting","2026-07-12T08:40:02.066471",{"slug":1805,"name":1805,"fn":1806,"description":1807,"org":1808,"tags":1809,"stars":1786,"repoUrl":1787,"updatedAt":1818},"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},[1810,1811,1812,1815],{"name":1778,"slug":1779,"type":16},{"name":1784,"slug":1785,"type":16},{"name":1813,"slug":1814,"type":16},"Financial Statements","financial-statements",{"name":1816,"slug":1817,"type":16},"Variance Analysis","variance-analysis","2026-07-12T08:40:00.79141",{"slug":1820,"name":1820,"fn":1821,"description":1822,"org":1823,"tags":1824,"stars":1786,"repoUrl":1787,"updatedAt":1833},"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},[1825,1828,1831],{"name":1826,"slug":1827,"type":16},"Automation","automation",{"name":1829,"slug":1830,"type":16},"Documents","documents",{"name":1832,"slug":1820,"type":16},"PDF","2026-07-12T08:41:44.135656",{"slug":1835,"name":1835,"fn":1836,"description":1837,"org":1838,"tags":1839,"stars":1786,"repoUrl":1787,"updatedAt":1848},"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},[1840,1841,1844,1845],{"name":1775,"slug":1776,"type":16},{"name":1842,"slug":1843,"type":16},"Data Analysis","data-analysis",{"name":1784,"slug":1785,"type":16},{"name":1846,"slug":1847,"type":16},"KPI","kpi","2026-07-12T08:39:59.54971",150,{"items":1851,"total":1940},[1852,1870,1885,1891,1904,1917,1930],{"slug":1853,"name":1853,"fn":1854,"description":1855,"org":1856,"tags":1857,"stars":23,"repoUrl":24,"updatedAt":1869},"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},[1858,1861,1862,1865,1866],{"name":1859,"slug":1860,"type":16},"Architecture","architecture",{"name":1677,"slug":1678,"type":16},{"name":1863,"slug":1864,"type":16},"Healthcare","healthcare",{"name":18,"slug":19,"type":16},{"name":1867,"slug":1868,"type":16},"LLM","llm","2026-07-12T08:38:07.975937",{"slug":1871,"name":1871,"fn":1872,"description":1873,"org":1874,"tags":1875,"stars":23,"repoUrl":24,"updatedAt":1884},"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},[1876,1877,1880,1881],{"name":1677,"slug":1678,"type":16},{"name":1878,"slug":1879,"type":16},"Bioinformatics","bioinformatics",{"name":18,"slug":19,"type":16},{"name":1882,"slug":1883,"type":16},"Research","research","2026-07-12T08:37:49.295301",{"slug":4,"name":4,"fn":5,"description":6,"org":1886,"tags":1887,"stars":23,"repoUrl":24,"updatedAt":25},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1888,1889,1890],{"name":14,"slug":15,"type":16},{"name":18,"slug":19,"type":16},{"name":21,"slug":22,"type":16},{"slug":1892,"name":1892,"fn":1893,"description":1894,"org":1895,"tags":1896,"stars":23,"repoUrl":24,"updatedAt":1903},"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},[1897,1898,1899,1900],{"name":1878,"slug":1879,"type":16},{"name":1842,"slug":1843,"type":16},{"name":18,"slug":19,"type":16},{"name":1901,"slug":1902,"type":16},"RNA-seq","rna-seq","2026-07-12T08:38:05.443454",{"slug":1905,"name":1905,"fn":1906,"description":1907,"org":1908,"tags":1909,"stars":23,"repoUrl":24,"updatedAt":1916},"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},[1910,1911,1914,1915],{"name":1878,"slug":1879,"type":16},{"name":1912,"slug":1913,"type":16},"Chemistry","chemistry",{"name":1842,"slug":1843,"type":16},{"name":1882,"slug":1883,"type":16},"2026-07-12T08:37:28.334619",{"slug":1918,"name":1918,"fn":1919,"description":1920,"org":1921,"tags":1922,"stars":23,"repoUrl":24,"updatedAt":1929},"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},[1923,1924,1925,1928],{"name":1842,"slug":1843,"type":16},{"name":1863,"slug":1864,"type":16},{"name":1926,"slug":1927,"type":16},"Insurance","insurance",{"name":18,"slug":19,"type":16},"2026-07-12T08:37:34.815088",{"slug":1931,"name":1931,"fn":1932,"description":1933,"org":1934,"tags":1935,"stars":23,"repoUrl":24,"updatedAt":1939},"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},[1936,1937,1938],{"name":1863,"slug":1864,"type":16},{"name":1926,"slug":1927,"type":16},{"name":21,"slug":22,"type":16},"2026-07-12T08:38:28.210856",40]