[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6XG9XANP6E9TYR0J875ZX0F":3,"skill-same:01M6XG9XANP6E9TYR0J875ZX0F":162},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":41,"linkOnly":42,"markdownContent":43,"markdownBody":44,"frontMatter":45,"refName":46,"commitSha":47,"skillDirectory":48,"forksCount":49,"repositoryHtmlUrl":50,"repositoryHomepageUrl":6,"ownerHtmlUrl":51,"ownerBlogUrl":6,"ownerDescription":52,"updatedAt":53,"install":54,"resources":67},"01M6XG9XANP6E9TYR0J875ZX0F","healthsim-trialsim",null,"Generate realistic clinical trial synthetic data including study definitions, sites, subjects, visits, adverse events, efficacy assessments, and disposition. Use when user requests: clinical trial data, CDISC\u002FSDTM\u002FADaM datasets, trial cohorts (Phase I\u002FII\u002FIII\u002FIV), FDA submission test data, or specific therapeutic areas like oncology or biologics\u002FCGT.","FDU-INS\u002FInsurance-Skills","FDU-INS","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F167067594?v=4","01M6XEYMRS4CVJMZ834YWE66BV","FDU-Insurance","01M6XEYMXPDA34HFM0ZE6AY78G",82,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Ftrialsim\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40],"trialsim","healthsim","healthsim trialsim","sites","when","phase","submission","oncology","requests","events","synthetic","test","iii","clinical","test data","study","datasets","fda","use","data","generate","synthetic data","2026-11-10 10:12:30",false,"---\nname: healthsim-trialsim\ndescription: \"Generate realistic clinical trial synthetic data including study definitions, sites, subjects, visits, adverse events, efficacy assessments, and disposition. Use when user requests: clinical trial data, CDISC\u002FSDTM\u002FADaM datasets, trial cohorts (Phase I\u002FII\u002FIII\u002FIV), FDA submission test data, or specific therapeutic areas like oncology or biologics\u002FCGT.\"\n---\n\n# TrialSim\n\n**Status**: Active Development\n\nTrialSim generates realistic synthetic clinical trial data for testing, training, and development purposes.\n\n## For Claude\n\nUse this skill when the user requests clinical trial data, CDISC-compliant datasets, or regulatory submission test data. This is the primary skill for generating realistic synthetic clinical trial data.\n\n**When to apply this skill:**\n\n- User mentions clinical trials, studies, or protocols\n- User requests CDISC, SDTM, or ADaM datasets\n- User specifies trial phases (Phase I, II, III, IV)\n- User mentions FDA\u002FEMA submission data or regulatory requirements\n- User asks for adverse events, safety data, or efficacy endpoints\n- User mentions specific therapeutic areas (oncology, cardiovascular, CNS)\n- User requests SDTM domains (DM, AE, VS, LB, CM, EX, DS, MH)\n\n**Key capabilities:**\n\n- Generate complete study definitions with protocol parameters\n- Create multi-site, multi-country trial configurations\n- Produce subject-level longitudinal data with realistic patterns\n- Generate safety data (adverse events, labs, vitals) with MedDRA\u002FLOINC coding\n- Create efficacy endpoints for various therapeutic areas\n- Output CDISC-compliant formats (SDTM, ADaM)\n\nFor specific trial phases, therapeutic areas, or SDTM domains, load the appropriate skill from the tables below.\n\n## Safety Guardrails\n\n**All data generated by TrialSim is synthetic and fictional.** It must never be used for real clinical decisions, patient care, or regulatory submissions without explicit disclaimers.\n\n- **Synthetic data only:** All subjects, sites, adverse events, and results are generated\u002Fsimulated. Always confirm this when presenting output.\n- **No clinical advice:** Never recommend treatments, prescribe medications, or interpret safety signals as if data were real. If asked \"should this patient receive X?\", remind the user this is synthetic test data.\n- **Real codes, synthetic entities:** Use real standard code systems (ICD-10, CPT, LOINC, SNOMED CT, MedDRA, RxNorm, NDC, NPI, ATC, HCPCS) for coding accuracy, but all people, sites, and events are fictional.\n- **Do NOT generate:** Real patient identifiers, actual investigator names, real site addresses, or any data that could be confused with actual clinical trial records.\n\n## Trigger Phrases\n\nActivate TrialSim when user mentions:\n- \"clinical trial\" or \"clinical study\"\n- \"Phase I\u002FII\u002FIII\u002FIV\" or \"pivotal trial\"\n- \"CDISC\", \"SDTM\", \"ADaM\"\n- \"FDA submission data\" or \"regulatory data\"\n- \"adverse events\" or \"safety data\"\n- \"efficacy endpoints\"\n- Trial therapeutic areas (oncology, cardiology, etc.)\n- SDTM domains (DM, AE, VS, LB, CM, EX, DS)\n\n## Quick Links\n\n### Core Skills\n\n| Topic | Skill | Description |\n|-------|-------|-------------|\n| Domain Knowledge | [clinical-trials-domain.md](clinical-trials-domain.md) | Core trial concepts, phases, regulatory |\n| Recruitment | [recruitment-enrollment.md](recruitment-enrollment.md) | Screening funnel, enrollment patterns |\n\n### Trial Phase Skills\n\n| Phase | Skill | Description |\n|-------|-------|-------------|\n| Phase 1 | [phase1-dose-escalation.md](phase1-dose-escalation.md) | FIH, dose escalation, MTD (3+3, BOIN, CRM) |\n| Phase 2 | [phase2-proof-of-concept.md](phase2-proof-of-concept.md) | POC, dose-ranging, futility (Simon's, MCP-Mod) |\n| Phase 3 | [phase3-pivotal.md](phase3-pivotal.md) | Pivotal registration trials, NDA\u002FBLA |\n\n### SDTM Domain Skills\n\n| Domain | Skill | Description |\n|--------|-------|-------------|\n| DM | [domains\u002Fdemographics-dm.md](domains\u002Fdemographics-dm.md) | Subject demographics, treatment arms |\n| AE | [domains\u002Fadverse-events-ae.md](domains\u002Fadverse-events-ae.md) | Adverse events with MedDRA coding |\n| VS | [domains\u002Fvital-signs-vs.md](domains\u002Fvital-signs-vs.md) | Vital sign measurements |\n| LB | [domains\u002Flaboratory-lb.md](domains\u002Flaboratory-lb.md) | Laboratory results with LOINC |\n| CM | [domains\u002Fconcomitant-meds-cm.md](domains\u002Fconcomitant-meds-cm.md) | Concomitant medications with ATC |\n| EX | [domains\u002Fexposure-ex.md](domains\u002Fexposure-ex.md) | Study drug exposure, dose modifications |\n| DS | [domains\u002Fdisposition-ds.md](domains\u002Fdisposition-ds.md) | Subject disposition, discontinuation |\n| MH | [domains\u002Fmedical-history-mh.md](domains\u002Fmedical-history-mh.md) | Medical history, comorbidities |\n| RS\u002FTR | [therapeutic-areas\u002Foncology.md](therapeutic-areas\u002Foncology.md) | Tumor results \u002F disease response (RECIST) |\n| Domain Index | [domains\u002FREADME.md](domains\u002FREADME.md) | All SDTM domains overview |\n\n### Therapeutic Areas\n\n| Area | Skill | Key Endpoints |\n|------|-------|---------------|\n| Oncology | [therapeutic-areas\u002Foncology.md](therapeutic-areas\u002Foncology.md) | Tumor response (RECIST), ORR, PFS, OS |\n| Cardiovascular | [therapeutic-areas\u002Fcardiovascular.md](therapeutic-areas\u002Fcardiovascular.md) | MACE, CV outcomes |\n| CNS | [therapeutic-areas\u002Fcns.md](therapeutic-areas\u002Fcns.md) | Cognitive scales, imaging |\n| CGT | [therapeutic-areas\u002Fcgt.md](therapeutic-areas\u002Fcgt.md) | CAR-T, gene therapy |\n\n### Real World Evidence\n\n| Topic | Skill | Description |\n|-------|-------|-------------|\n| RWE Overview | [rwe\u002Foverview.md](rwe\u002Foverview.md) | RWE concepts, data sources |\n| Synthetic Controls | [rwe\u002Fsynthetic-control.md](rwe\u002Fsynthetic-control.md) | External control arm generation |\n\n## Output Formats\n\n| Format | Skill | Use Case |\n|--------|-------|----------|\n| SDTM | [..\u002F..\u002Fformats\u002Fcdisc-sdtm.md](..\u002F..\u002Fformats\u002Fcdisc-sdtm.md) | Regulatory submission |\n| ADaM | [..\u002F..\u002Fformats\u002Fcdisc-adam.md](..\u002F..\u002Fformats\u002Fcdisc-adam.md) | Statistical analysis |\n| Dimensional | [..\u002F..\u002Fformats\u002Fdimensional-analytics.md](..\u002F..\u002Fformats\u002Fdimensional-analytics.md) | BI dashboards, analytics |\n| JSON | Default | API integration |\n| CSV | [..\u002F..\u002Fformats\u002Fcsv.md](..\u002F..\u002Fformats\u002Fcsv.md) | Spreadsheet analysis |\n\n## Data Models & References\n\n| Resource | Location | Description |\n|----------|----------|-------------|\n| Canonical Models | [..\u002F..\u002Freferences\u002Fdata-models.md#trialsim-models](..\u002F..\u002Freferences\u002Fdata-models.md#trialsim-models) | 15 entity schemas (Subject, Study, Site, AE, etc.) |\n| Dimensional Schema | [..\u002F..\u002Fformats\u002Fdimensional-analytics.md#trialsim-clinical-trial-analytics](..\u002F..\u002Fformats\u002Fdimensional-analytics.md#trialsim-clinical-trial-analytics) | Star schema for BI (7 dims, 6 facts) |\n| Code Systems | [..\u002F..\u002Freferences\u002Fcode-systems.md](..\u002F..\u002Freferences\u002Fcode-systems.md) | MedDRA, LOINC, ATC, ICD-10, SNOMED CT, RxNorm, NDC, NPI, HCPCS, CPT |\n\n## Core Entities\n\nTrialSim uses 15 canonical entity schemas. See [Data Models Reference](..\u002F..\u002Freferences\u002Fdata-models.md#trialsim-models) for complete JSON schemas.\n\n### Entity Overview\n\n| Entity | SDTM Domain | Description |\n|--------|-------------|-------------|\n| Subject | DM | Trial participant (extends Person) |\n| Study | TS | Protocol definition |\n| Site | - | Investigational site |\n| TreatmentArm | TA | Study arm definition |\n| VisitSchedule | TV | Protocol visits |\n| ActualVisit | SV | Subject visit occurrence |\n| Randomization | DM\u002FSE | Subject randomization |\n| AdverseEvent | AE | Safety events with MedDRA |\n| Exposure | EX | Study drug dosing |\n| ConcomitantMed | CM | Prior\u002Fconcomitant meds with ATC |\n| TrialLab | LB | Lab results with LOINC |\n| EfficacyAssessment | RS\u002FTR | Response assessments |\n| MedicalHistory | MH | Pre-existing conditions |\n| DispositionEvent | DS | Subject disposition |\n| ProtocolDeviation | DV | Protocol deviations |\n\n### Key Entity Examples\n\n**Study:**\n```json\n{\n  \"study_id\": \"ABC-123-001\",\n  \"protocol_title\": \"A Phase 3, Randomized, Double-Blind Study...\",\n  \"phase\": \"Phase 3\",\n  \"therapeutic_area\": \"Oncology\",\n  \"indication\": \"Non-Small Cell Lung Cancer\",\n  \"sponsor\": \"Example Pharma Inc.\",\n  \"status\": \"Ongoing\"\n}\n```\n\n**Subject (with cross-product linking):**\n```json\n{\n  \"subject_id\": \"0001\",\n  \"usubjid\": \"ABC-123-001-001-0001\",\n  \"site_id\": \"001\",\n  \"patient_ref\": \"MRN-12345\",\n  \"screening_date\": \"2024-01-15\",\n  \"randomization_date\": \"2024-01-22\",\n  \"treatment_arm\": \"TRT\",\n  \"status\": \"Active\"\n}\n```\n\n## Integration with Other Products\n\nTrialSim integrates with other HealthSim products for complete clinical trial data:\n\n| From | To | Integration Pattern |\n|------|-----|---------------------|\n| PatientSim | TrialSim | Patient → Subject (add consent, randomization, protocol visits) |\n| NetworkSim | TrialSim | Provider → Investigator (add credentials, training, delegation log) |\n| PopulationSim | TrialSim | Demographics → Recruitment pool (geographic, demographic eligibility) |\n\n### Cross-Product: PatientSim\n\nTrial subjects are patients with additional trial-specific data:\n\n- [..\u002Fpatientsim\u002Foncology\u002F](..\u002Fpatientsim\u002Foncology\u002F) - Oncology trial subjects\n- [..\u002Fpatientsim\u002Fheart-failure.md](..\u002Fpatientsim\u002Fheart-failure.md) - CV outcomes trial subjects\n- [..\u002Fpatientsim\u002Fbehavioral-health.md](..\u002Fpatientsim\u002Fbehavioral-health.md) - CNS trial subjects\n- [..\u002Fpatientsim\u002Fdiabetes-management.md](..\u002Fpatientsim\u002Fdiabetes-management.md) - Metabolic trial subjects\n\n> **Integration Pattern:** Use PatientSim for baseline clinical characteristics. TrialSim adds protocol-specific assessments (RECIST, NYHA class changes), randomization, and SDTM-formatted data.\n\n### Cross-Product: PopulationSim Integration\n\nPopulationSim provides embedded real-world data (CDC PLACES, SVI, ADI) for evidence-based trial planning, site selection, and FDA diversity compliance. When geographies are specified, TrialSim grounds feasibility estimates and enrollment projections in actual prevalence and demographic data.\n\nSee [populationsim-integration.md](populationsim-integration.md) for detailed data-driven planning patterns, embedded data sources, and site selection examples.\n\n## Development Status\n\nAll skill files complete: core skills, Phase 1-3, SDTM domains (DM, AE, VS, LB, CM, EX, DS, MH), therapeutic areas, and RWE.\n\n## Related Skills\n\n- [PatientSim](..\u002Fpatientsim\u002FSKILL.md) - Clinical patient data\n- [MemberSim](..\u002Fmembersim\u002FSKILL.md) - Claims integration\n- [Code Systems](..\u002F..\u002Freferences\u002Fcode-systems.md) - Standard terminologies (ICD-10, CPT, LOINC, SNOMED, RxNorm, NDC, HCPCS)\n\n## Usage Examples\n\n### Example 1: Basic Phase 3 Trial\n\n**Prompt:** \"Generate a Phase 3 oncology trial with 200 subjects\"\n\n**Output:**\n```json\n{\n  \"study\": {\n    \"study_id\": \"ONCO-2025-001\",\n    \"protocol_title\": \"A Phase 3, Randomized, Double-Blind, Placebo-Controlled Study of ABC-123 in Advanced NSCLC\",\n    \"phase\": \"Phase 3\",\n    \"therapeutic_area\": \"Oncology\",\n    \"indication\": \"Non-Small Cell Lung Cancer\",\n    \"design\": \"Randomized, Double-Blind, Placebo-Controlled\",\n    \"primary_endpoint\": \"Overall Survival\",\n    \"target_enrollment\": 200,\n    \"arms\": [\n      { \"arm_id\": \"A\", \"name\": \"ABC-123 + SOC\", \"allocation_ratio\": 1 },\n      { \"arm_id\": \"B\", \"name\": \"Placebo + SOC\", \"allocation_ratio\": 1 }\n    ]\n  },\n  \"sites\": [\n    { \"site_id\": \"001\", \"name\": \"Memorial Cancer Center\", \"country\": \"USA\", \"enrolled\": 25 },\n    { \"site_id\": \"002\", \"name\": \"University Oncology\", \"country\": \"USA\", \"enrolled\": 22 }\n  ],\n  \"subjects\": [\n    {\n      \"subject_id\": \"001-0001\",\n      \"site_id\": \"001\",\n      \"arm\": \"A\",\n      \"status\": \"Active\",\n      \"randomization_date\": \"2025-01-15\"\n    }\n  ]\n}\n```\n\n### Example 2: Adverse Events with MedDRA\n\n**Prompt:** \"Generate adverse events for a 50-subject immunotherapy trial\"\n\n**Output:**\n```json\n{\n  \"domain\": \"AE\",\n  \"adverse_events\": [\n    {\n      \"USUBJID\": \"IO-001-0023\",\n      \"AESEQ\": 1,\n      \"AETERM\": \"Fatigue\",\n      \"AEDECOD\": \"Fatigue\",\n      \"AEBODSYS\": \"General disorders and administration site conditions\",\n      \"AESEV\": \"MILD\",\n      \"AESER\": \"N\",\n      \"AEREL\": \"POSSIBLY RELATED\",\n      \"AESTDTC\": \"2025-02-10\",\n      \"AEENDTC\": \"2025-02-18\",\n      \"AEOUT\": \"RECOVERED\u002FRESOLVED\"\n    },\n    {\n      \"USUBJID\": \"IO-001-0007\",\n      \"AESEQ\": 1,\n      \"AETERM\": \"Immune-mediated colitis\",\n      \"AEDECOD\": \"Colitis\",\n      \"AEBODSYS\": \"Gastrointestinal disorders\",\n      \"AESEV\": \"SEVERE\",\n      \"AESER\": \"Y\",\n      \"AESHOSP\": \"Y\",\n      \"AEREL\": \"RELATED\",\n      \"AEACN\": \"DRUG INTERRUPTED\",\n      \"AESTDTC\": \"2025-03-05\",\n      \"AEOUT\": \"NOT RECOVERED\u002FNOT RESOLVED\"\n    }\n  ]\n}\n```\n\n### Example 3: Screening and Enrollment\n\n**Prompt:** \"Generate screening data with 30% screen failure rate for 100 subjects\"\n\n**Output:**\n```json\n{\n  \"screening_summary\": {\n    \"total_screened\": 143,\n    \"screen_passed\": 100,\n    \"screen_failed\": 43,\n    \"screen_failure_rate\": 0.30\n  },\n  \"screen_failures\": [\n    {\n      \"screening_id\": \"SCR-0015\",\n      \"failure_reason\": \"Inclusion criteria not met\",\n      \"failure_detail\": \"EGFR mutation negative\",\n      \"screening_date\": \"2025-01-20\"\n    },\n    {\n      \"screening_id\": \"SCR-0028\",\n      \"failure_reason\": \"Exclusion criteria met\",\n      \"failure_detail\": \"Prior immunotherapy within 6 months\",\n      \"screening_date\": \"2025-01-25\"\n    }\n  ]\n}\n```\n\n### Example 4: DM Domain SDTM Output\n\n**Prompt:** \"Generate DM domain for 10 subjects as SDTM\"\n\n**Output:**\n```json\n{\n  \"domain\": \"DM\",\n  \"records\": [\n    {\n      \"STUDYID\": \"ONCO-2025-001\",\n      \"DOMAIN\": \"DM\",\n      \"USUBJID\": \"ONCO-2025-001-001-0001\",\n      \"SUBJID\": \"0001\",\n      \"SITEID\": \"001\",\n      \"RFSTDTC\": \"2025-01-22\",\n      \"RFENDTC\": null,\n      \"BRTHDTC\": \"1958-05-15\",\n      \"AGE\": 66,\n      \"AGEU\": \"YEARS\",\n      \"SEX\": \"M\",\n      \"RACE\": \"WHITE\",\n      \"ETHNIC\": \"NOT HISPANIC OR LATINO\",\n      \"ARMCD\": \"TRT\",\n      \"ARM\": \"ABC-123 + SOC\",\n      \"COUNTRY\": \"USA\"\n    }\n  ]\n}\n```\n\n### Example 5: Laboratory Results with LOINC\n\n**Prompt:** \"Generate LB domain with liver function tests for safety monitoring\"\n\n**Output:**\n```json\n{\n  \"domain\": \"LB\",\n  \"records\": [\n    {\n      \"STUDYID\": \"SAFE-001\",\n      \"DOMAIN\": \"LB\",\n      \"USUBJID\": \"SAFE-001-001-0042\",\n      \"LBSEQ\": 1,\n      \"LBTESTCD\": \"ALT\",\n      \"LBTEST\": \"Alanine Aminotransferase\",\n      \"LBCAT\": \"CHEMISTRY\",\n      \"LBORRES\": \"32\",\n      \"LBORRESU\": \"U\u002FL\",\n      \"LBSTRESN\": 32,\n      \"LBSTRESU\": \"U\u002FL\",\n      \"LBSTNRLO\": 7,\n      \"LBSTNRHI\": 56,\n      \"LBNRIND\": \"NORMAL\",\n      \"LBLOINC\": \"1742-6\",\n      \"LBBLFL\": \"Y\",\n      \"VISITNUM\": 2,\n      \"VISIT\": \"BASELINE\"\n    }\n  ]\n}\n```\n\n---\n\n### Example 6: ADaM Datasets (ADSL + ADTTE)\n\n**Prompt:** \"Derive ADSL and ADTTE datasets from the SDTM data for this trial\"\n\n**ADSL (subject-level analysis dataset with baseline characteristics):**\n```json\n{\n  \"dataset\": \"ADSL\",\n  \"records\": [\n    {\n      \"STUDYID\": \"ONCO-2025-001\", \"USUBJID\": \"ONCO-2025-001-001-0001\",\n      \"SUBJID\": \"0001\", \"SITEID\": \"001\", \"TRT01P\": \"ABC-123 + SOC\",\n      \"AGE\": 66, \"SEX\": \"M\", \"RACE\": \"WHITE\",\n      \"RFSTDTC\": \"2025-01-22\", \"RFENDTC\": \"2025-07-15\",\n      \"EOSSTT\": \"COMPLETED\", \"DCSREAS\": null,\n      \"BMIBL\": 24.3, \"ECOGBL\": 1\n    }\n  ]\n}\n```\n\n**ADTTE (time-to-event analysis dataset):**\n```json\n{\n  \"dataset\": \"ADTTE\",\n  \"records\": [\n    {\n      \"STUDYID\": \"ONCO-2025-001\", \"USUBJID\": \"ONCO-2025-001-001-0001\",\n      \"PARAMCD\": \"PFS\", \"PARAM\": \"Progression-Free Survival\",\n      \"AVAL\": 182, \"AVALU\": \"DAYS\",\n      \"CNSR\": 0, \"EVNTDESC\": \"Disease Progression (RECIST)\",\n      \"STARTDT\": \"2025-01-22\", \"ADT\": \"2025-07-23\"\n    },\n    {\n      \"STUDYID\": \"ONCO-2025-001\", \"USUBJID\": \"ONCO-2025-001-001-0002\",\n      \"PARAMCD\": \"OS\", \"PARAM\": \"Overall Survival\",\n      \"AVAL\": 365, \"AVALU\": \"DAYS\",\n      \"CNSR\": 1, \"EVNTDESC\": \"Censored (alive at cutoff)\",\n      \"STARTDT\": \"2025-01-29\", \"ADT\": \"2026-01-29\"\n    }\n  ]\n}\n```\n\n---\n\n## Generative Framework Integration\n\nTrialSim integrates with the [Generative Framework](..\u002Fgeneration\u002FSKILL.md) for specification-driven generation at scale.\n\n### Profile-Driven Generation\n\nUse profile specifications to generate trial subject populations. The Profile Executor samples demographics meeting I\u002FE criteria, generates baseline disease characteristics, applies randomization, and creates screening assessments.\n\n### Journey-Driven Generation\n\nAttach protocol journey specifications to create visit sequences. The Journey Executor generates protocol visits at specified windows, creates assessments per schedule, applies visit variance, and handles protocol deviations and early termination.\n\n### Cross-Domain Sync\n\nWhen generating across products, TrialSim entities are automatically linked:\n\n| TrialSim Entity | Links To |\n|-----------------|----------|\n| Subject | PatientSim Patient (via SSN) |\n| Site | NetworkSim Facility |\n| Investigator | NetworkSim Provider |\n| Conmed | RxMemberSim Fill (if applicable) |\n\nSee: [..\u002Fgeneration\u002Fexecutors\u002Fcross-domain-sync.md](..\u002Fgeneration\u002Fexecutors\u002Fcross-domain-sync.md)\n","# TrialSim\n\n**Status**: Active Development\n\nTrialSim generates realistic synthetic clinical trial data for testing, training, and development purposes.\n\n## For Claude\n\nUse this skill when the user requests clinical trial data, CDISC-compliant datasets, or regulatory submission test data. This is the primary skill for generating realistic synthetic clinical trial data.\n\n**When to apply this skill:**\n\n- User mentions clinical trials, studies, or protocols\n- User requests CDISC, SDTM, or ADaM datasets\n- User specifies trial phases (Phase I, II, III, IV)\n- User mentions FDA\u002FEMA submission data or regulatory requirements\n- User asks for adverse events, safety data, or efficacy endpoints\n- User mentions specific therapeutic areas (oncology, cardiovascular, CNS)\n- User requests SDTM domains (DM, AE, VS, LB, CM, EX, DS, MH)\n\n**Key capabilities:**\n\n- Generate complete study definitions with protocol parameters\n- Create multi-site, multi-country trial configurations\n- Produce subject-level longitudinal data with realistic patterns\n- Generate safety data (adverse events, labs, vitals) with MedDRA\u002FLOINC coding\n- Create efficacy endpoints for various therapeutic areas\n- Output CDISC-compliant formats (SDTM, ADaM)\n\nFor specific trial phases, therapeutic areas, or SDTM domains, load the appropriate skill from the tables below.\n\n## Safety Guardrails\n\n**All data generated by TrialSim is synthetic and fictional.** It must never be used for real clinical decisions, patient care, or regulatory submissions without explicit disclaimers.\n\n- **Synthetic data only:** All subjects, sites, adverse events, and results are generated\u002Fsimulated. Always confirm this when presenting output.\n- **No clinical advice:** Never recommend treatments, prescribe medications, or interpret safety signals as if data were real. If asked \"should this patient receive X?\", remind the user this is synthetic test data.\n- **Real codes, synthetic entities:** Use real standard code systems (ICD-10, CPT, LOINC, SNOMED CT, MedDRA, RxNorm, NDC, NPI, ATC, HCPCS) for coding accuracy, but all people, sites, and events are fictional.\n- **Do NOT generate:** Real patient identifiers, actual investigator names, real site addresses, or any data that could be confused with actual clinical trial records.\n\n## Trigger Phrases\n\nActivate TrialSim when user mentions:\n- \"clinical trial\" or \"clinical study\"\n- \"Phase I\u002FII\u002FIII\u002FIV\" or \"pivotal trial\"\n- \"CDISC\", \"SDTM\", \"ADaM\"\n- \"FDA submission data\" or \"regulatory data\"\n- \"adverse events\" or \"safety data\"\n- \"efficacy endpoints\"\n- Trial therapeutic areas (oncology, cardiology, etc.)\n- SDTM domains (DM, AE, VS, LB, CM, EX, DS)\n\n## Quick Links\n\n### Core Skills\n\n| Topic | Skill | Description |\n|-------|-------|-------------|\n| Domain Knowledge | [clinical-trials-domain.md](clinical-trials-domain.md) | Core trial concepts, phases, regulatory |\n| Recruitment | [recruitment-enrollment.md](recruitment-enrollment.md) | Screening funnel, enrollment patterns |\n\n### Trial Phase Skills\n\n| Phase | Skill | Description |\n|-------|-------|-------------|\n| Phase 1 | [phase1-dose-escalation.md](phase1-dose-escalation.md) | FIH, dose escalation, MTD (3+3, BOIN, CRM) |\n| Phase 2 | [phase2-proof-of-concept.md](phase2-proof-of-concept.md) | POC, dose-ranging, futility (Simon's, MCP-Mod) |\n| Phase 3 | [phase3-pivotal.md](phase3-pivotal.md) | Pivotal registration trials, NDA\u002FBLA |\n\n### SDTM Domain Skills\n\n| Domain | Skill | Description |\n|--------|-------|-------------|\n| DM | [domains\u002Fdemographics-dm.md](domains\u002Fdemographics-dm.md) | Subject demographics, treatment arms |\n| AE | [domains\u002Fadverse-events-ae.md](domains\u002Fadverse-events-ae.md) | Adverse events with MedDRA coding |\n| VS | [domains\u002Fvital-signs-vs.md](domains\u002Fvital-signs-vs.md) | Vital sign measurements |\n| LB | [domains\u002Flaboratory-lb.md](domains\u002Flaboratory-lb.md) | Laboratory results with LOINC |\n| CM | [domains\u002Fconcomitant-meds-cm.md](domains\u002Fconcomitant-meds-cm.md) | Concomitant medications with ATC |\n| EX | [domains\u002Fexposure-ex.md](domains\u002Fexposure-ex.md) | Study drug exposure, dose modifications |\n| DS | [domains\u002Fdisposition-ds.md](domains\u002Fdisposition-ds.md) | Subject disposition, discontinuation |\n| MH | [domains\u002Fmedical-history-mh.md](domains\u002Fmedical-history-mh.md) | Medical history, comorbidities |\n| RS\u002FTR | [therapeutic-areas\u002Foncology.md](therapeutic-areas\u002Foncology.md) | Tumor results \u002F disease response (RECIST) |\n| Domain Index | [domains\u002FREADME.md](domains\u002FREADME.md) | All SDTM domains overview |\n\n### Therapeutic Areas\n\n| Area | Skill | Key Endpoints |\n|------|-------|---------------|\n| Oncology | [therapeutic-areas\u002Foncology.md](therapeutic-areas\u002Foncology.md) | Tumor response (RECIST), ORR, PFS, OS |\n| Cardiovascular | [therapeutic-areas\u002Fcardiovascular.md](therapeutic-areas\u002Fcardiovascular.md) | MACE, CV outcomes |\n| CNS | [therapeutic-areas\u002Fcns.md](therapeutic-areas\u002Fcns.md) | Cognitive scales, imaging |\n| CGT | [therapeutic-areas\u002Fcgt.md](therapeutic-areas\u002Fcgt.md) | CAR-T, gene therapy |\n\n### Real World Evidence\n\n| Topic | Skill | Description |\n|-------|-------|-------------|\n| RWE Overview | [rwe\u002Foverview.md](rwe\u002Foverview.md) | RWE concepts, data sources |\n| Synthetic Controls | [rwe\u002Fsynthetic-control.md](rwe\u002Fsynthetic-control.md) | External control arm generation |\n\n## Output Formats\n\n| Format | Skill | Use Case |\n|--------|-------|----------|\n| SDTM | [..\u002F..\u002Fformats\u002Fcdisc-sdtm.md](..\u002F..\u002Fformats\u002Fcdisc-sdtm.md) | Regulatory submission |\n| ADaM | [..\u002F..\u002Fformats\u002Fcdisc-adam.md](..\u002F..\u002Fformats\u002Fcdisc-adam.md) | Statistical analysis |\n| Dimensional | [..\u002F..\u002Fformats\u002Fdimensional-analytics.md](..\u002F..\u002Fformats\u002Fdimensional-analytics.md) | BI dashboards, analytics |\n| JSON | Default | API integration |\n| CSV | [..\u002F..\u002Fformats\u002Fcsv.md](..\u002F..\u002Fformats\u002Fcsv.md) | Spreadsheet analysis |\n\n## Data Models & References\n\n| Resource | Location | Description |\n|----------|----------|-------------|\n| Canonical Models | [..\u002F..\u002Freferences\u002Fdata-models.md#trialsim-models](..\u002F..\u002Freferences\u002Fdata-models.md#trialsim-models) | 15 entity schemas (Subject, Study, Site, AE, etc.) |\n| Dimensional Schema | [..\u002F..\u002Fformats\u002Fdimensional-analytics.md#trialsim-clinical-trial-analytics](..\u002F..\u002Fformats\u002Fdimensional-analytics.md#trialsim-clinical-trial-analytics) | Star schema for BI (7 dims, 6 facts) |\n| Code Systems | [..\u002F..\u002Freferences\u002Fcode-systems.md](..\u002F..\u002Freferences\u002Fcode-systems.md) | MedDRA, LOINC, ATC, ICD-10, SNOMED CT, RxNorm, NDC, NPI, HCPCS, CPT |\n\n## Core Entities\n\nTrialSim uses 15 canonical entity schemas. See [Data Models Reference](..\u002F..\u002Freferences\u002Fdata-models.md#trialsim-models) for complete JSON schemas.\n\n### Entity Overview\n\n| Entity | SDTM Domain | Description |\n|--------|-------------|-------------|\n| Subject | DM | Trial participant (extends Person) |\n| Study | TS | Protocol definition |\n| Site | - | Investigational site |\n| TreatmentArm | TA | Study arm definition |\n| VisitSchedule | TV | Protocol visits |\n| ActualVisit | SV | Subject visit occurrence |\n| Randomization | DM\u002FSE | Subject randomization |\n| AdverseEvent | AE | Safety events with MedDRA |\n| Exposure | EX | Study drug dosing |\n| ConcomitantMed | CM | Prior\u002Fconcomitant meds with ATC |\n| TrialLab | LB | Lab results with LOINC |\n| EfficacyAssessment | RS\u002FTR | Response assessments |\n| MedicalHistory | MH | Pre-existing conditions |\n| DispositionEvent | DS | Subject disposition |\n| ProtocolDeviation | DV | Protocol deviations |\n\n### Key Entity Examples\n\n**Study:**\n```json\n{\n  \"study_id\": \"ABC-123-001\",\n  \"protocol_title\": \"A Phase 3, Randomized, Double-Blind Study...\",\n  \"phase\": \"Phase 3\",\n  \"therapeutic_area\": \"Oncology\",\n  \"indication\": \"Non-Small Cell Lung Cancer\",\n  \"sponsor\": \"Example Pharma Inc.\",\n  \"status\": \"Ongoing\"\n}\n```\n\n**Subject (with cross-product linking):**\n```json\n{\n  \"subject_id\": \"0001\",\n  \"usubjid\": \"ABC-123-001-001-0001\",\n  \"site_id\": \"001\",\n  \"patient_ref\": \"MRN-12345\",\n  \"screening_date\": \"2024-01-15\",\n  \"randomization_date\": \"2024-01-22\",\n  \"treatment_arm\": \"TRT\",\n  \"status\": \"Active\"\n}\n```\n\n## Integration with Other Products\n\nTrialSim integrates with other HealthSim products for complete clinical trial data:\n\n| From | To | Integration Pattern |\n|------|-----|---------------------|\n| PatientSim | TrialSim | Patient → Subject (add consent, randomization, protocol visits) |\n| NetworkSim | TrialSim | Provider → Investigator (add credentials, training, delegation log) |\n| PopulationSim | TrialSim | Demographics → Recruitment pool (geographic, demographic eligibility) |\n\n### Cross-Product: PatientSim\n\nTrial subjects are patients with additional trial-specific data:\n\n- [..\u002Fpatientsim\u002Foncology\u002F](..\u002Fpatientsim\u002Foncology\u002F) - Oncology trial subjects\n- [..\u002Fpatientsim\u002Fheart-failure.md](..\u002Fpatientsim\u002Fheart-failure.md) - CV outcomes trial subjects\n- [..\u002Fpatientsim\u002Fbehavioral-health.md](..\u002Fpatientsim\u002Fbehavioral-health.md) - CNS trial subjects\n- [..\u002Fpatientsim\u002Fdiabetes-management.md](..\u002Fpatientsim\u002Fdiabetes-management.md) - Metabolic trial subjects\n\n> **Integration Pattern:** Use PatientSim for baseline clinical characteristics. TrialSim adds protocol-specific assessments (RECIST, NYHA class changes), randomization, and SDTM-formatted data.\n\n### Cross-Product: PopulationSim Integration\n\nPopulationSim provides embedded real-world data (CDC PLACES, SVI, ADI) for evidence-based trial planning, site selection, and FDA diversity compliance. When geographies are specified, TrialSim grounds feasibility estimates and enrollment projections in actual prevalence and demographic data.\n\nSee [populationsim-integration.md](populationsim-integration.md) for detailed data-driven planning patterns, embedded data sources, and site selection examples.\n\n## Development Status\n\nAll skill files complete: core skills, Phase 1-3, SDTM domains (DM, AE, VS, LB, CM, EX, DS, MH), therapeutic areas, and RWE.\n\n## Related Skills\n\n- [PatientSim](..\u002Fpatientsim\u002FSKILL.md) - Clinical patient data\n- [MemberSim](..\u002Fmembersim\u002FSKILL.md) - Claims integration\n- [Code Systems](..\u002F..\u002Freferences\u002Fcode-systems.md) - Standard terminologies (ICD-10, CPT, LOINC, SNOMED, RxNorm, NDC, HCPCS)\n\n## Usage Examples\n\n### Example 1: Basic Phase 3 Trial\n\n**Prompt:** \"Generate a Phase 3 oncology trial with 200 subjects\"\n\n**Output:**\n```json\n{\n  \"study\": {\n    \"study_id\": \"ONCO-2025-001\",\n    \"protocol_title\": \"A Phase 3, Randomized, Double-Blind, Placebo-Controlled Study of ABC-123 in Advanced NSCLC\",\n    \"phase\": \"Phase 3\",\n    \"therapeutic_area\": \"Oncology\",\n    \"indication\": \"Non-Small Cell Lung Cancer\",\n    \"design\": \"Randomized, Double-Blind, Placebo-Controlled\",\n    \"primary_endpoint\": \"Overall Survival\",\n    \"target_enrollment\": 200,\n    \"arms\": [\n      { \"arm_id\": \"A\", \"name\": \"ABC-123 + SOC\", \"allocation_ratio\": 1 },\n      { \"arm_id\": \"B\", \"name\": \"Placebo + SOC\", \"allocation_ratio\": 1 }\n    ]\n  },\n  \"sites\": [\n    { \"site_id\": \"001\", \"name\": \"Memorial Cancer Center\", \"country\": \"USA\", \"enrolled\": 25 },\n    { \"site_id\": \"002\", \"name\": \"University Oncology\", \"country\": \"USA\", \"enrolled\": 22 }\n  ],\n  \"subjects\": [\n    {\n      \"subject_id\": \"001-0001\",\n      \"site_id\": \"001\",\n      \"arm\": \"A\",\n      \"status\": \"Active\",\n      \"randomization_date\": \"2025-01-15\"\n    }\n  ]\n}\n```\n\n### Example 2: Adverse Events with MedDRA\n\n**Prompt:** \"Generate adverse events for a 50-subject immunotherapy trial\"\n\n**Output:**\n```json\n{\n  \"domain\": \"AE\",\n  \"adverse_events\": [\n    {\n      \"USUBJID\": \"IO-001-0023\",\n      \"AESEQ\": 1,\n      \"AETERM\": \"Fatigue\",\n      \"AEDECOD\": \"Fatigue\",\n      \"AEBODSYS\": \"General disorders and administration site conditions\",\n      \"AESEV\": \"MILD\",\n      \"AESER\": \"N\",\n      \"AEREL\": \"POSSIBLY RELATED\",\n      \"AESTDTC\": \"2025-02-10\",\n      \"AEENDTC\": \"2025-02-18\",\n      \"AEOUT\": \"RECOVERED\u002FRESOLVED\"\n    },\n    {\n      \"USUBJID\": \"IO-001-0007\",\n      \"AESEQ\": 1,\n      \"AETERM\": \"Immune-mediated colitis\",\n      \"AEDECOD\": \"Colitis\",\n      \"AEBODSYS\": \"Gastrointestinal disorders\",\n      \"AESEV\": \"SEVERE\",\n      \"AESER\": \"Y\",\n      \"AESHOSP\": \"Y\",\n      \"AEREL\": \"RELATED\",\n      \"AEACN\": \"DRUG INTERRUPTED\",\n      \"AESTDTC\": \"2025-03-05\",\n      \"AEOUT\": \"NOT RECOVERED\u002FNOT RESOLVED\"\n    }\n  ]\n}\n```\n\n### Example 3: Screening and Enrollment\n\n**Prompt:** \"Generate screening data with 30% screen failure rate for 100 subjects\"\n\n**Output:**\n```json\n{\n  \"screening_summary\": {\n    \"total_screened\": 143,\n    \"screen_passed\": 100,\n    \"screen_failed\": 43,\n    \"screen_failure_rate\": 0.30\n  },\n  \"screen_failures\": [\n    {\n      \"screening_id\": \"SCR-0015\",\n      \"failure_reason\": \"Inclusion criteria not met\",\n      \"failure_detail\": \"EGFR mutation negative\",\n      \"screening_date\": \"2025-01-20\"\n    },\n    {\n      \"screening_id\": \"SCR-0028\",\n      \"failure_reason\": \"Exclusion criteria met\",\n      \"failure_detail\": \"Prior immunotherapy within 6 months\",\n      \"screening_date\": \"2025-01-25\"\n    }\n  ]\n}\n```\n\n### Example 4: DM Domain SDTM Output\n\n**Prompt:** \"Generate DM domain for 10 subjects as SDTM\"\n\n**Output:**\n```json\n{\n  \"domain\": \"DM\",\n  \"records\": [\n    {\n      \"STUDYID\": \"ONCO-2025-001\",\n      \"DOMAIN\": \"DM\",\n      \"USUBJID\": \"ONCO-2025-001-001-0001\",\n      \"SUBJID\": \"0001\",\n      \"SITEID\": \"001\",\n      \"RFSTDTC\": \"2025-01-22\",\n      \"RFENDTC\": null,\n      \"BRTHDTC\": \"1958-05-15\",\n      \"AGE\": 66,\n      \"AGEU\": \"YEARS\",\n      \"SEX\": \"M\",\n      \"RACE\": \"WHITE\",\n      \"ETHNIC\": \"NOT HISPANIC OR LATINO\",\n      \"ARMCD\": \"TRT\",\n      \"ARM\": \"ABC-123 + SOC\",\n      \"COUNTRY\": \"USA\"\n    }\n  ]\n}\n```\n\n### Example 5: Laboratory Results with LOINC\n\n**Prompt:** \"Generate LB domain with liver function tests for safety monitoring\"\n\n**Output:**\n```json\n{\n  \"domain\": \"LB\",\n  \"records\": [\n    {\n      \"STUDYID\": \"SAFE-001\",\n      \"DOMAIN\": \"LB\",\n      \"USUBJID\": \"SAFE-001-001-0042\",\n      \"LBSEQ\": 1,\n      \"LBTESTCD\": \"ALT\",\n      \"LBTEST\": \"Alanine Aminotransferase\",\n      \"LBCAT\": \"CHEMISTRY\",\n      \"LBORRES\": \"32\",\n      \"LBORRESU\": \"U\u002FL\",\n      \"LBSTRESN\": 32,\n      \"LBSTRESU\": \"U\u002FL\",\n      \"LBSTNRLO\": 7,\n      \"LBSTNRHI\": 56,\n      \"LBNRIND\": \"NORMAL\",\n      \"LBLOINC\": \"1742-6\",\n      \"LBBLFL\": \"Y\",\n      \"VISITNUM\": 2,\n      \"VISIT\": \"BASELINE\"\n    }\n  ]\n}\n```\n\n---\n\n### Example 6: ADaM Datasets (ADSL + ADTTE)\n\n**Prompt:** \"Derive ADSL and ADTTE datasets from the SDTM data for this trial\"\n\n**ADSL (subject-level analysis dataset with baseline characteristics):**\n```json\n{\n  \"dataset\": \"ADSL\",\n  \"records\": [\n    {\n      \"STUDYID\": \"ONCO-2025-001\", \"USUBJID\": \"ONCO-2025-001-001-0001\",\n      \"SUBJID\": \"0001\", \"SITEID\": \"001\", \"TRT01P\": \"ABC-123 + SOC\",\n      \"AGE\": 66, \"SEX\": \"M\", \"RACE\": \"WHITE\",\n      \"RFSTDTC\": \"2025-01-22\", \"RFENDTC\": \"2025-07-15\",\n      \"EOSSTT\": \"COMPLETED\", \"DCSREAS\": null,\n      \"BMIBL\": 24.3, \"ECOGBL\": 1\n    }\n  ]\n}\n```\n\n**ADTTE (time-to-event analysis dataset):**\n```json\n{\n  \"dataset\": \"ADTTE\",\n  \"records\": [\n    {\n      \"STUDYID\": \"ONCO-2025-001\", \"USUBJID\": \"ONCO-2025-001-001-0001\",\n      \"PARAMCD\": \"PFS\", \"PARAM\": \"Progression-Free Survival\",\n      \"AVAL\": 182, \"AVALU\": \"DAYS\",\n      \"CNSR\": 0, \"EVNTDESC\": \"Disease Progression (RECIST)\",\n      \"STARTDT\": \"2025-01-22\", \"ADT\": \"2025-07-23\"\n    },\n    {\n      \"STUDYID\": \"ONCO-2025-001\", \"USUBJID\": \"ONCO-2025-001-001-0002\",\n      \"PARAMCD\": \"OS\", \"PARAM\": \"Overall Survival\",\n      \"AVAL\": 365, \"AVALU\": \"DAYS\",\n      \"CNSR\": 1, \"EVNTDESC\": \"Censored (alive at cutoff)\",\n      \"STARTDT\": \"2025-01-29\", \"ADT\": \"2026-01-29\"\n    }\n  ]\n}\n```\n\n---\n\n## Generative Framework Integration\n\nTrialSim integrates with the [Generative Framework](..\u002Fgeneration\u002FSKILL.md) for specification-driven generation at scale.\n\n### Profile-Driven Generation\n\nUse profile specifications to generate trial subject populations. The Profile Executor samples demographics meeting I\u002FE criteria, generates baseline disease characteristics, applies randomization, and creates screening assessments.\n\n### Journey-Driven Generation\n\nAttach protocol journey specifications to create visit sequences. The Journey Executor generates protocol visits at specified windows, creates assessments per schedule, applies visit variance, and handles protocol deviations and early termination.\n\n### Cross-Domain Sync\n\nWhen generating across products, TrialSim entities are automatically linked:\n\n| TrialSim Entity | Links To |\n|-----------------|----------|\n| Subject | PatientSim Patient (via SSN) |\n| Site | NetworkSim Facility |\n| Investigator | NetworkSim Provider |\n| Conmed | RxMemberSim Fill (if applicable) |\n\nSee: [..\u002Fgeneration\u002Fexecutors\u002Fcross-domain-sync.md](..\u002Fgeneration\u002Fexecutors\u002Fcross-domain-sync.md)\n",{"name":5,"description":7},"main","b22eca2e974f918ce591c5b2bd829fb7510e0191","Skills\u002Fhealthsim-2\u002Ftrialsim",18,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills","https:\u002F\u002Fgithub.com\u002FFDU-INS","Fudan University Department of Risk Management and Insurance","2026-07-12 12:54:34",{"source":8,"skillName":5,"commands":55,"prompt":65,"zipAvailable":66},[56,59,62],{"tool":57,"command":58},"npx","npx skills add FDU-INS\u002FInsurance-Skills --skill healthsim-trialsim",{"tool":60,"command":61},"bunx","bunx skills add FDU-INS\u002FInsurance-Skills --skill healthsim-trialsim",{"tool":63,"command":64},"pnpm","pnpm dlx skills add FDU-INS\u002FInsurance-Skills --skill healthsim-trialsim","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Ftrialsim\u002FSKILL.md",true,[68,74,78,82,86,90,94,98,102,106,110,114,118,122,126,130,134,138,142,146,150,154,158],{"path":69,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":72,"sourceHtmlUrl":73},"clinical-trials-domain.md","REFERENCE","参考文档",3727,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Ftrialsim\u002Fclinical-trials-domain.md",{"path":75,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":76,"sourceHtmlUrl":77},"domains\u002Fadverse-events-ae.md",12264,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Ftrialsim\u002Fdomains\u002Fadverse-events-ae.md",{"path":79,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":80,"sourceHtmlUrl":81},"domains\u002Fconcomitant-meds-cm.md",12976,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Ftrialsim\u002Fdomains\u002Fconcomitant-meds-cm.md",{"path":83,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":84,"sourceHtmlUrl":85},"domains\u002Fdemographics-dm.md",10903,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Ftrialsim\u002Fdomains\u002Fdemographics-dm.md",{"path":87,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":88,"sourceHtmlUrl":89},"domains\u002Fdisposition-ds.md",14033,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Ftrialsim\u002Fdomains\u002Fdisposition-ds.md",{"path":91,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":92,"sourceHtmlUrl":93},"domains\u002Fexposure-ex.md",15340,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Ftrialsim\u002Fdomains\u002Fexposure-ex.md",{"path":95,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":96,"sourceHtmlUrl":97},"domains\u002Flaboratory-lb.md",12092,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Ftrialsim\u002Fdomains\u002Flaboratory-lb.md",{"path":99,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":100,"sourceHtmlUrl":101},"domains\u002Fmedical-history-mh.md",16686,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Ftrialsim\u002Fdomains\u002Fmedical-history-mh.md",{"path":103,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":104,"sourceHtmlUrl":105},"domains\u002FREADME.md",4932,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Ftrialsim\u002Fdomains\u002FREADME.md",{"path":107,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":108,"sourceHtmlUrl":109},"domains\u002Fvital-signs-vs.md",12194,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Ftrialsim\u002Fdomains\u002Fvital-signs-vs.md",{"path":111,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":112,"sourceHtmlUrl":113},"phase1-dose-escalation.md",27618,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Ftrialsim\u002Fphase1-dose-escalation.md",{"path":115,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":116,"sourceHtmlUrl":117},"phase2-proof-of-concept.md",27657,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Ftrialsim\u002Fphase2-proof-of-concept.md",{"path":119,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":120,"sourceHtmlUrl":121},"phase3-pivotal.md",21983,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Ftrialsim\u002Fphase3-pivotal.md",{"path":123,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":124,"sourceHtmlUrl":125},"README.md",5240,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Ftrialsim\u002FREADME.md",{"path":127,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":128,"sourceHtmlUrl":129},"recruitment-enrollment.md",14693,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Ftrialsim\u002Frecruitment-enrollment.md",{"path":131,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":132,"sourceHtmlUrl":133},"rwe\u002Foverview.md",3997,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Ftrialsim\u002Frwe\u002Foverview.md",{"path":135,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":136,"sourceHtmlUrl":137},"rwe\u002FREADME.md",1295,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Ftrialsim\u002Frwe\u002FREADME.md",{"path":139,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":140,"sourceHtmlUrl":141},"rwe\u002Fsynthetic-control.md",3329,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Ftrialsim\u002Frwe\u002Fsynthetic-control.md",{"path":143,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":144,"sourceHtmlUrl":145},"therapeutic-areas\u002Fcardiovascular.md",4475,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Ftrialsim\u002Ftherapeutic-areas\u002Fcardiovascular.md",{"path":147,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":148,"sourceHtmlUrl":149},"therapeutic-areas\u002Fcgt.md",4832,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Ftrialsim\u002Ftherapeutic-areas\u002Fcgt.md",{"path":151,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":152,"sourceHtmlUrl":153},"therapeutic-areas\u002Fcns.md",4896,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Ftrialsim\u002Ftherapeutic-areas\u002Fcns.md",{"path":155,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":156,"sourceHtmlUrl":157},"therapeutic-areas\u002Foncology.md",7608,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Ftrialsim\u002Ftherapeutic-areas\u002Foncology.md",{"path":159,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":160,"sourceHtmlUrl":161},"therapeutic-areas\u002FREADME.md",1552,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Ftrialsim\u002Ftherapeutic-areas\u002FREADME.md",[163,193,217,248,270,301],{"skillNo":164,"name":165,"nameZh":6,"description":166,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":167,"categories":168,"keywords":174,"publishedAt":41},"01M713QW6EGEG0YAD75440GSD0","로인장 (Roinjiang)","Activates when the user needs legal advice, contract review, insurance law consultation, startup legal support, or any legal\u002Fregulatory matter. She is a top-tier in-house lawyer with absolute loyalty to the CEO, specializing in insurance law, financial consumer protection, privacy, contracts, labor law, family law, civil and criminal matters.","https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002F로인장 (Roinjiang)\u002FSKILL.md",[169],{"categoryNo":170,"categoryName":171,"taxonomyType":172,"taxonomyTypeDesc":173},"01JBSEEDCAT000000000000037","律师与法务","PROFESSION","适用职业",[165,175,176,177,178,179,23,180,181,182,183,184,185,186,187,188,189,190,191,192],"insurance law","insurance","civil","contract","family","review","loyalty","with","top","contract review","ceo","support","advice","consultation","regulatory","privacy","protection","startup",{"skillNo":194,"name":195,"nameZh":6,"description":196,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":197,"categories":198,"keywords":199,"publishedAt":41},"01M713QRN8VFMA9VKS6R4DJ2WS","zocdoc-doctor-finder","Use when a user needs to find a doctor, dentist, specialist, therapist, or healthcare provider — especially when they mention insurance, in-network, availability, location, appointments, or booking. Also use for browsing provider reviews, comparing doctors by specialty, or checking if a provider takes their insurance.","https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fzocdoc-doctor-finder\u002FSKILL.md",[],[200,201,202,203,176,204,205,23,206,207,208,209,210,211,212,213,214,215,37,216],"zocdoc doctor finder","doctor","healthcare","reviews","browser automation","access","browsing","browser","booking","network","therapist","computer","availability","for","provider","tool","automation",{"skillNo":218,"name":219,"nameZh":6,"description":220,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":221,"categories":222,"keywords":228,"publishedAt":41},"01M713QKGV3FTX7EEYWKDM8ENZ","zenmux-context","Answers any question about ZenMux by reading the latest official documentation. Use this skill whenever the user asks about ZenMux product features, API usage, configuration, integration, pricing, models, providers, routing, fallback, streaming, multimodal, structured output, tool calling, reasoning, prompt caching, image generation, video generation, web search, long context, observability, logs, cost tracking, usage analytics, insurance, subscription, pay-as-you-go, invoices, best practices for tools like Claude Code, Cursor, Cline, CodeX, Gemini CLI, opencode, Cherry Studio, Obsidian, Sider, Open-WebUI, Dify, Neovate, GitHub Copilot, OpenClaw, CC-Switch, Immersive Translate, Studio Chat, architecture, benchmarks, FAQ, contact, privacy, terms of service, compliance, or any other ZenMux-related topic. Also trigger when the user writes in Chinese about ZenMux: 文档, 使用指南, 快速开始, API 参考, 最佳实践, 模型路由, 供应商路由, 订阅, 按量计费, 可观测性, 帮助, 常见问题, 接入指南, 配置. Trigger on phrases like \"how to use ZenMux\", \"ZenMux docs\", \"ZenMux API\", \"ZenMux integration\", \"ZenMux 怎么用\", \"ZenMux 接入\", \"ZenMux 配置\". Even if the user doesn't say \"ZenMux\" explicitly but asks about LLM API aggregation, model routing, provider fallback in a context where ZenMux is the project being worked on, this skill should activate.","https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fzenmux-context\u002FSKILL.md",[223],{"categoryNo":224,"categoryName":225,"taxonomyType":226,"taxonomyTypeDesc":227},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",[229,230,231,232,176,233,234,235,236,237,238,239,240,241,242,243,244,245,246,247],"context","zenmux context","Video","chinese","project","web search","translate","search","open","question","pay","image","you","activate","architecture","logs","streaming","cherry studio","how",{"skillNo":249,"name":250,"nameZh":6,"description":251,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":252,"categories":253,"keywords":254,"publishedAt":41},"01M713QHWTBG634BCBV7NBJME1","workers-comp-guide","Guide workers compensation compliance and claims management.\nTRIGGERS - Use when user needs help with workers-comp-guide related tasks.","https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fworkers-comp-guide\u002FSKILL.md",[],[255,256,257,258,259,176,260,261,37,23,262,182,263,264,265,266,267,268,269],"workers","comp","workers comp","workers comp guide","guide","triggers","workers-comp","tasks","claims management","claims","compliance","help","compensation","management","user",{"skillNo":271,"name":272,"nameZh":6,"description":273,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":274,"categories":275,"keywords":285,"publishedAt":41},"01M713QF45VMV1685AFNF1GPMA","weekly-kpi-report","Generate McKinsey-style board presentation PPTs from weekly auto insurance data. Automatically calculates 16+ KPIs, creates executive-level slides with actionable insights, and supports week-over-week comparisons. Use when user uploads insurance cost data (Excel\u002FCSV) and requests board report, weekly presentation, executive briefing, or mentions keywords like 董事会汇报, 周报PPT, 经营分析演示, McKinsey-style reports.","https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fweekly-kpi-report\u002FSKILL.md",[276,279,282],{"categoryNo":277,"categoryName":278,"taxonomyType":226,"taxonomyTypeDesc":227},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":280,"categoryName":281,"taxonomyType":226,"taxonomyTypeDesc":227},"01JBSEEDCAT000000000000004","电子表格",{"categoryNo":283,"categoryName":284,"taxonomyType":172,"taxonomyTypeDesc":173},"01JBSEEDCAT000000000000034","行政与办公人员",[286,287,288,289,290,176,291,292,293,294,23,295,296,39,297,38,298,299,37,300],"weekly","weekly kpi report","kpi","report","xlsx","actionable","insights","briefing","auto","board report","reports","演示","presentation","slides","uploads",{"skillNo":302,"name":303,"nameZh":6,"description":304,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":305,"categories":306,"keywords":310,"publishedAt":41},"01M713QA9WJDHMNVTTY1ENRKVB","wealth-advisory","Wealth management and financial planning for HNW and UHNW clients. Activate when the user\nmentions wealth management, financial planning, retirement, estate planning, tax planning,\nGRAT, IDGT, trust, asset allocation, withdrawal rate, Monte Carlo simulation, goals-based\ninvesting, tax-loss harvesting, Roth conversion, insurance, annuity, mortgage strategy,\nconcentrated stock, family office, direct indexing, 529 plan, charitable giving, donor-advised\nfund, private foundation, or asks about personal finance strategy, inheritance, long-term\nfinancial planning, or UHNW advisory.","https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fwealth-advisory\u002FSKILL.md",[307],{"categoryNo":308,"categoryName":309,"taxonomyType":172,"taxonomyTypeDesc":173},"01JBSEEDCAT000000000000040","财务",[311,312,176,313,314,23,242,315,316,317,318,319,320,321,322,323,324,325,326,327],"wealth advisory","advisory","stock","inheritance","conversion","indexing","plan","simulation","personal finance","rate","allocation","asset","direct","personal","investing","trust","planning"]