[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DANHPN4S4DG2Z7EKVWZ63D":3,"skill-same:01M6DANHPN4S4DG2Z7EKVWZ63D":108},{"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":28,"publishedAt":48,"linkOnly":49,"markdownContent":50,"markdownBody":51,"frontMatter":52,"refName":53,"commitSha":54,"skillDirectory":55,"forksCount":14,"repositoryHtmlUrl":56,"repositoryHomepageUrl":6,"ownerHtmlUrl":57,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":58,"install":59,"resources":72},"01M6DANHPN4S4DG2Z7EKVWZ63D","tooluniverse-clinical-trial-design",null,"Strategic clinical trial design feasibility assessment using ToolUniverse. Evaluates patient population sizing, biomarker prevalence, endpoint selection, comparator analysis, safety monitoring, and regulatory pathways. Creates comprehensive feasibility reports with evidence grading, enrollment projections, and trial design recommendations. Use when planning Phase 1\u002F2 trials, assessing trial feasibility, or designing biomarker-driven studies.","Prekzursil\u002Fagent-skills-toolchain","Prekzursil","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F54636077?v=4","01M6DACZ1PCQHD99SCR1YXG28B","Andrei Mihai Visalon","01M6DACZ670WZF535V3WYYSS4Z",0,"MIT","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-clinical-trial-design\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47],"tooluniverse clinical trial design","clinical","design","regulatory","driven","patient","recommendations","grading","selection","reports","evidence","use","analysis","Safety","endpoint","monitoring","planning","assessment","feasibility","2026-11-10 10:12:30",false,"---\nname: tooluniverse-clinical-trial-design\ndescription: Strategic clinical trial design feasibility assessment using ToolUniverse. Evaluates patient population sizing, biomarker prevalence, endpoint selection, comparator analysis, safety monitoring, and regulatory pathways. Creates comprehensive feasibility reports with evidence grading, enrollment projections, and trial design recommendations. Use when planning Phase 1\u002F2 trials, assessing trial feasibility, or designing biomarker-driven studies.\n---\n\n# Clinical Trial Design Feasibility Assessment\n\nSystematically assess clinical trial feasibility by analyzing 6 research dimensions. Produces comprehensive feasibility reports with quantitative enrollment projections, endpoint recommendations, and regulatory pathway analysis.\n\n**IMPORTANT**: Always use English terms in tool calls (drug names, disease names, biomarker names), even if the user writes in another language. Only try original-language terms as a fallback if English returns no results. Respond in the user's language.\n\n## Reasoning Before Searching\n\nTrial design starts with the question, not the methods. Answer these four questions before running any tools — they determine everything else:\n\n1. **What is the primary endpoint?** Is it overall survival (gold standard but slow), PFS (faster but surrogate), ORR (single-arm friendly but not always accepted), or a biomarker (needs validation as surrogate first)? The endpoint determines FDA pathway, statistical design, and duration.\n2. **Who is the population?** Broad unselected vs. biomarker-enriched. Enriched populations have higher response rates, allowing smaller trials — but require a validated companion diagnostic and reduce the eligible patient pool.\n3. **What is the comparator?** Placebo (only if no standard of care exists), active control (requires non-inferiority or superiority framing), or single-arm with historical control (acceptable for rare diseases or breakthrough designations, but FDA scrutiny is high).\n4. **Is the effect size realistic given the mechanism?** A 20% improvement in ORR over SOC requires ~100 patients per arm. A 50% improvement requires ~30. If the mechanism only justifies a 10% improvement, the trial may be underpowered regardless of design. Check precedent effect sizes in similar trials before committing to an endpoint.\n\nThese four answers determine sample size, duration, and trial design. Look them up from precedent trials and FDA guidance — do not derive them from first principles.\n\n**LOOK UP DON'T GUESS**: Never assume what the standard of care is for an indication — look it up with DrugBank and FDA tools. Never assume an endpoint is FDA-accepted — verify with `search_clinical_trials` precedents and `OpenFDA_get_approval_history`. Never estimate prevalence from memory — use OpenTargets, gnomAD, or COSMIC.\n\n## Core Principles\n\n### 1. Report-First Approach (MANDATORY)\n**DO NOT** show tool outputs to user. Instead:\n1. Create `[INDICATION]_trial_feasibility_report.md` FIRST\n2. Initialize with all section headers\n3. Progressively update as data arrives\n4. Present only the final report\n\n### 2. Evidence Grading System\n\n| Grade | Symbol | Criteria | Examples |\n|-------|--------|----------|----------|\n| **A** | 3-star | Regulatory acceptance, multiple precedents | FDA-approved endpoint in same indication |\n| **B** | 2-star | Clinical validation, single precedent | Phase 3 trial in related indication |\n| **C** | 1-star | Preclinical or exploratory | Phase 1 use, biomarker validation ongoing |\n| **D** | 0-star | Proposed, no validation | Novel endpoint, no precedent |\n\n### 3. Feasibility Score (0-100)\nWeighted composite score:\n- **Patient Availability** (30%): Population size x biomarker prevalence x geography\n- **Endpoint Precedent** (25%): Historical use, regulatory acceptance\n- **Regulatory Clarity** (20%): Pathway defined, precedents exist\n- **Comparator Feasibility** (15%): Standard of care availability\n- **Safety Monitoring** (10%): Known risks, monitoring established\n\n**Interpretation**: >=75 HIGH (proceed), 50-74 MODERATE (additional validation), \u003C50 LOW (de-risking required)\n\n---\n\n## When to Use This Skill\n\nApply when users:\n- Plan early-phase trials (Phase 1\u002F2 emphasis)\n- Need enrollment feasibility assessment\n- Design biomarker-selected trials\n- Evaluate endpoint strategies\n- Assess regulatory pathways\n- Compare trial design options\n- Need safety monitoring plans\n\n**Trigger phrases**: \"clinical trial design\", \"trial feasibility\", \"enrollment projections\", \"endpoint selection\", \"trial planning\", \"Phase 1\u002F2 design\", \"basket trial\", \"biomarker trial\"\n\n---\n\n## Core Strategy: 6 Research Paths\n\nExecute 6 parallel research dimensions. See `STUDY_DESIGN_PROCEDURES.md` for detailed steps per path.\n\n```\nTrial Design Query\n|\n+-- PATH 1: Patient Population Sizing\n|   Disease prevalence, biomarker prevalence, geographic distribution,\n|   eligibility criteria impact, enrollment projections\n|\n+-- PATH 2: Biomarker Prevalence & Testing\n|   Mutation frequency, testing availability, turnaround time,\n|   cost\u002Freimbursement, alternative biomarkers\n|\n+-- PATH 3: Comparator Selection\n|   Standard of care, approved comparators, historical controls,\n|   placebo appropriateness, combination therapy\n|\n+-- PATH 4: Endpoint Selection\n|   Primary endpoint precedents, FDA acceptance history,\n|   measurement feasibility, surrogate vs clinical endpoints\n|\n+-- PATH 5: Safety Endpoints & Monitoring\n|   Mechanism-based toxicity, class effects, organ-specific monitoring,\n|   DLT history, safety monitoring plan\n|\n+-- PATH 6: Regulatory Pathway\n    Regulatory precedents (505(b)(1), 505(b)(2)), breakthrough therapy,\n    orphan drug, fast track, FDA guidance\n```\n\n---\n\n## Report Structure (14 Sections)\n\nCreate `[INDICATION]_trial_feasibility_report.md` with all 14 sections. See `REPORT_TEMPLATE.md` for full templates with fillable fields.\n\n1. **Executive Summary** - Feasibility score, key findings, go\u002Fno-go recommendation\n2. **Disease Background** - Prevalence, incidence, SOC, unmet need\n3. **Patient Population Analysis** - Base population, biomarker selection, eligibility funnel, enrollment projections\n4. **Biomarker Strategy** - Primary biomarker, alternatives, testing logistics\n5. **Endpoint Selection & Justification** - Primary\u002Fsecondary\u002Fexploratory endpoints, statistical considerations\n6. **Comparator Analysis** - SOC, trial design options (single-arm vs randomized vs non-inferiority), drug sourcing\n7. **Safety Endpoints & Monitoring Plan** - DLT definition, mechanism-based toxicities, organ monitoring, SMC\n8. **Study Design Recommendations** - Phase, design type, schema, eligibility, treatment plan, assessment schedule\n9. **Enrollment & Site Strategy** - Site selection, enrollment projections, recruitment strategies\n10. **Regulatory Pathway** - FDA pathway, precedents, pre-IND meeting, IND timeline\n11. **Budget & Resource Considerations** - Cost drivers, timeline, FTE requirements\n12. **Risk Assessment** - Feasibility risks, scientific risks, mitigation strategies\n13. **Success Criteria & Go\u002FNo-Go Decision** - Phase 1\u002F2 criteria, interim analysis, feasibility scorecard\n14. **Recommendations & Next Steps** - Final recommendation, critical path to IND, alternative designs\n\n---\n\n## Tool Reference by Research Path\n\n### PATH 1: Patient Population Sizing\n- `OpenTargets_get_disease_id_description_by_name` - Disease lookup\n- `OpenTargets_get_diseases_phenotypes_by_target_ensembl` - Prevalence data\n- `ClinVar_search_variants` - Biomarker mutation frequency\n- `gnomad_search_variants` - Population allele frequencies\n- `PubMed_search_articles` - Epidemiology literature\n- `search_clinical_trials` - Enrollment feasibility from past trials\n\n### PATH 2: Biomarker Prevalence & Testing\n- `ClinVar_get_variant_details` - Variant pathogenicity\n- `COSMIC_search_mutations` - Cancer-specific mutation frequencies\n- `gnomad_get_variant` - Population genetics\n- `PubMed_search_articles` - CDx test performance, guidelines\n\n### PATH 3: Comparator Selection\n- `drugbank_get_drug_basic_info_by_drug_name_or_id` - Drug info\n- `drugbank_get_indications_by_drug_name_or_drugbank_id` - Approved indications\n- `drugbank_get_pharmacology_by_drug_name_or_drugbank_id` - Mechanism\n- `FDA_OrangeBook_search_drug` - Generic availability\n- `OpenFDA_get_approval_history` - Approval details\n- `search_clinical_trials` - Historical control data\n\n### PATH 4: Endpoint Selection\n- `search_clinical_trials` - Precedent trials, endpoints used\n- `PubMed_search_articles` - FDA acceptance history, endpoint validation\n- `OpenFDA_get_approval_history` - Approved endpoints by indication\n\n### PATH 5: Safety Endpoints & Monitoring\n- `drugbank_get_pharmacology_by_drug_name_or_drugbank_id` - Mechanism toxicity\n- `FDA_get_warnings_and_cautions_by_drug_name` - FDA black box warnings\n- `FAERS_search_reports_by_drug_and_reaction` - Real-world adverse events\n- `FAERS_count_reactions_by_drug_event` - AE frequency\n- `FAERS_count_death_related_by_drug` - Serious outcomes\n- `PubMed_search_articles` - DLT definitions, monitoring strategies\n\n### PATH 6: Regulatory Pathway\n- `OpenFDA_get_approval_history` - Precedent approvals\n- `PubMed_search_articles` - Breakthrough designations, FDA guidance\n- `search_clinical_trials` - Regulatory precedents (accelerated approval)\n\n---\n\n## Quick Start Example\n\n```python\nfrom tooluniverse import ToolUniverse\n\ntu = ToolUniverse(use_cache=True)\ntu.load_tools()\n\n# Example: EGFR+ NSCLC trial feasibility\n# Step 1: Disease prevalence\ndisease_info = tu.tools.OpenTargets_get_disease_id_description_by_name(\n    diseaseName=\"non-small cell lung cancer\"\n)\nprevalence = tu.tools.OpenTargets_get_diseases_phenotypes(\n    efoId=disease_info['data']['id']\n)\n\n# Step 2: Biomarker prevalence\nvariants = tu.tools.ClinVar_search_variants(gene=\"EGFR\", significance=\"pathogenic\")\n\n# Step 3: Precedent trials\ntrials = tu.tools.search_clinical_trials(\n    condition=\"EGFR positive non-small cell lung cancer\",\n    status=\"completed\", phase=\"2\"\n)\n\n# Step 4: Standard of care comparator\nsoc = tu.tools.FDA_OrangeBook_search_drug(ingredient=\"osimertinib\")\n\n# Compile into feasibility report...\n```\n\nSee `WORKFLOW_DETAILS.md` for the complete 6-path Python workflow and use case examples.\n\n---\n\n## Integration with Other Skills\n\n- **tooluniverse-drug-research**: Investigate mechanism, preclinical data\n- **tooluniverse-disease-research**: Deep dive on disease biology\n- **tooluniverse-target-research**: Validate drug target, essentiality\n- **tooluniverse-pharmacovigilance**: Post-market safety for comparator drugs\n- **tooluniverse-precision-oncology**: Biomarker biology, resistance mechanisms\n\n---\n\n## Programmatic Access (Beyond Tools)\n\nWhen ToolUniverse tools return limited trial metadata, use the ClinicalTrials.gov v2 API directly:\n\n```python\nimport requests, pandas as pd\n\n# Search with pagination (all lung cancer immunotherapy trials with results)\nall_studies = []\ntoken = None\nwhile True:\n    params = {\"query.cond\": \"lung cancer\", \"query.intr\": \"immunotherapy\",\n              \"filter.overallStatus\": \"COMPLETED\", \"filter.results\": \"WITH_RESULTS\", \"pageSize\": 100}\n    if token: params[\"pageToken\"] = token\n    resp = requests.get(\"https:\u002F\u002Fclinicaltrials.gov\u002Fapi\u002Fv2\u002Fstudies\", params=params).json()\n    all_studies.extend(resp.get(\"studies\", []))\n    token = resp.get(\"nextPageToken\")\n    if not token: break\n\n# Extract structured data\nrows = []\nfor s in all_studies:\n    proto = s.get(\"protocolSection\", {})\n    rows.append({\n        \"nctId\": proto.get(\"identificationModule\", {}).get(\"nctId\"),\n        \"title\": proto.get(\"identificationModule\", {}).get(\"briefTitle\"),\n        \"enrollment\": proto.get(\"designModule\", {}).get(\"enrollmentInfo\", {}).get(\"count\"),\n        \"phase\": proto.get(\"designModule\", {}).get(\"phases\", [None])[0] if proto.get(\"designModule\", {}).get(\"phases\") else None,\n    })\ndf = pd.DataFrame(rows)\n\n# FDA drug approval history\ndrug = \"pembrolizumab\"\nfda = requests.get(f\"https:\u002F\u002Fapi.fda.gov\u002Fdrug\u002Fdrugsfda.json?search=openfda.brand_name:{drug}&limit=10\").json()\n```\n\nSee `tooluniverse-data-wrangling` skill for pagination, error handling, and bulk download patterns.\n\n---\n\n## Reference Files\n\n| File | Content |\n|------|---------|\n| `REPORT_TEMPLATE.md` | Full 14-section report template with fillable fields |\n| `STUDY_DESIGN_PROCEDURES.md` | Detailed steps for each of the 6 research paths |\n| `WORKFLOW_DETAILS.md` | Complete Python example workflow and 5 use case summaries |\n| `BEST_PRACTICES.md` | Best practices, common pitfalls, output format requirements |\n| `EXAMPLES.md` | Additional examples |\n| `QUICK_START.md` | Quick start guide |\n\n---\n\n## Version Information\n\n- **Version**: 1.0.0\n- **Last Updated**: February 2026\n- **Compatible with**: ToolUniverse 0.5+\n- **Focus**: Phase 1\u002F2 early clinical development\n","# Clinical Trial Design Feasibility Assessment\n\nSystematically assess clinical trial feasibility by analyzing 6 research dimensions. Produces comprehensive feasibility reports with quantitative enrollment projections, endpoint recommendations, and regulatory pathway analysis.\n\n**IMPORTANT**: Always use English terms in tool calls (drug names, disease names, biomarker names), even if the user writes in another language. Only try original-language terms as a fallback if English returns no results. Respond in the user's language.\n\n## Reasoning Before Searching\n\nTrial design starts with the question, not the methods. Answer these four questions before running any tools — they determine everything else:\n\n1. **What is the primary endpoint?** Is it overall survival (gold standard but slow), PFS (faster but surrogate), ORR (single-arm friendly but not always accepted), or a biomarker (needs validation as surrogate first)? The endpoint determines FDA pathway, statistical design, and duration.\n2. **Who is the population?** Broad unselected vs. biomarker-enriched. Enriched populations have higher response rates, allowing smaller trials — but require a validated companion diagnostic and reduce the eligible patient pool.\n3. **What is the comparator?** Placebo (only if no standard of care exists), active control (requires non-inferiority or superiority framing), or single-arm with historical control (acceptable for rare diseases or breakthrough designations, but FDA scrutiny is high).\n4. **Is the effect size realistic given the mechanism?** A 20% improvement in ORR over SOC requires ~100 patients per arm. A 50% improvement requires ~30. If the mechanism only justifies a 10% improvement, the trial may be underpowered regardless of design. Check precedent effect sizes in similar trials before committing to an endpoint.\n\nThese four answers determine sample size, duration, and trial design. Look them up from precedent trials and FDA guidance — do not derive them from first principles.\n\n**LOOK UP DON'T GUESS**: Never assume what the standard of care is for an indication — look it up with DrugBank and FDA tools. Never assume an endpoint is FDA-accepted — verify with `search_clinical_trials` precedents and `OpenFDA_get_approval_history`. Never estimate prevalence from memory — use OpenTargets, gnomAD, or COSMIC.\n\n## Core Principles\n\n### 1. Report-First Approach (MANDATORY)\n**DO NOT** show tool outputs to user. Instead:\n1. Create `[INDICATION]_trial_feasibility_report.md` FIRST\n2. Initialize with all section headers\n3. Progressively update as data arrives\n4. Present only the final report\n\n### 2. Evidence Grading System\n\n| Grade | Symbol | Criteria | Examples |\n|-------|--------|----------|----------|\n| **A** | 3-star | Regulatory acceptance, multiple precedents | FDA-approved endpoint in same indication |\n| **B** | 2-star | Clinical validation, single precedent | Phase 3 trial in related indication |\n| **C** | 1-star | Preclinical or exploratory | Phase 1 use, biomarker validation ongoing |\n| **D** | 0-star | Proposed, no validation | Novel endpoint, no precedent |\n\n### 3. Feasibility Score (0-100)\nWeighted composite score:\n- **Patient Availability** (30%): Population size x biomarker prevalence x geography\n- **Endpoint Precedent** (25%): Historical use, regulatory acceptance\n- **Regulatory Clarity** (20%): Pathway defined, precedents exist\n- **Comparator Feasibility** (15%): Standard of care availability\n- **Safety Monitoring** (10%): Known risks, monitoring established\n\n**Interpretation**: >=75 HIGH (proceed), 50-74 MODERATE (additional validation), \u003C50 LOW (de-risking required)\n\n---\n\n## When to Use This Skill\n\nApply when users:\n- Plan early-phase trials (Phase 1\u002F2 emphasis)\n- Need enrollment feasibility assessment\n- Design biomarker-selected trials\n- Evaluate endpoint strategies\n- Assess regulatory pathways\n- Compare trial design options\n- Need safety monitoring plans\n\n**Trigger phrases**: \"clinical trial design\", \"trial feasibility\", \"enrollment projections\", \"endpoint selection\", \"trial planning\", \"Phase 1\u002F2 design\", \"basket trial\", \"biomarker trial\"\n\n---\n\n## Core Strategy: 6 Research Paths\n\nExecute 6 parallel research dimensions. See `STUDY_DESIGN_PROCEDURES.md` for detailed steps per path.\n\n```\nTrial Design Query\n|\n+-- PATH 1: Patient Population Sizing\n|   Disease prevalence, biomarker prevalence, geographic distribution,\n|   eligibility criteria impact, enrollment projections\n|\n+-- PATH 2: Biomarker Prevalence & Testing\n|   Mutation frequency, testing availability, turnaround time,\n|   cost\u002Freimbursement, alternative biomarkers\n|\n+-- PATH 3: Comparator Selection\n|   Standard of care, approved comparators, historical controls,\n|   placebo appropriateness, combination therapy\n|\n+-- PATH 4: Endpoint Selection\n|   Primary endpoint precedents, FDA acceptance history,\n|   measurement feasibility, surrogate vs clinical endpoints\n|\n+-- PATH 5: Safety Endpoints & Monitoring\n|   Mechanism-based toxicity, class effects, organ-specific monitoring,\n|   DLT history, safety monitoring plan\n|\n+-- PATH 6: Regulatory Pathway\n    Regulatory precedents (505(b)(1), 505(b)(2)), breakthrough therapy,\n    orphan drug, fast track, FDA guidance\n```\n\n---\n\n## Report Structure (14 Sections)\n\nCreate `[INDICATION]_trial_feasibility_report.md` with all 14 sections. See `REPORT_TEMPLATE.md` for full templates with fillable fields.\n\n1. **Executive Summary** - Feasibility score, key findings, go\u002Fno-go recommendation\n2. **Disease Background** - Prevalence, incidence, SOC, unmet need\n3. **Patient Population Analysis** - Base population, biomarker selection, eligibility funnel, enrollment projections\n4. **Biomarker Strategy** - Primary biomarker, alternatives, testing logistics\n5. **Endpoint Selection & Justification** - Primary\u002Fsecondary\u002Fexploratory endpoints, statistical considerations\n6. **Comparator Analysis** - SOC, trial design options (single-arm vs randomized vs non-inferiority), drug sourcing\n7. **Safety Endpoints & Monitoring Plan** - DLT definition, mechanism-based toxicities, organ monitoring, SMC\n8. **Study Design Recommendations** - Phase, design type, schema, eligibility, treatment plan, assessment schedule\n9. **Enrollment & Site Strategy** - Site selection, enrollment projections, recruitment strategies\n10. **Regulatory Pathway** - FDA pathway, precedents, pre-IND meeting, IND timeline\n11. **Budget & Resource Considerations** - Cost drivers, timeline, FTE requirements\n12. **Risk Assessment** - Feasibility risks, scientific risks, mitigation strategies\n13. **Success Criteria & Go\u002FNo-Go Decision** - Phase 1\u002F2 criteria, interim analysis, feasibility scorecard\n14. **Recommendations & Next Steps** - Final recommendation, critical path to IND, alternative designs\n\n---\n\n## Tool Reference by Research Path\n\n### PATH 1: Patient Population Sizing\n- `OpenTargets_get_disease_id_description_by_name` - Disease lookup\n- `OpenTargets_get_diseases_phenotypes_by_target_ensembl` - Prevalence data\n- `ClinVar_search_variants` - Biomarker mutation frequency\n- `gnomad_search_variants` - Population allele frequencies\n- `PubMed_search_articles` - Epidemiology literature\n- `search_clinical_trials` - Enrollment feasibility from past trials\n\n### PATH 2: Biomarker Prevalence & Testing\n- `ClinVar_get_variant_details` - Variant pathogenicity\n- `COSMIC_search_mutations` - Cancer-specific mutation frequencies\n- `gnomad_get_variant` - Population genetics\n- `PubMed_search_articles` - CDx test performance, guidelines\n\n### PATH 3: Comparator Selection\n- `drugbank_get_drug_basic_info_by_drug_name_or_id` - Drug info\n- `drugbank_get_indications_by_drug_name_or_drugbank_id` - Approved indications\n- `drugbank_get_pharmacology_by_drug_name_or_drugbank_id` - Mechanism\n- `FDA_OrangeBook_search_drug` - Generic availability\n- `OpenFDA_get_approval_history` - Approval details\n- `search_clinical_trials` - Historical control data\n\n### PATH 4: Endpoint Selection\n- `search_clinical_trials` - Precedent trials, endpoints used\n- `PubMed_search_articles` - FDA acceptance history, endpoint validation\n- `OpenFDA_get_approval_history` - Approved endpoints by indication\n\n### PATH 5: Safety Endpoints & Monitoring\n- `drugbank_get_pharmacology_by_drug_name_or_drugbank_id` - Mechanism toxicity\n- `FDA_get_warnings_and_cautions_by_drug_name` - FDA black box warnings\n- `FAERS_search_reports_by_drug_and_reaction` - Real-world adverse events\n- `FAERS_count_reactions_by_drug_event` - AE frequency\n- `FAERS_count_death_related_by_drug` - Serious outcomes\n- `PubMed_search_articles` - DLT definitions, monitoring strategies\n\n### PATH 6: Regulatory Pathway\n- `OpenFDA_get_approval_history` - Precedent approvals\n- `PubMed_search_articles` - Breakthrough designations, FDA guidance\n- `search_clinical_trials` - Regulatory precedents (accelerated approval)\n\n---\n\n## Quick Start Example\n\n```python\nfrom tooluniverse import ToolUniverse\n\ntu = ToolUniverse(use_cache=True)\ntu.load_tools()\n\n# Example: EGFR+ NSCLC trial feasibility\n# Step 1: Disease prevalence\ndisease_info = tu.tools.OpenTargets_get_disease_id_description_by_name(\n    diseaseName=\"non-small cell lung cancer\"\n)\nprevalence = tu.tools.OpenTargets_get_diseases_phenotypes(\n    efoId=disease_info['data']['id']\n)\n\n# Step 2: Biomarker prevalence\nvariants = tu.tools.ClinVar_search_variants(gene=\"EGFR\", significance=\"pathogenic\")\n\n# Step 3: Precedent trials\ntrials = tu.tools.search_clinical_trials(\n    condition=\"EGFR positive non-small cell lung cancer\",\n    status=\"completed\", phase=\"2\"\n)\n\n# Step 4: Standard of care comparator\nsoc = tu.tools.FDA_OrangeBook_search_drug(ingredient=\"osimertinib\")\n\n# Compile into feasibility report...\n```\n\nSee `WORKFLOW_DETAILS.md` for the complete 6-path Python workflow and use case examples.\n\n---\n\n## Integration with Other Skills\n\n- **tooluniverse-drug-research**: Investigate mechanism, preclinical data\n- **tooluniverse-disease-research**: Deep dive on disease biology\n- **tooluniverse-target-research**: Validate drug target, essentiality\n- **tooluniverse-pharmacovigilance**: Post-market safety for comparator drugs\n- **tooluniverse-precision-oncology**: Biomarker biology, resistance mechanisms\n\n---\n\n## Programmatic Access (Beyond Tools)\n\nWhen ToolUniverse tools return limited trial metadata, use the ClinicalTrials.gov v2 API directly:\n\n```python\nimport requests, pandas as pd\n\n# Search with pagination (all lung cancer immunotherapy trials with results)\nall_studies = []\ntoken = None\nwhile True:\n    params = {\"query.cond\": \"lung cancer\", \"query.intr\": \"immunotherapy\",\n              \"filter.overallStatus\": \"COMPLETED\", \"filter.results\": \"WITH_RESULTS\", \"pageSize\": 100}\n    if token: params[\"pageToken\"] = token\n    resp = requests.get(\"https:\u002F\u002Fclinicaltrials.gov\u002Fapi\u002Fv2\u002Fstudies\", params=params).json()\n    all_studies.extend(resp.get(\"studies\", []))\n    token = resp.get(\"nextPageToken\")\n    if not token: break\n\n# Extract structured data\nrows = []\nfor s in all_studies:\n    proto = s.get(\"protocolSection\", {})\n    rows.append({\n        \"nctId\": proto.get(\"identificationModule\", {}).get(\"nctId\"),\n        \"title\": proto.get(\"identificationModule\", {}).get(\"briefTitle\"),\n        \"enrollment\": proto.get(\"designModule\", {}).get(\"enrollmentInfo\", {}).get(\"count\"),\n        \"phase\": proto.get(\"designModule\", {}).get(\"phases\", [None])[0] if proto.get(\"designModule\", {}).get(\"phases\") else None,\n    })\ndf = pd.DataFrame(rows)\n\n# FDA drug approval history\ndrug = \"pembrolizumab\"\nfda = requests.get(f\"https:\u002F\u002Fapi.fda.gov\u002Fdrug\u002Fdrugsfda.json?search=openfda.brand_name:{drug}&limit=10\").json()\n```\n\nSee `tooluniverse-data-wrangling` skill for pagination, error handling, and bulk download patterns.\n\n---\n\n## Reference Files\n\n| File | Content |\n|------|---------|\n| `REPORT_TEMPLATE.md` | Full 14-section report template with fillable fields |\n| `STUDY_DESIGN_PROCEDURES.md` | Detailed steps for each of the 6 research paths |\n| `WORKFLOW_DETAILS.md` | Complete Python example workflow and 5 use case summaries |\n| `BEST_PRACTICES.md` | Best practices, common pitfalls, output format requirements |\n| `EXAMPLES.md` | Additional examples |\n| `QUICK_START.md` | Quick start guide |\n\n---\n\n## Version Information\n\n- **Version**: 1.0.0\n- **Last Updated**: February 2026\n- **Compatible with**: ToolUniverse 0.5+\n- **Focus**: Phase 1\u002F2 early clinical development\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Flibrary\u002Fskills\u002Ftooluniverse-clinical-trial-design","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":60,"prompt":70,"zipAvailable":71},[61,64,67],{"tool":62,"command":63},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-clinical-trial-design",{"tool":65,"command":66},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-clinical-trial-design",{"tool":68,"command":69},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-clinical-trial-design","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-clinical-trial-design\u002FSKILL.md",true,[73,79,83,89,93,97,101,104],{"path":74,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":77,"sourceHtmlUrl":78},"BEST_PRACTICES.md","REFERENCE","参考文档",4866,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-clinical-trial-design\u002FBEST_PRACTICES.md",{"path":80,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":81,"sourceHtmlUrl":82},"EXAMPLES.md",58438,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-clinical-trial-design\u002FEXAMPLES.md",{"path":84,"resourceType":85,"resourceTypeDesc":86,"sizeBytes":87,"sourceHtmlUrl":88},"python_implementation.py","SCRIPT","脚本",14716,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-clinical-trial-design\u002Fpython_implementation.py",{"path":90,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":91,"sourceHtmlUrl":92},"QUICK_START.md",7714,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-clinical-trial-design\u002FQUICK_START.md",{"path":94,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":95,"sourceHtmlUrl":96},"REPORT_TEMPLATE.md",17798,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-clinical-trial-design\u002FREPORT_TEMPLATE.md",{"path":98,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":99,"sourceHtmlUrl":100},"STUDY_DESIGN_PROCEDURES.md",5572,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-clinical-trial-design\u002FSTUDY_DESIGN_PROCEDURES.md",{"path":102,"resourceType":85,"resourceTypeDesc":86,"sizeBytes":87,"sourceHtmlUrl":103},"trial_pipeline.py","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-clinical-trial-design\u002Ftrial_pipeline.py",{"path":105,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":106,"sourceHtmlUrl":107},"WORKFLOW_DETAILS.md",9617,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-clinical-trial-design\u002FWORKFLOW_DETAILS.md",[109,130,159,186,200,216],{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":48},"01M6DF7D7478R55P46REYH4QAC","clarify-requirements","Resolve genuine pre-execution ambiguity by scanning repo context, generating 1-6 grounded options, and asking 1-3 focused questions via AskUserQuestion. NOT for mid-task use (injection risk); NOT when the goal is already unambiguous; use to disambiguate vague prompts before any file edits.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fworkspace-hooks\u002Fskills\u002Fclarify-requirements\u002FSKILL.md",[],[116,117,118,119,120,121,122,123,124,40,125,126,127,128,129],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","context","repo","injection","execution","file",{"skillNo":131,"name":132,"nameZh":6,"description":133,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":134,"categories":135,"keywords":139,"publishedAt":48},"01M6DF79CA4BHJS66J8EZDBPWJ","openmm-md","Run FREE, open-source, Windows-native GPU molecular dynamics via the openmm-md MCP (OpenMM + CUDA on the local NVIDIA GPU). Use for protein \u002F protein-ligand MD when you want a free stack or are on Windows without a Schrodinger license. Covers the full workflow (prepare, solvate, minimize, equilibrate, production, analyze, mmgbsa) AND an honest decision guide vs Schrodinger Desmond, including how to run Desmond legitimately on Linux or a cloud GPU with a real license. This is a deliberately LESSER free alternative and does NOT replace the schrodinger MCP tools. Do NOT use it to pick a free tool when a validated FEP+, WaterMap, IFD-MD, or Prime MM-GBSA result is actually required.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fmcp\u002Fopenmm-md-mcp\u002Fskill\u002Fopenmm-md\u002FSKILL.md",[136],{"categoryNo":137,"categoryName":138,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[140,141,142,143,144,145,146,147,148,149,150,151,152,153,40,154,155,156,157,158],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":160,"name":161,"nameZh":6,"description":162,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":163,"categories":164,"keywords":171,"publishedAt":48},"01M6DF76C1MG85VEWP8VZCBNMN","visual-review","Take screenshots of web pages and UI using Playwright for visual review and iteration","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fvisual-review\u002FSKILL.md",[165,168],{"categoryNo":166,"categoryName":167,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":169,"categoryName":170,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[172,173,174,175,176,177,178,179,180,181,141,182,183,184,185],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":187,"name":188,"nameZh":6,"description":189,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":190,"categories":191,"keywords":192,"publishedAt":48},"01M6DF73AQVCBZKEN0YXEX9FXP","status","Diagnostic status report — shows metaswarm installation state, project setup, and potential issues","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstatus\u002FSKILL.md",[],[188,193,194,195,196,197,198,199],"setup","report","project","installation","project setup","issues","state",{"skillNo":201,"name":202,"nameZh":6,"description":203,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":204,"categories":205,"keywords":207,"publishedAt":48},"01M6DF6X6C2XB0P6GX76P7TTYV","start","Use when starting work on any task, when the user mentions metaswarm, or when the user wants to begin tracked development work","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstart\u002FSKILL.md",[206],{"categoryNo":137,"categoryName":138,"taxonomyType":21,"taxonomyTypeDesc":22},[202,208,121,209,210,211,40,212,213,214,215],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":217,"name":193,"nameZh":6,"description":218,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":219,"categories":220,"keywords":221,"publishedAt":48},"01M6DF6QMJ9AJKFKHHKRT005PQ","Interactive project setup — detects your project, configures metaswarm, writes project-local files","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fsetup\u002FSKILL.md",[],[193,195,156,222,197,223],"files","interactive"]