[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DANNWHG05XRMG1YK1NSBZC":3,"skill-same:01M6DANNWHG05XRMG1YK1NSBZC":98},{"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":37,"linkOnly":38,"markdownContent":39,"markdownBody":40,"frontMatter":41,"refName":42,"commitSha":43,"skillDirectory":44,"forksCount":14,"repositoryHtmlUrl":45,"repositoryHomepageUrl":6,"ownerHtmlUrl":46,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":47,"install":48,"resources":61},"01M6DANNWHG05XRMG1YK1NSBZC","tooluniverse-clinical-trial-matching",null,"AI-driven patient-to-trial matching for precision medicine and oncology. Given a patient profile (disease, molecular alterations, stage, prior treatments), discovers and ranks clinical trials from ClinicalTrials.gov using multi-dimensional matching across molecular eligibility, clinical criteria, drug-biomarker alignment, evidence strength, and geographic feasibility. Produces a quantitative Trial Match Score (0-100) per trial with tiered recommendations and a comprehensive markdown report. Use when oncologists, molecular tumor boards, or patients ask about clinical trial options for specific cancer types, biomarker profiles, or post-progression scenarios.","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-matching\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36],"tooluniverse clinical trial matching","clinical","matching","across","driven","patient","recommendations","molecular","stage","feasibility","options","alignment","evidence","use","profile","ask","markdown","report","2026-11-10 10:12:30",false,"---\nname: tooluniverse-clinical-trial-matching\ndescription: AI-driven patient-to-trial matching for precision medicine and oncology. Given a patient profile (disease, molecular alterations, stage, prior treatments), discovers and ranks clinical trials from ClinicalTrials.gov using multi-dimensional matching across molecular eligibility, clinical criteria, drug-biomarker alignment, evidence strength, and geographic feasibility. Produces a quantitative Trial Match Score (0-100) per trial with tiered recommendations and a comprehensive markdown report. Use when oncologists, molecular tumor boards, or patients ask about clinical trial options for specific cancer types, biomarker profiles, or post-progression scenarios.\n---\n\n# Clinical Trial Matching for Precision Medicine\n\nTransform patient molecular profiles and clinical characteristics into prioritized clinical trial recommendations. Searches ClinicalTrials.gov and cross-references with molecular databases (CIViC, OpenTargets, ChEMBL, FDA) to produce evidence-graded, scored trial matches.\n\n**KEY PRINCIPLES**:\n1. **Report-first approach** - Create report file FIRST, then populate progressively\n2. **Patient-centric** - Every recommendation considers the individual patient's profile\n3. **Molecular-first matching** - Prioritize trials targeting patient's specific biomarkers\n\n## Molecular Matching Priority\n\nMatch patients to trials by molecular profile FIRST (specific mutations), then by disease stage, then by prior treatments. A patient with EGFR L858R should match to EGFR-targeted trials regardless of other factors.\n4. **Evidence-graded** - Every recommendation has an evidence tier (T1-T4)\n5. **Quantitative scoring** - Trial Match Score (0-100) for every trial\n6. **Eligibility-aware** - Parse and evaluate inclusion\u002Fexclusion criteria\n7. **Actionable output** - Clear next steps, contact info, enrollment status\n8. **Source-referenced** - Every statement cites the tool\u002Fdatabase source\n9. **Completeness checklist** - Mandatory section showing analysis coverage\n10. **English-first queries** - Always use English terms in tool calls. Respond in user's language\n\n## LOOK UP, DON'T GUESS\nWhen uncertain about any scientific fact, SEARCH databases first rather than reasoning from memory. A database-verified answer is always more reliable than a guess.\n\n---\n\n## COMPUTE, DON'T DESCRIBE\nWhen analysis requires computation (statistics, data processing, scoring, enrichment), write and run Python code via Bash. Don't describe what you would do — execute it and report actual results. Use ToolUniverse tools to retrieve data, then Python (pandas, scipy, statsmodels, matplotlib) to analyze it.\n\n## When to Use\n\nApply when user asks:\n- \"What clinical trials are available for my NSCLC with EGFR L858R?\"\n- \"Patient has BRAF V600E melanoma, failed ipilimumab - what trials?\"\n- \"Find basket trials for NTRK fusion\"\n- \"Breast cancer with HER2 amplification, post-CDK4\u002F6 inhibitor trials\"\n- \"KRAS G12C colorectal cancer clinical trials\"\n- \"Immunotherapy trials for TMB-high solid tumors\"\n- \"Clinical trials near Boston for lung cancer\"\n- \"What are my options after failing osimertinib for EGFR+ NSCLC?\"\n\n**NOT for** (use other skills instead):\n- Single variant interpretation without trial focus -> Use `tooluniverse-cancer-variant-interpretation`\n- Drug safety profiling -> Use `tooluniverse-adverse-event-detection`\n- Target validation -> Use `tooluniverse-drug-target-validation`\n- General disease research -> Use `tooluniverse-disease-research`\n\n---\n\n## Input Parsing\n\n### Required Input\n- **Disease\u002Fcancer type**: Free-text disease name (e.g., \"non-small cell lung cancer\", \"melanoma\")\n\n### Strongly Recommended\n- **Molecular alterations**: One or more biomarkers (e.g., \"EGFR L858R\", \"KRAS G12C\", \"PD-L1 50%\", \"TMB-high\")\n- **Stage\u002Fgrade**: Disease stage (e.g., \"Stage IV\", \"metastatic\", \"locally advanced\")\n- **Prior treatments**: Previous therapies and outcomes (e.g., \"failed platinum chemotherapy\", \"progressed on osimertinib\")\n\n### Optional\n- **Performance status**: ECOG or Karnofsky score\n- **Geographic location**: City\u002Fstate for proximity filtering\n- **Trial phase preference**: I, II, III, IV, or \"any\"\n- **Intervention type**: drug, biological, device, etc.\n- **Recruiting status preference**: recruiting, not yet recruiting, active\n\nFor biomarker parsing rules and gene symbol normalization, see [MATCHING_ALGORITHMS.md](.\u002FMATCHING_ALGORITHMS.md).\n\n---\n\n## Workflow Overview\n\n```\nInput: Patient profile (disease + biomarkers + stage + prior treatments)\n\nPhase 1: Patient Profile Standardization\n  - Resolve disease to EFO\u002Fontology IDs (OpenTargets, OLS)\n  - Parse molecular alterations to gene + variant\n  - Resolve gene symbols to Ensembl\u002FEntrez IDs (MyGene)\n  - Classify biomarker actionability (FDA-approved vs investigational)\n\nPhase 2: Broad Trial Discovery\n  - Disease-based trial search (ClinicalTrials.gov)\n  - Biomarker-specific trial search\n  - Intervention-based search (for known drugs targeting patient's biomarkers)\n  - Deduplicate and collect NCT IDs\n\nPhase 3: Trial Characterization (batch, groups of 10)\n  - Eligibility criteria, conditions\u002Finterventions, locations, status, descriptions\n\nPhase 4: Molecular Eligibility Matching\n  - Parse eligibility text for biomarker requirements\n  - Match patient's molecular profile to trial requirements\n  - Score molecular eligibility (0-40 points)\n\nPhase 5: Drug-Biomarker Alignment\n  - Identify trial intervention drugs and mechanisms (OpenTargets, ChEMBL)\n  - FDA approval status for biomarker-drug combinations\n  - Classify drugs (targeted therapy, immunotherapy, chemotherapy)\n\nPhase 6: Evidence Assessment\n  - FDA-approved biomarker-drug combinations\n  - Clinical trial results (PubMed), CIViC evidence, PharmGKB\n  - Evidence tier classification (T1-T4)\n\nPhase 7: Geographic & Feasibility Analysis\n  - Trial site locations, enrollment status, proximity scoring\n\nPhase 8: Alternative Options\n  - Basket trials, expanded access, related studies\n\nPhase 9: Scoring & Ranking (0-100 composite score)\n  - Tier classification: Optimal (80-100) \u002F Good (60-79) \u002F Possible (40-59) \u002F Exploratory (0-39)\n\nPhase 10: Report Synthesis\n  - Executive summary, ranked trial list, evidence grading, completeness checklist\n```\n\n---\n\n## Critical Tool Parameters\n\n### Clinical Trial Search Tools\n\n| Tool | Key Parameters | Notes |\n|------|---------------|-------|\n| `search_clinical_trials` | `query_term` (REQ), `condition`, `intervention`, `pageSize` | Main search |\n| `search_clinical_trials` | `action=\"search_studies\"` (REQ), `condition`, `intervention`, `limit` | Alternative search |\n| `get_clinical_trial_descriptions` | `action=\"get_study_details\"` (REQ), `nct_id` (REQ) | Full trial details |\n\n### Batch Trial Detail Tools (all take `nct_ids` array)\n\n| Tool | Second Required Param | Returns |\n|------|----------------------|---------|\n| `get_clinical_trial_eligibility_criteria` | `eligibility_criteria=\"all\"` | Eligibility text |\n| `get_clinical_trial_locations` | `location=\"all\"` | Site locations |\n| `get_clinical_trial_conditions_and_interventions` | `condition_and_intervention=\"all\"` | Arms\u002Finterventions |\n| `get_clinical_trial_status_and_dates` | `status_and_date=\"all\"` | Status\u002Fdates |\n| `get_clinical_trial_descriptions` | `description_type=\"brief\"` or `\"full\"` | Titles\u002Fsummaries |\n| `get_clinical_trial_outcome_measures` | `outcome_measures=\"all\"` | Outcomes |\n\n### Gene\u002FDisease Resolution\n\n| Tool | Key Parameters |\n|------|---------------|\n| `MyGene_query_genes` | `query`, `species` |\n| `OpenTargets_get_disease_id_description_by_name` | `diseaseName` |\n| `OpenTargets_get_target_id_description_by_name` | `targetName` |\n| `ols_search_efo_terms` | `query`, `limit` |\n\n### Drug Information\n\n| Tool | Key Parameters | Notes |\n|------|---------------|-------|\n| `OpenTargets_get_drug_id_description_by_name` | `drugName` | Resolve drug to ChEMBL ID |\n| `OpenTargets_get_drug_mechanisms_of_action_by_chemblId` | `chemblId` | Drug MoA and targets |\n| `OpenTargets_get_associated_drugs_by_target_ensemblID` | `ensemblId`, `size` | Drugs for a target |\n| `drugbank_get_targets_by_drug_name_or_drugbank_id` | `query`, `case_sensitive`, `exact_match`, `limit` (ALL REQ) | Drug targets |\n| `fda_pharmacogenomic_biomarkers` | (none) | FDA biomarker-drug list |\n| `FDA_get_indications_by_drug_name` | `drug_name`, `limit` | FDA indications |\n\n### Evidence Tools\n\n| Tool | Key Parameters |\n|------|---------------|\n| `PubMed_search_articles` | `query`, `max_results` |\n| `civic_get_variants_by_gene` | `gene_id` (CIViC int ID), `limit` |\n| `PharmGKB_search_genes` | `query` |\n\n### Known CIViC Gene IDs\n\nEGFR=19, BRAF=5, ALK=1, ABL1=4, KRAS=30, TP53=45, ERBB2=20, NTRK1=197, NTRK2=560, NTRK3=561, PIK3CA=37, MET=52, ROS1=118, RET=122, BRCA1=2370, BRCA2=2371\n\n### Critical Parameter Notes\n\n1. **DrugBank tools**: ALL 4 parameters (`query`, `case_sensitive`, `exact_match`, `limit`) are REQUIRED\n2. **`search_clinical_trials`**: `query_term` is REQUIRED even for disease-only searches\n3. **`search_clinical_trials`**: `action` must be exactly `\"search_studies\"`\n4. **CIViC `civic_search_variants`**: Does NOT filter by query - returns alphabetically\n5. **CIViC `civic_get_variants_by_gene`**: Takes CIViC gene ID (integer), NOT gene symbol\n6. **Batch clinical trial tools**: Accept arrays of NCT IDs, process in batches of 10\n\n---\n\n## Scoring Summary\n\n**Trial Match Score (0-100)**:\n- Molecular Match: 0-40 pts (exact variant=40, gene-level=30, pathway=20, none=10, excluded=0)\n- Clinical Eligibility: 0-25 pts (all met=25, most=18, some=10, ineligible=0)\n- Evidence Strength: 0-20 pts (FDA-approved=20, Phase III=15, Phase II=10, Phase I=5)\n- Trial Phase: 0-10 pts (III=10, II=8, I\u002FII=6, I=4)\n- Geographic: 0-5 pts (local=5, same country=3, international=1)\n\n**Recommendation Tiers**: Optimal (80-100), Good (60-79), Possible (40-59), Exploratory (0-39)\n\n**Evidence Tiers**: T1 (FDA\u002Fguideline), T2 (Phase III), T3 (Phase I\u002FII), T4 (computational)\n\nFor detailed scoring logic, see [SCORING_CRITERIA.md](.\u002FSCORING_CRITERIA.md).\n\n---\n\n## Parallelization Strategy\n\n**Group 1** (Phase 1 - simultaneous):\n- `MyGene_query_genes` per gene, `OpenTargets` disease search, `ols_search_efo_terms`, `fda_pharmacogenomic_biomarkers`\n\n**Group 2** (Phase 2 - simultaneous):\n- `search_clinical_trials` by disease, biomarker, and intervention; `search_clinical_trials` alternative\n\n**Group 3** (Phase 3 - simultaneous):\n- All batch detail tools (eligibility, interventions, locations, status, descriptions)\n\n**Group 4** (Phases 5-6 - per drug):\n- Drug resolution, MoA, FDA indications, PubMed evidence\n\n---\n\n## Error Handling\n\n1. Wrap every tool call in try\u002Fexcept\n2. Check for empty results and string error responses\n3. Use fallback tools when primary fails (e.g., OLS if OpenTargets fails)\n4. Document failures in completeness checklist\n5. Never let one failure block the entire analysis\n\n---\n\n## Reference Files\n\n| File | Contents |\n|------|----------|\n| [TOOLS_REFERENCE.md](.\u002FTOOLS_REFERENCE.md) | Full tool inventory with parameters and response structures |\n| [MATCHING_ALGORITHMS.md](.\u002FMATCHING_ALGORITHMS.md) | Patient profile standardization, biomarker parsing, molecular eligibility matching, drug-biomarker alignment code |\n| [SCORING_CRITERIA.md](.\u002FSCORING_CRITERIA.md) | Detailed scoring tables, molecular match logic, drug-biomarker alignment scoring |\n| [REPORT_TEMPLATE.md](.\u002FREPORT_TEMPLATE.md) | Full markdown report template with all sections |\n| [TRIAL_SEARCH_PATTERNS.md](.\u002FTRIAL_SEARCH_PATTERNS.md) | Search functions, batch retrieval, parallelization, common use patterns, edge cases |\n| [EXAMPLES.md](.\u002FEXAMPLES.md) | Worked examples for different matching scenarios |\n| [QUICK_START.md](.\u002FQUICK_START.md) | Quick-start guide for common workflows |\n","# Clinical Trial Matching for Precision Medicine\n\nTransform patient molecular profiles and clinical characteristics into prioritized clinical trial recommendations. Searches ClinicalTrials.gov and cross-references with molecular databases (CIViC, OpenTargets, ChEMBL, FDA) to produce evidence-graded, scored trial matches.\n\n**KEY PRINCIPLES**:\n1. **Report-first approach** - Create report file FIRST, then populate progressively\n2. **Patient-centric** - Every recommendation considers the individual patient's profile\n3. **Molecular-first matching** - Prioritize trials targeting patient's specific biomarkers\n\n## Molecular Matching Priority\n\nMatch patients to trials by molecular profile FIRST (specific mutations), then by disease stage, then by prior treatments. A patient with EGFR L858R should match to EGFR-targeted trials regardless of other factors.\n4. **Evidence-graded** - Every recommendation has an evidence tier (T1-T4)\n5. **Quantitative scoring** - Trial Match Score (0-100) for every trial\n6. **Eligibility-aware** - Parse and evaluate inclusion\u002Fexclusion criteria\n7. **Actionable output** - Clear next steps, contact info, enrollment status\n8. **Source-referenced** - Every statement cites the tool\u002Fdatabase source\n9. **Completeness checklist** - Mandatory section showing analysis coverage\n10. **English-first queries** - Always use English terms in tool calls. Respond in user's language\n\n## LOOK UP, DON'T GUESS\nWhen uncertain about any scientific fact, SEARCH databases first rather than reasoning from memory. A database-verified answer is always more reliable than a guess.\n\n---\n\n## COMPUTE, DON'T DESCRIBE\nWhen analysis requires computation (statistics, data processing, scoring, enrichment), write and run Python code via Bash. Don't describe what you would do — execute it and report actual results. Use ToolUniverse tools to retrieve data, then Python (pandas, scipy, statsmodels, matplotlib) to analyze it.\n\n## When to Use\n\nApply when user asks:\n- \"What clinical trials are available for my NSCLC with EGFR L858R?\"\n- \"Patient has BRAF V600E melanoma, failed ipilimumab - what trials?\"\n- \"Find basket trials for NTRK fusion\"\n- \"Breast cancer with HER2 amplification, post-CDK4\u002F6 inhibitor trials\"\n- \"KRAS G12C colorectal cancer clinical trials\"\n- \"Immunotherapy trials for TMB-high solid tumors\"\n- \"Clinical trials near Boston for lung cancer\"\n- \"What are my options after failing osimertinib for EGFR+ NSCLC?\"\n\n**NOT for** (use other skills instead):\n- Single variant interpretation without trial focus -> Use `tooluniverse-cancer-variant-interpretation`\n- Drug safety profiling -> Use `tooluniverse-adverse-event-detection`\n- Target validation -> Use `tooluniverse-drug-target-validation`\n- General disease research -> Use `tooluniverse-disease-research`\n\n---\n\n## Input Parsing\n\n### Required Input\n- **Disease\u002Fcancer type**: Free-text disease name (e.g., \"non-small cell lung cancer\", \"melanoma\")\n\n### Strongly Recommended\n- **Molecular alterations**: One or more biomarkers (e.g., \"EGFR L858R\", \"KRAS G12C\", \"PD-L1 50%\", \"TMB-high\")\n- **Stage\u002Fgrade**: Disease stage (e.g., \"Stage IV\", \"metastatic\", \"locally advanced\")\n- **Prior treatments**: Previous therapies and outcomes (e.g., \"failed platinum chemotherapy\", \"progressed on osimertinib\")\n\n### Optional\n- **Performance status**: ECOG or Karnofsky score\n- **Geographic location**: City\u002Fstate for proximity filtering\n- **Trial phase preference**: I, II, III, IV, or \"any\"\n- **Intervention type**: drug, biological, device, etc.\n- **Recruiting status preference**: recruiting, not yet recruiting, active\n\nFor biomarker parsing rules and gene symbol normalization, see [MATCHING_ALGORITHMS.md](.\u002FMATCHING_ALGORITHMS.md).\n\n---\n\n## Workflow Overview\n\n```\nInput: Patient profile (disease + biomarkers + stage + prior treatments)\n\nPhase 1: Patient Profile Standardization\n  - Resolve disease to EFO\u002Fontology IDs (OpenTargets, OLS)\n  - Parse molecular alterations to gene + variant\n  - Resolve gene symbols to Ensembl\u002FEntrez IDs (MyGene)\n  - Classify biomarker actionability (FDA-approved vs investigational)\n\nPhase 2: Broad Trial Discovery\n  - Disease-based trial search (ClinicalTrials.gov)\n  - Biomarker-specific trial search\n  - Intervention-based search (for known drugs targeting patient's biomarkers)\n  - Deduplicate and collect NCT IDs\n\nPhase 3: Trial Characterization (batch, groups of 10)\n  - Eligibility criteria, conditions\u002Finterventions, locations, status, descriptions\n\nPhase 4: Molecular Eligibility Matching\n  - Parse eligibility text for biomarker requirements\n  - Match patient's molecular profile to trial requirements\n  - Score molecular eligibility (0-40 points)\n\nPhase 5: Drug-Biomarker Alignment\n  - Identify trial intervention drugs and mechanisms (OpenTargets, ChEMBL)\n  - FDA approval status for biomarker-drug combinations\n  - Classify drugs (targeted therapy, immunotherapy, chemotherapy)\n\nPhase 6: Evidence Assessment\n  - FDA-approved biomarker-drug combinations\n  - Clinical trial results (PubMed), CIViC evidence, PharmGKB\n  - Evidence tier classification (T1-T4)\n\nPhase 7: Geographic & Feasibility Analysis\n  - Trial site locations, enrollment status, proximity scoring\n\nPhase 8: Alternative Options\n  - Basket trials, expanded access, related studies\n\nPhase 9: Scoring & Ranking (0-100 composite score)\n  - Tier classification: Optimal (80-100) \u002F Good (60-79) \u002F Possible (40-59) \u002F Exploratory (0-39)\n\nPhase 10: Report Synthesis\n  - Executive summary, ranked trial list, evidence grading, completeness checklist\n```\n\n---\n\n## Critical Tool Parameters\n\n### Clinical Trial Search Tools\n\n| Tool | Key Parameters | Notes |\n|------|---------------|-------|\n| `search_clinical_trials` | `query_term` (REQ), `condition`, `intervention`, `pageSize` | Main search |\n| `search_clinical_trials` | `action=\"search_studies\"` (REQ), `condition`, `intervention`, `limit` | Alternative search |\n| `get_clinical_trial_descriptions` | `action=\"get_study_details\"` (REQ), `nct_id` (REQ) | Full trial details |\n\n### Batch Trial Detail Tools (all take `nct_ids` array)\n\n| Tool | Second Required Param | Returns |\n|------|----------------------|---------|\n| `get_clinical_trial_eligibility_criteria` | `eligibility_criteria=\"all\"` | Eligibility text |\n| `get_clinical_trial_locations` | `location=\"all\"` | Site locations |\n| `get_clinical_trial_conditions_and_interventions` | `condition_and_intervention=\"all\"` | Arms\u002Finterventions |\n| `get_clinical_trial_status_and_dates` | `status_and_date=\"all\"` | Status\u002Fdates |\n| `get_clinical_trial_descriptions` | `description_type=\"brief\"` or `\"full\"` | Titles\u002Fsummaries |\n| `get_clinical_trial_outcome_measures` | `outcome_measures=\"all\"` | Outcomes |\n\n### Gene\u002FDisease Resolution\n\n| Tool | Key Parameters |\n|------|---------------|\n| `MyGene_query_genes` | `query`, `species` |\n| `OpenTargets_get_disease_id_description_by_name` | `diseaseName` |\n| `OpenTargets_get_target_id_description_by_name` | `targetName` |\n| `ols_search_efo_terms` | `query`, `limit` |\n\n### Drug Information\n\n| Tool | Key Parameters | Notes |\n|------|---------------|-------|\n| `OpenTargets_get_drug_id_description_by_name` | `drugName` | Resolve drug to ChEMBL ID |\n| `OpenTargets_get_drug_mechanisms_of_action_by_chemblId` | `chemblId` | Drug MoA and targets |\n| `OpenTargets_get_associated_drugs_by_target_ensemblID` | `ensemblId`, `size` | Drugs for a target |\n| `drugbank_get_targets_by_drug_name_or_drugbank_id` | `query`, `case_sensitive`, `exact_match`, `limit` (ALL REQ) | Drug targets |\n| `fda_pharmacogenomic_biomarkers` | (none) | FDA biomarker-drug list |\n| `FDA_get_indications_by_drug_name` | `drug_name`, `limit` | FDA indications |\n\n### Evidence Tools\n\n| Tool | Key Parameters |\n|------|---------------|\n| `PubMed_search_articles` | `query`, `max_results` |\n| `civic_get_variants_by_gene` | `gene_id` (CIViC int ID), `limit` |\n| `PharmGKB_search_genes` | `query` |\n\n### Known CIViC Gene IDs\n\nEGFR=19, BRAF=5, ALK=1, ABL1=4, KRAS=30, TP53=45, ERBB2=20, NTRK1=197, NTRK2=560, NTRK3=561, PIK3CA=37, MET=52, ROS1=118, RET=122, BRCA1=2370, BRCA2=2371\n\n### Critical Parameter Notes\n\n1. **DrugBank tools**: ALL 4 parameters (`query`, `case_sensitive`, `exact_match`, `limit`) are REQUIRED\n2. **`search_clinical_trials`**: `query_term` is REQUIRED even for disease-only searches\n3. **`search_clinical_trials`**: `action` must be exactly `\"search_studies\"`\n4. **CIViC `civic_search_variants`**: Does NOT filter by query - returns alphabetically\n5. **CIViC `civic_get_variants_by_gene`**: Takes CIViC gene ID (integer), NOT gene symbol\n6. **Batch clinical trial tools**: Accept arrays of NCT IDs, process in batches of 10\n\n---\n\n## Scoring Summary\n\n**Trial Match Score (0-100)**:\n- Molecular Match: 0-40 pts (exact variant=40, gene-level=30, pathway=20, none=10, excluded=0)\n- Clinical Eligibility: 0-25 pts (all met=25, most=18, some=10, ineligible=0)\n- Evidence Strength: 0-20 pts (FDA-approved=20, Phase III=15, Phase II=10, Phase I=5)\n- Trial Phase: 0-10 pts (III=10, II=8, I\u002FII=6, I=4)\n- Geographic: 0-5 pts (local=5, same country=3, international=1)\n\n**Recommendation Tiers**: Optimal (80-100), Good (60-79), Possible (40-59), Exploratory (0-39)\n\n**Evidence Tiers**: T1 (FDA\u002Fguideline), T2 (Phase III), T3 (Phase I\u002FII), T4 (computational)\n\nFor detailed scoring logic, see [SCORING_CRITERIA.md](.\u002FSCORING_CRITERIA.md).\n\n---\n\n## Parallelization Strategy\n\n**Group 1** (Phase 1 - simultaneous):\n- `MyGene_query_genes` per gene, `OpenTargets` disease search, `ols_search_efo_terms`, `fda_pharmacogenomic_biomarkers`\n\n**Group 2** (Phase 2 - simultaneous):\n- `search_clinical_trials` by disease, biomarker, and intervention; `search_clinical_trials` alternative\n\n**Group 3** (Phase 3 - simultaneous):\n- All batch detail tools (eligibility, interventions, locations, status, descriptions)\n\n**Group 4** (Phases 5-6 - per drug):\n- Drug resolution, MoA, FDA indications, PubMed evidence\n\n---\n\n## Error Handling\n\n1. Wrap every tool call in try\u002Fexcept\n2. Check for empty results and string error responses\n3. Use fallback tools when primary fails (e.g., OLS if OpenTargets fails)\n4. Document failures in completeness checklist\n5. Never let one failure block the entire analysis\n\n---\n\n## Reference Files\n\n| File | Contents |\n|------|----------|\n| [TOOLS_REFERENCE.md](.\u002FTOOLS_REFERENCE.md) | Full tool inventory with parameters and response structures |\n| [MATCHING_ALGORITHMS.md](.\u002FMATCHING_ALGORITHMS.md) | Patient profile standardization, biomarker parsing, molecular eligibility matching, drug-biomarker alignment code |\n| [SCORING_CRITERIA.md](.\u002FSCORING_CRITERIA.md) | Detailed scoring tables, molecular match logic, drug-biomarker alignment scoring |\n| [REPORT_TEMPLATE.md](.\u002FREPORT_TEMPLATE.md) | Full markdown report template with all sections |\n| [TRIAL_SEARCH_PATTERNS.md](.\u002FTRIAL_SEARCH_PATTERNS.md) | Search functions, batch retrieval, parallelization, common use patterns, edge cases |\n| [EXAMPLES.md](.\u002FEXAMPLES.md) | Worked examples for different matching scenarios |\n| [QUICK_START.md](.\u002FQUICK_START.md) | Quick-start guide for common workflows |\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Flibrary\u002Fskills\u002Ftooluniverse-clinical-trial-matching","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":49,"prompt":59,"zipAvailable":60},[50,53,56],{"tool":51,"command":52},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-clinical-trial-matching",{"tool":54,"command":55},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-clinical-trial-matching",{"tool":57,"command":58},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-clinical-trial-matching","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-matching\u002FSKILL.md",true,[62,68,72,76,80,84,90,94],{"path":63,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":66,"sourceHtmlUrl":67},"EXAMPLES.md","REFERENCE","参考文档",5399,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-clinical-trial-matching\u002FEXAMPLES.md",{"path":69,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":70,"sourceHtmlUrl":71},"MATCHING_ALGORITHMS.md",11118,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-clinical-trial-matching\u002FMATCHING_ALGORITHMS.md",{"path":73,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":74,"sourceHtmlUrl":75},"QUICK_START.md",4786,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-clinical-trial-matching\u002FQUICK_START.md",{"path":77,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":78,"sourceHtmlUrl":79},"REPORT_TEMPLATE.md",5896,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-clinical-trial-matching\u002FREPORT_TEMPLATE.md",{"path":81,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":82,"sourceHtmlUrl":83},"SCORING_CRITERIA.md",4615,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-clinical-trial-matching\u002FSCORING_CRITERIA.md",{"path":85,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":88,"sourceHtmlUrl":89},"test_skill.py","SCRIPT","脚本",44173,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-clinical-trial-matching\u002Ftest_skill.py",{"path":91,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":92,"sourceHtmlUrl":93},"TOOLS_REFERENCE.md",7442,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-clinical-trial-matching\u002FTOOLS_REFERENCE.md",{"path":95,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":96,"sourceHtmlUrl":97},"TRIAL_SEARCH_PATTERNS.md",11366,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-clinical-trial-matching\u002FTRIAL_SEARCH_PATTERNS.md",[99,119,150,177,190,206],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":37},"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",[],[106,107,108,109,29,110,111,112,113,32,114,115,116,117,118],"clarify requirements","clarify","requirements","risk","task","prompts","goal","scanning","context","repo","injection","execution","file",{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":130,"publishedAt":37},"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",[125],{"categoryNo":126,"categoryName":127,"taxonomyType":128,"taxonomyTypeDesc":129},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[131,132,133,134,135,136,137,138,139,140,141,142,143,144,32,145,146,147,148,149],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":151,"name":152,"nameZh":6,"description":153,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":154,"categories":155,"keywords":162,"publishedAt":37},"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",[156,159],{"categoryNo":157,"categoryName":158,"taxonomyType":128,"taxonomyTypeDesc":129},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":160,"categoryName":161,"taxonomyType":128,"taxonomyTypeDesc":129},"01JBSEEDCAT000000000000008","测试与质量",[163,164,165,166,167,168,169,170,171,172,132,173,174,175,176],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":178,"name":179,"nameZh":6,"description":180,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":181,"categories":182,"keywords":183,"publishedAt":37},"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",[],[179,184,36,185,186,187,188,189],"setup","project","installation","project setup","issues","state",{"skillNo":191,"name":192,"nameZh":6,"description":193,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":194,"categories":195,"keywords":197,"publishedAt":37},"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",[196],{"categoryNo":126,"categoryName":127,"taxonomyType":128,"taxonomyTypeDesc":129},[192,198,110,199,200,201,32,202,203,204,205],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":207,"name":184,"nameZh":6,"description":208,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":209,"categories":210,"keywords":211,"publishedAt":37},"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",[],[184,185,147,212,187,213],"files","interactive"]