[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DAVSAGQGGCSEHYWA3QMYQ3":3,"skill-same:01M6DAVSAGQGGCSEHYWA3QMYQ3":92},{"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":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":44,"commitSha":45,"skillDirectory":46,"forksCount":14,"repositoryHtmlUrl":47,"repositoryHomepageUrl":6,"ownerHtmlUrl":48,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":49,"install":50,"resources":63},"01M6DAVSAGQGGCSEHYWA3QMYQ3","tooluniverse-precision-medicine-stratification",null,"Comprehensive patient stratification for precision medicine by integrating genomic, clinical, and therapeutic data. Given a disease\u002Fcondition, genomic data (germline variants, somatic mutations, expression), and optional clinical parameters, performs multi-phase analysis covering disease disambiguation, genetic risk assessment, disease-specific molecular stratification, pharmacogenomic profiling, comorbidity\u002FDDI risk, pathway analysis, clinical evidence and guideline mapping, clinical trial matching, and integrated outcome prediction. Generates a quantitative Precision Medicine Risk Score (0-100) with risk tier assignment, treatment algorithm, pharmacogenomic guidance, clinical trial matches, and monitoring plan.","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-precision-medicine-stratification\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"tooluniverse precision medicine stratification","outcome","patient","clinical","molecular","matching","somatic","mutations","guidance","evidence","risk score","profiling","plan","analysis","risk","data","monitoring","assessment","risk assessment","monitoring plan","2026-11-10 10:12:30",false,"---\nname: tooluniverse-precision-medicine-stratification\ndescription: Comprehensive patient stratification for precision medicine by integrating genomic, clinical, and therapeutic data. Given a disease\u002Fcondition, genomic data (germline variants, somatic mutations, expression), and optional clinical parameters, performs multi-phase analysis covering disease disambiguation, genetic risk assessment, disease-specific molecular stratification, pharmacogenomic profiling, comorbidity\u002FDDI risk, pathway analysis, clinical evidence and guideline mapping, clinical trial matching, and integrated outcome prediction. Generates a quantitative Precision Medicine Risk Score (0-100) with risk tier assignment, treatment algorithm, pharmacogenomic guidance, clinical trial matches, and monitoring plan.\n---\n\n# Precision Medicine Patient Stratification\n\nTransform patient genomic and clinical profiles into actionable risk stratification, treatment recommendations, and personalized therapeutic strategies.\n\n## Reasoning Before Searching\n\nStratification means splitting patients into groups that respond differently to a treatment or have different prognoses. Ask these questions before running any tools:\n\n1. **What molecular feature predicts response?** Candidates: somatic mutation (e.g., EGFR L858R), germline variant (e.g., BRCA1 LoF), expression level (e.g., HER2 overexpression), germline pharmacogenomic variant (e.g., CYP2C19 PM), or composite biomarker (e.g., TMB-H + MSI-H).\n2. **Is the predictive feature actionable?** Knowing it must change treatment — either the drug choice, dose, or monitoring plan. A variant with prognostic value but no therapeutic consequence is not a stratification biomarker.\n3. **What is the evidence level for the stratifier?** FDA-approved companion diagnostic (T1) vs. exploratory (T4) changes how much weight to place on the finding.\n\nRoute to the correct Phase 3 path BEFORE running Phase 2 tools — cancer, metabolic, CVD, rare disease, and autoimmune pipelines require different stratifiers.\n\n**LOOK UP DON'T GUESS**: Never assume a variant is pathogenic, never assume a gene is relevant to a disease, never assign metabolizer status without PharmGKB or CPIC evidence.\n\n**KEY PRINCIPLES**:\n1. **Report-first** - Create report file FIRST, then populate progressively\n2. **Disease-specific logic** - Cancer vs metabolic vs rare disease pipelines diverge at Phase 3\n3. **Multi-level integration** - Germline + somatic + expression + clinical data layers\n4. **Evidence-graded** - Every finding has an evidence tier (T1-T4)\n5. **Quantitative output** - Precision Medicine Risk Score (0-100)\n6. **Source-referenced** - Every statement cites the tool\u002Fdatabase source\n7. **English-first queries** - Always use English terms in tool calls\n\n**Reference files** (same directory):\n- `TOOLS_REFERENCE.md` - Tool parameters, response formats, phase-by-phase tool lists\n- `SCORING_REFERENCE.md` - Scoring matrices, risk tiers, pathogenicity tables, PGx tables\n- `REPORT_TEMPLATE.md` - Output report template, treatment algorithms, completeness requirements\n- `EXAMPLES.md` - Six worked examples (cancer, metabolic, NSCLC, CVD, rare, neuro)\n- `QUICK_START.md` - Sample prompts and output summary\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 about patient risk stratification, treatment selection, prognosis prediction, or personalized therapeutic strategy for any disease with genomic\u002Fclinical data.\n\n**NOT for** (use other skills instead):\n- Single variant interpretation -> `tooluniverse-variant-interpretation`\n- Immunotherapy-specific prediction -> `tooluniverse-immunotherapy-response-prediction`\n- Drug safety profiling only -> `tooluniverse-adverse-event-detection`\n- Target validation -> `tooluniverse-drug-target-validation`\n- Clinical trial search only -> `tooluniverse-clinical-trial-matching`\n- Drug-drug interaction only -> `tooluniverse-drug-drug-interaction`\n- PRS calculation only -> `tooluniverse-polygenic-risk-score`\n\n---\n\n## Input Parsing\n\n### Required\n- **Disease\u002Fcondition**: Free-text disease name\n- **At least one of**: Germline variants, somatic mutations, gene list, or clinical biomarkers\n\n### Optional (improves stratification)\n- Age, sex, ethnicity, disease stage, comorbidities, prior treatments, family history\n- Current medications (for DDI and PGx), stratification goal\n\n### Disease Type Classification\n\nClassify into one category (determines Phase 3 routing):\n\n| Category | Examples |\n|----------|----------|\n| **CANCER** | Breast, lung, colorectal, melanoma |\n| **METABOLIC** | Type 2 diabetes, obesity, NAFLD |\n| **CARDIOVASCULAR** | CAD, heart failure, AF |\n| **NEUROLOGICAL** | Alzheimer, Parkinson, epilepsy |\n| **RARE\u002FMONOGENIC** | Marfan, CF, sickle cell, Huntington |\n| **AUTOIMMUNE** | RA, lupus, MS, Crohn's |\n\n---\n\n## Critical Tool Parameter Notes\n\nSee `TOOLS_REFERENCE.md` for full details. Key gotchas:\n\n- **MyGene_query_genes**: param is `query` (NOT `q`)\n- **EnsemblVEP_annotate_rsid**: param is `variant_id` (NOT `rsid`)\n- **ensembl_lookup_gene**: REQUIRES `species='homo_sapiens'`\n- **DrugBank tools**: ALL require 4 params: `query`, `case_sensitive`, `exact_match`, `limit`\n- **cBioPortal_get_mutations**: `gene_list` is a STRING (space-separated), not array\n- **PubMed_search_articles**: Returns a plain list of dicts, NOT `{articles: [...]}`\n- **fda_pharmacogenomic_biomarkers**: Use `limit=1000` for all results\n- **gnomAD**: May return \"Service overloaded\" - skip gracefully\n- **OpenTargets**: Always nested `{data: {entity: {field: ...}}}` structure\n\n---\n\n## Workflow Overview\n\n```\nPhase 1: Disease Disambiguation & Profile Standardization\nPhase 2: Genetic Risk Assessment\nPhase 3: Disease-Specific Molecular Stratification (routes by disease type)\nPhase 4: Pharmacogenomic Profiling\nPhase 5: Comorbidity & Drug Interaction Risk\nPhase 6: Molecular Pathway Analysis\nPhase 7: Clinical Evidence & Guidelines\nPhase 8: Clinical Trial Matching\nPhase 9: Integrated Scoring & Recommendations\n```\n\n---\n\n## Phase 1: Disease Disambiguation & Profile Standardization\n\n1. **Resolve disease to EFO ID** using `OpenTargets_get_disease_id_description_by_name`\n2. **Classify disease type** (CANCER\u002FMETABOLIC\u002FCVD\u002FNEUROLOGICAL\u002FRARE\u002FAUTOIMMUNE)\n3. **Parse genomic data** into structured format (gene, variant, type)\n4. **Resolve gene IDs** using `MyGene_query_genes` to get Ensembl\u002FEntrez IDs\n\n## Phase 2: Genetic Risk Assessment\n\n1. **Germline variant pathogenicity**: `ClinVar_search_variants`, `EnsemblVEP_annotate_rsid`\u002F`_hgvs`\n2. **Gene-disease association**: `OpenTargets_target_disease_evidence`\n3. **GWAS polygenic risk**: `gwas_get_associations_for_trait`, `OpenTargets_search_gwas_studies_by_disease`\n4. **Population frequency**: `gnomad_get_variant`\n5. **Gene constraint**: `gnomad_get_gene_constraints` (pLI, LOEUF scores)\n\nScoring: See `SCORING_REFERENCE.md` for genetic risk score component (0-35 points).\n\n## Phase 3: Disease-Specific Molecular Stratification\n\n### CANCER PATH\n1. **Molecular subtyping**: `cBioPortal_get_mutations`, `HPA_get_cancer_prognostics_by_gene`\n2. **TMB\u002FMSI\u002FHRD**: `fda_pharmacogenomic_biomarkers` for FDA cutoffs\n3. **Prognostic stratification**: Combine stage + molecular features\n\n### METABOLIC PATH\n1. **Genetic risk integration**: `GWAS_search_associations_by_gene`, `OpenTargets_target_disease_evidence`\n2. **Complication risk**: Based on HbA1c, duration, existing complications\n\n### CVD PATH\n1. **FH gene check**: `ClinVar_search_variants` for LDLR, APOB, PCSK9\n2. **Statin PGx**: `PharmGKB_get_clinical_annotations` for SLCO1B1\n\n### RARE DISEASE PATH\n1. **Causal variant identification**: `ClinVar_search_variants`\n2. **Genotype-phenotype**: `UniProt_get_disease_variants_by_accession`\n\nScoring: See `SCORING_REFERENCE.md` for disease-specific tables.\n\n## Phase 4: Pharmacogenomic Profiling\n\n1. **Drug-metabolizing enzymes**: `PharmGKB_get_clinical_annotations`, `PharmGKB_get_dosing_guidelines`\n2. **FDA PGx biomarkers**: `fda_pharmacogenomic_biomarkers` (use `limit=1000`)\n3. **Treatment-specific PGx**: `PharmGKB_get_drug_details`\n\nScoring: See `SCORING_REFERENCE.md` for PGx risk score (0-10 points).\n\n## Phase 5: Comorbidity & Drug Interaction Risk\n\n1. **Disease overlap**: `OpenTargets_get_associated_targets_by_disease_efoId`\n2. **DDI check**: `drugbank_get_drug_interactions_by_drug_name_or_id`, `FDA_get_drug_interactions_by_drug_name`\n3. **PGx-amplified DDI**: If PM genotype + CYP inhibitor, flag compounded risk\n\n## Phase 6: Molecular Pathway Analysis\n\n1. **Pathway enrichment**: `enrichr_gene_enrichment_analysis` (libs: `KEGG_2021_Human`, `Reactome_2022`, `GO_Biological_Process_2023`)\n2. **Reactome mapping**: `ReactomeAnalysis_pathway_enrichment`, `Reactome_map_uniprot_to_pathways`\n3. **Network analysis**: `STRING_get_interaction_partners`, `STRING_functional_enrichment`\n4. **Druggable targets**: `OpenTargets_get_target_tractability_by_ensemblID`\n\n## Phase 7: Clinical Evidence & Guidelines\n\n1. **Guidelines search**: `PubMed_Guidelines_Search` (fallback: `PubMed_search_articles`)\n2. **FDA-approved therapies**: `OpenTargets_get_associated_drugs_by_disease_efoId`, `FDA_get_indications_by_drug_name`\n3. **Biomarker-drug evidence**: `civic_search_evidence_items`, `civic_search_assertions`\n\n## Phase 8: Clinical Trial Matching\n\n1. **Biomarker-driven trials**: `search_clinical_trials` with condition + intervention\n2. **Precision medicine trials**: `search_clinical_trials` for basket\u002Fumbrella trials\n\n## Phase 9: Integrated Scoring & Recommendations\n\n### Score Components (total 0-100)\n- **Genetic Risk** (0-35): Pathogenicity + gene-disease association + PRS\n- **Clinical Risk** (0-30): Stage\u002Fbiomarkers\u002Fcomorbidities\n- **Molecular Features** (0-25): Driver mutations, subtypes, actionable targets\n- **Pharmacogenomic Risk** (0-10): Metabolizer status, HLA alleles\n\n### Risk Tiers\n| Score | Tier | Management |\n|-------|------|------------|\n| 75-100 | VERY HIGH | Intensive treatment, subspecialty referral, clinical trial |\n| 50-74 | HIGH | Aggressive treatment, close monitoring |\n| 25-49 | INTERMEDIATE | Standard guideline-based care, PGx-guided dosing |\n| 0-24 | LOW | Surveillance, prevention, risk factor modification |\n\n### Output\nGenerate report per `REPORT_TEMPLATE.md`. See `SCORING_REFERENCE.md` for detailed scoring matrices.\n\n---\n\n## Common Use Patterns\n\nSee `EXAMPLES.md` for six detailed worked examples:\n1. **Cancer + actionable mutation**: Breast cancer, BRCA1, ER+\u002FHER2- -> Score ~55-65 (HIGH)\n2. **Metabolic + PGx concern**: T2D, CYP2C19 PM on clopidogrel -> Score ~55-65 (HIGH)\n3. **NSCLC comprehensive**: EGFR L858R, TMB 25, PD-L1 80% -> Score ~75-85 (VERY HIGH)\n4. **CVD risk**: LDL 190, SLCO1B1*5, family hx MI -> Score ~50-60 (HIGH)\n5. **Rare disease**: Marfan, FBN1 variant -> Score ~55-65 (HIGH)\n6. **Neurological risk**: APOE e4\u002Fe4, family hx Alzheimer's -> Score ~60-72 (HIGH)\n","# Precision Medicine Patient Stratification\n\nTransform patient genomic and clinical profiles into actionable risk stratification, treatment recommendations, and personalized therapeutic strategies.\n\n## Reasoning Before Searching\n\nStratification means splitting patients into groups that respond differently to a treatment or have different prognoses. Ask these questions before running any tools:\n\n1. **What molecular feature predicts response?** Candidates: somatic mutation (e.g., EGFR L858R), germline variant (e.g., BRCA1 LoF), expression level (e.g., HER2 overexpression), germline pharmacogenomic variant (e.g., CYP2C19 PM), or composite biomarker (e.g., TMB-H + MSI-H).\n2. **Is the predictive feature actionable?** Knowing it must change treatment — either the drug choice, dose, or monitoring plan. A variant with prognostic value but no therapeutic consequence is not a stratification biomarker.\n3. **What is the evidence level for the stratifier?** FDA-approved companion diagnostic (T1) vs. exploratory (T4) changes how much weight to place on the finding.\n\nRoute to the correct Phase 3 path BEFORE running Phase 2 tools — cancer, metabolic, CVD, rare disease, and autoimmune pipelines require different stratifiers.\n\n**LOOK UP DON'T GUESS**: Never assume a variant is pathogenic, never assume a gene is relevant to a disease, never assign metabolizer status without PharmGKB or CPIC evidence.\n\n**KEY PRINCIPLES**:\n1. **Report-first** - Create report file FIRST, then populate progressively\n2. **Disease-specific logic** - Cancer vs metabolic vs rare disease pipelines diverge at Phase 3\n3. **Multi-level integration** - Germline + somatic + expression + clinical data layers\n4. **Evidence-graded** - Every finding has an evidence tier (T1-T4)\n5. **Quantitative output** - Precision Medicine Risk Score (0-100)\n6. **Source-referenced** - Every statement cites the tool\u002Fdatabase source\n7. **English-first queries** - Always use English terms in tool calls\n\n**Reference files** (same directory):\n- `TOOLS_REFERENCE.md` - Tool parameters, response formats, phase-by-phase tool lists\n- `SCORING_REFERENCE.md` - Scoring matrices, risk tiers, pathogenicity tables, PGx tables\n- `REPORT_TEMPLATE.md` - Output report template, treatment algorithms, completeness requirements\n- `EXAMPLES.md` - Six worked examples (cancer, metabolic, NSCLC, CVD, rare, neuro)\n- `QUICK_START.md` - Sample prompts and output summary\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 about patient risk stratification, treatment selection, prognosis prediction, or personalized therapeutic strategy for any disease with genomic\u002Fclinical data.\n\n**NOT for** (use other skills instead):\n- Single variant interpretation -> `tooluniverse-variant-interpretation`\n- Immunotherapy-specific prediction -> `tooluniverse-immunotherapy-response-prediction`\n- Drug safety profiling only -> `tooluniverse-adverse-event-detection`\n- Target validation -> `tooluniverse-drug-target-validation`\n- Clinical trial search only -> `tooluniverse-clinical-trial-matching`\n- Drug-drug interaction only -> `tooluniverse-drug-drug-interaction`\n- PRS calculation only -> `tooluniverse-polygenic-risk-score`\n\n---\n\n## Input Parsing\n\n### Required\n- **Disease\u002Fcondition**: Free-text disease name\n- **At least one of**: Germline variants, somatic mutations, gene list, or clinical biomarkers\n\n### Optional (improves stratification)\n- Age, sex, ethnicity, disease stage, comorbidities, prior treatments, family history\n- Current medications (for DDI and PGx), stratification goal\n\n### Disease Type Classification\n\nClassify into one category (determines Phase 3 routing):\n\n| Category | Examples |\n|----------|----------|\n| **CANCER** | Breast, lung, colorectal, melanoma |\n| **METABOLIC** | Type 2 diabetes, obesity, NAFLD |\n| **CARDIOVASCULAR** | CAD, heart failure, AF |\n| **NEUROLOGICAL** | Alzheimer, Parkinson, epilepsy |\n| **RARE\u002FMONOGENIC** | Marfan, CF, sickle cell, Huntington |\n| **AUTOIMMUNE** | RA, lupus, MS, Crohn's |\n\n---\n\n## Critical Tool Parameter Notes\n\nSee `TOOLS_REFERENCE.md` for full details. Key gotchas:\n\n- **MyGene_query_genes**: param is `query` (NOT `q`)\n- **EnsemblVEP_annotate_rsid**: param is `variant_id` (NOT `rsid`)\n- **ensembl_lookup_gene**: REQUIRES `species='homo_sapiens'`\n- **DrugBank tools**: ALL require 4 params: `query`, `case_sensitive`, `exact_match`, `limit`\n- **cBioPortal_get_mutations**: `gene_list` is a STRING (space-separated), not array\n- **PubMed_search_articles**: Returns a plain list of dicts, NOT `{articles: [...]}`\n- **fda_pharmacogenomic_biomarkers**: Use `limit=1000` for all results\n- **gnomAD**: May return \"Service overloaded\" - skip gracefully\n- **OpenTargets**: Always nested `{data: {entity: {field: ...}}}` structure\n\n---\n\n## Workflow Overview\n\n```\nPhase 1: Disease Disambiguation & Profile Standardization\nPhase 2: Genetic Risk Assessment\nPhase 3: Disease-Specific Molecular Stratification (routes by disease type)\nPhase 4: Pharmacogenomic Profiling\nPhase 5: Comorbidity & Drug Interaction Risk\nPhase 6: Molecular Pathway Analysis\nPhase 7: Clinical Evidence & Guidelines\nPhase 8: Clinical Trial Matching\nPhase 9: Integrated Scoring & Recommendations\n```\n\n---\n\n## Phase 1: Disease Disambiguation & Profile Standardization\n\n1. **Resolve disease to EFO ID** using `OpenTargets_get_disease_id_description_by_name`\n2. **Classify disease type** (CANCER\u002FMETABOLIC\u002FCVD\u002FNEUROLOGICAL\u002FRARE\u002FAUTOIMMUNE)\n3. **Parse genomic data** into structured format (gene, variant, type)\n4. **Resolve gene IDs** using `MyGene_query_genes` to get Ensembl\u002FEntrez IDs\n\n## Phase 2: Genetic Risk Assessment\n\n1. **Germline variant pathogenicity**: `ClinVar_search_variants`, `EnsemblVEP_annotate_rsid`\u002F`_hgvs`\n2. **Gene-disease association**: `OpenTargets_target_disease_evidence`\n3. **GWAS polygenic risk**: `gwas_get_associations_for_trait`, `OpenTargets_search_gwas_studies_by_disease`\n4. **Population frequency**: `gnomad_get_variant`\n5. **Gene constraint**: `gnomad_get_gene_constraints` (pLI, LOEUF scores)\n\nScoring: See `SCORING_REFERENCE.md` for genetic risk score component (0-35 points).\n\n## Phase 3: Disease-Specific Molecular Stratification\n\n### CANCER PATH\n1. **Molecular subtyping**: `cBioPortal_get_mutations`, `HPA_get_cancer_prognostics_by_gene`\n2. **TMB\u002FMSI\u002FHRD**: `fda_pharmacogenomic_biomarkers` for FDA cutoffs\n3. **Prognostic stratification**: Combine stage + molecular features\n\n### METABOLIC PATH\n1. **Genetic risk integration**: `GWAS_search_associations_by_gene`, `OpenTargets_target_disease_evidence`\n2. **Complication risk**: Based on HbA1c, duration, existing complications\n\n### CVD PATH\n1. **FH gene check**: `ClinVar_search_variants` for LDLR, APOB, PCSK9\n2. **Statin PGx**: `PharmGKB_get_clinical_annotations` for SLCO1B1\n\n### RARE DISEASE PATH\n1. **Causal variant identification**: `ClinVar_search_variants`\n2. **Genotype-phenotype**: `UniProt_get_disease_variants_by_accession`\n\nScoring: See `SCORING_REFERENCE.md` for disease-specific tables.\n\n## Phase 4: Pharmacogenomic Profiling\n\n1. **Drug-metabolizing enzymes**: `PharmGKB_get_clinical_annotations`, `PharmGKB_get_dosing_guidelines`\n2. **FDA PGx biomarkers**: `fda_pharmacogenomic_biomarkers` (use `limit=1000`)\n3. **Treatment-specific PGx**: `PharmGKB_get_drug_details`\n\nScoring: See `SCORING_REFERENCE.md` for PGx risk score (0-10 points).\n\n## Phase 5: Comorbidity & Drug Interaction Risk\n\n1. **Disease overlap**: `OpenTargets_get_associated_targets_by_disease_efoId`\n2. **DDI check**: `drugbank_get_drug_interactions_by_drug_name_or_id`, `FDA_get_drug_interactions_by_drug_name`\n3. **PGx-amplified DDI**: If PM genotype + CYP inhibitor, flag compounded risk\n\n## Phase 6: Molecular Pathway Analysis\n\n1. **Pathway enrichment**: `enrichr_gene_enrichment_analysis` (libs: `KEGG_2021_Human`, `Reactome_2022`, `GO_Biological_Process_2023`)\n2. **Reactome mapping**: `ReactomeAnalysis_pathway_enrichment`, `Reactome_map_uniprot_to_pathways`\n3. **Network analysis**: `STRING_get_interaction_partners`, `STRING_functional_enrichment`\n4. **Druggable targets**: `OpenTargets_get_target_tractability_by_ensemblID`\n\n## Phase 7: Clinical Evidence & Guidelines\n\n1. **Guidelines search**: `PubMed_Guidelines_Search` (fallback: `PubMed_search_articles`)\n2. **FDA-approved therapies**: `OpenTargets_get_associated_drugs_by_disease_efoId`, `FDA_get_indications_by_drug_name`\n3. **Biomarker-drug evidence**: `civic_search_evidence_items`, `civic_search_assertions`\n\n## Phase 8: Clinical Trial Matching\n\n1. **Biomarker-driven trials**: `search_clinical_trials` with condition + intervention\n2. **Precision medicine trials**: `search_clinical_trials` for basket\u002Fumbrella trials\n\n## Phase 9: Integrated Scoring & Recommendations\n\n### Score Components (total 0-100)\n- **Genetic Risk** (0-35): Pathogenicity + gene-disease association + PRS\n- **Clinical Risk** (0-30): Stage\u002Fbiomarkers\u002Fcomorbidities\n- **Molecular Features** (0-25): Driver mutations, subtypes, actionable targets\n- **Pharmacogenomic Risk** (0-10): Metabolizer status, HLA alleles\n\n### Risk Tiers\n| Score | Tier | Management |\n|-------|------|------------|\n| 75-100 | VERY HIGH | Intensive treatment, subspecialty referral, clinical trial |\n| 50-74 | HIGH | Aggressive treatment, close monitoring |\n| 25-49 | INTERMEDIATE | Standard guideline-based care, PGx-guided dosing |\n| 0-24 | LOW | Surveillance, prevention, risk factor modification |\n\n### Output\nGenerate report per `REPORT_TEMPLATE.md`. See `SCORING_REFERENCE.md` for detailed scoring matrices.\n\n---\n\n## Common Use Patterns\n\nSee `EXAMPLES.md` for six detailed worked examples:\n1. **Cancer + actionable mutation**: Breast cancer, BRCA1, ER+\u002FHER2- -> Score ~55-65 (HIGH)\n2. **Metabolic + PGx concern**: T2D, CYP2C19 PM on clopidogrel -> Score ~55-65 (HIGH)\n3. **NSCLC comprehensive**: EGFR L858R, TMB 25, PD-L1 80% -> Score ~75-85 (VERY HIGH)\n4. **CVD risk**: LDL 190, SLCO1B1*5, family hx MI -> Score ~50-60 (HIGH)\n5. **Rare disease**: Marfan, FBN1 variant -> Score ~55-65 (HIGH)\n6. **Neurological risk**: APOE e4\u002Fe4, family hx Alzheimer's -> Score ~60-72 (HIGH)\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Flibrary\u002Fskills\u002Ftooluniverse-precision-medicine-stratification","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":51,"prompt":61,"zipAvailable":62},[52,55,58],{"tool":53,"command":54},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-precision-medicine-stratification",{"tool":56,"command":57},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-precision-medicine-stratification",{"tool":59,"command":60},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-precision-medicine-stratification","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-precision-medicine-stratification\u002FSKILL.md",true,[64,70,74,78,82,88],{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"EXAMPLES.md","REFERENCE","参考文档",8656,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-precision-medicine-stratification\u002FEXAMPLES.md",{"path":71,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":72,"sourceHtmlUrl":73},"QUICK_START.md",3691,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-precision-medicine-stratification\u002FQUICK_START.md",{"path":75,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":76,"sourceHtmlUrl":77},"REPORT_TEMPLATE.md",5134,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-precision-medicine-stratification\u002FREPORT_TEMPLATE.md",{"path":79,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":80,"sourceHtmlUrl":81},"SCORING_REFERENCE.md",9471,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-precision-medicine-stratification\u002FSCORING_REFERENCE.md",{"path":83,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":86,"sourceHtmlUrl":87},"test_skill.py","SCRIPT","脚本",57116,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-precision-medicine-stratification\u002Ftest_skill.py",{"path":89,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":90,"sourceHtmlUrl":91},"TOOLS_REFERENCE.md",8723,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-precision-medicine-stratification\u002FTOOLS_REFERENCE.md",[93,114,145,172,186,202],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":39},"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",[],[100,101,102,33,103,104,105,106,107,108,109,110,111,112,113],"clarify requirements","clarify","requirements","options","task","prompts","goal","scanning","use","context","repo","injection","execution","file",{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":125,"publishedAt":39},"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",[120],{"categoryNo":121,"categoryName":122,"taxonomyType":123,"taxonomyTypeDesc":124},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[126,127,128,129,130,131,132,133,134,135,136,137,138,139,108,140,141,142,143,144],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":146,"name":147,"nameZh":6,"description":148,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":149,"categories":150,"keywords":157,"publishedAt":39},"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",[151,154],{"categoryNo":152,"categoryName":153,"taxonomyType":123,"taxonomyTypeDesc":124},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":155,"categoryName":156,"taxonomyType":123,"taxonomyTypeDesc":124},"01JBSEEDCAT000000000000008","测试与质量",[158,159,160,161,162,163,164,165,166,167,127,168,169,170,171],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":173,"name":174,"nameZh":6,"description":175,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":176,"categories":177,"keywords":178,"publishedAt":39},"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",[],[174,179,180,181,182,183,184,185],"setup","report","project","installation","project setup","issues","state",{"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":193,"publishedAt":39},"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",[192],{"categoryNo":121,"categoryName":122,"taxonomyType":123,"taxonomyTypeDesc":124},[188,194,104,195,196,197,108,198,199,200,201],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":203,"name":179,"nameZh":6,"description":204,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":205,"categories":206,"keywords":207,"publishedAt":39},"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",[],[179,181,142,208,183,209],"files","interactive"]