[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DAQ65TDK608YHVAM6KSWED":3,"skill-same:01M6DAQ65TDK608YHVAM6KSWED":93},{"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":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":14,"repositoryHtmlUrl":52,"repositoryHomepageUrl":6,"ownerHtmlUrl":53,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":54,"install":55,"resources":68},"01M6DAQ65TDK608YHVAM6KSWED","tooluniverse-drug-target-validation",null,"Comprehensive computational validation of drug targets for early-stage drug discovery. Evaluates targets across 10 dimensions (disambiguation, disease association, druggability, chemical matter, clinical precedent, safety, pathway context, validation evidence, structural insights, validation roadmap) using 60+ ToolUniverse tools. Produces a quantitative Target Validation Score (0-100) with GO\u002FNO-GO recommendation. Use when users ask about target validation, druggability assessment, target prioritization, or \"is X a good drug target for Y?\"","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-drug-target-validation\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000031","产品经理","PROFESSION","适用职业",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"tooluniverse drug target validation","validation","evidence","clinical","structural","computational","stage","chemical","across","dimensions","roadmap","go","good","use","ask","precedent","prioritization","discovery","Safety","assessment","2026-11-10 10:12:30",false,"---\nname: tooluniverse-drug-target-validation\ndescription: Comprehensive computational validation of drug targets for early-stage drug discovery. Evaluates targets across 10 dimensions (disambiguation, disease association, druggability, chemical matter, clinical precedent, safety, pathway context, validation evidence, structural insights, validation roadmap) using 60+ ToolUniverse tools. Produces a quantitative Target Validation Score (0-100) with GO\u002FNO-GO recommendation. Use when users ask about target validation, druggability assessment, target prioritization, or \"is X a good drug target for Y?\"\n---\n\n# Drug Target Validation Pipeline\n\nValidate drug target hypotheses using multi-dimensional computational evidence before committing to wet-lab work. Produces a quantitative Target Validation Score (0-100) with priority tier classification and GO\u002FNO-GO recommendation.\n\n## Reasoning Before Searching\n\nA valid drug target must pass 4 gates in order. Failing an early gate makes later gates irrelevant:\n\n1. **Genetic evidence linking it to disease**: Does human genetic data (GWAS, rare variant studies, Mendelian genetics) support this target's role? Genetic evidence is the strongest predictor of clinical success. Use OpenTargets and GWAS catalog before anything else. If no genetic link exists, the hypothesis is speculative — document this clearly.\n2. **Druggability**: Can a molecule reach and modulate the target? Check structure availability (PDB, AlphaFold), binding pocket prediction (ProteinsPlus), target class (kinase, GPCR, nuclear receptor = favorable; transcription factor, scaffold protein = difficult), and existing chemical probes.\n3. **Safety — essentiality in normal tissue**: Is the target expressed in critical tissues (heart, liver, bone marrow)? Is knockout lethal in mice? High expression in essential tissue or lethality in mouse models is a strong safety red flag even before any clinical data.\n4. **Competitive landscape**: Are other drugs already approved or in late-stage trials for this target? If so, the bar is differentiation, not first-in-class. Check ChEMBL, DrugBank, and ClinicalTrials.gov early.\n\nDo not proceed to Phase 3 (Chemical Matter) before completing Phase 1 (Disease Association). Gate 1 failures should prompt a NO-GO or pivot recommendation.\n\n**LOOK UP DON'T GUESS**: Never assume a target is druggable based on its protein family alone, never assume expression is low in a tissue without checking GTEx or HPA, never assume no competitors without searching ClinicalTrials.gov.\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## Key Principles\n\n1. **Report-first** - Create report file FIRST, then populate progressively\n2. **Target disambiguation FIRST** - Resolve all identifiers before analysis\n3. **Evidence grading** - Grade all evidence as T1 (experimental) to T4 (computational)\n4. **Disease-specific** - Tailor analysis to disease context when provided\n5. **Modality-aware** - Consider small molecule vs biologics tractability\n6. **Safety-first** - Prominently flag safety concerns early\n7. **Quantitative scoring** - Every dimension scored numerically (0-100 composite)\n8. **Negative results documented** - \"No data\" is data; empty sections are failures\n9. **Source references** - Every statement must cite tool\u002Fdatabase\n10. **English-first queries** - Always use English terms in tool calls; respond in user's language\n\n## When to Use\n\nApply when users ask about:\n- \"Is [target] a good drug target for [disease]?\"\n- Target validation, druggability assessment, or target prioritization\n- Safety risks of modulating a target\n- Chemical starting points for target validation\n- GO\u002FNO-GO recommendation for a target\n\n**Not for** (use other skills): general target biology (`tooluniverse-target-research`), drug compound profiling (`tooluniverse-drug-research`), variant interpretation (`tooluniverse-variant-interpretation`), disease research (`tooluniverse-disease-research`).\n\n## Input Parameters\n\n| Parameter | Required | Description | Example |\n|-----------|----------|-------------|---------|\n| **target** | Yes | Gene symbol, protein name, or UniProt ID | `EGFR`, `P00533` |\n| **disease** | No | Disease\u002Findication for context | `Non-small cell lung cancer` |\n| **modality** | No | Preferred therapeutic modality | `small molecule`, `antibody`, `PROTAC` |\n\n## Reference Files\n\n- **SCORING_CRITERIA.md** - Detailed scoring matrices, evidence grading, priority tiers, score calculation\n- **REPORT_TEMPLATE.md** - Full report template, completeness checklist, section format examples\n- **TOOL_REFERENCE.md** - Verified tool parameters, known corrections, fallback chains, modality-specific guidance, phase-by-phase tool lists\n- **QUICK_START.md** - Quick start guide\n\n---\n\n## Scoring Overview\n\n**Total: 0-100 points** across 5 dimensions (details in SCORING_CRITERIA.md):\n\n| Dimension | Max | Sub-dimensions |\n|-----------|-----|----------------|\n| Disease Association | 30 | Genetic (10) + Literature (10) + Pathway (10) |\n| Druggability | 25 | Structure (10) + Chemical matter (10) + Target class (5) |\n| Safety Profile | 20 | Expression (5) + Genetic validation (10) + ADRs (5) |\n| Clinical Precedent | 15 | Based on highest clinical stage achieved |\n| Validation Evidence | 10 | Functional studies (5) + Disease models (5) |\n\n**Priority Tiers**: 80-100 = Tier 1 (GO) | 60-79 = Tier 2 (CONDITIONAL GO) | 40-59 = Tier 3 (CAUTION) | 0-39 = Tier 4 (NO-GO)\n\n**Evidence Grades**: T1 (clinical proof) > T2 (functional studies) > T3 (associations) > T4 (predictions)\n\n---\n\n## Pipeline Phases\n\n### Phase 0: Target Disambiguation (ALWAYS FIRST)\n\nResolve target to ALL identifiers before any analysis.\n\n**Steps**:\n1. `MyGene_query_genes` - Get initial IDs (Ensembl, UniProt, Entrez)\n2. `ensembl_lookup_gene` - Get versioned Ensembl ID (species=\"homo_sapiens\" REQUIRED)\n3. `ensembl_get_xrefs` - Cross-references (HGNC, etc.)\n4. `OpenTargets_get_target_id_description_by_name` - Verify OT target\n5. `ChEMBL_search_targets` - Get ChEMBL target ID\n6. `UniProt_get_function_by_accession` - Function summary (returns list of strings)\n7. `UniProt_get_alternative_names_by_accession` - Collision detection\n\n**Output**: Table of verified identifiers (Gene Symbol, Ensembl, UniProt, Entrez, ChEMBL, HGNC) plus protein function and target class.\n\n### Phase 1: Disease Association (0-30 pts)\n\nQuantify target-disease association from genetic, literature, and pathway evidence.\n\n**Key tools**:\n- `OpenTargets_get_diseases_phenotypes_by_target_ensembl` - Disease associations\n- `OpenTargets_target_disease_evidence` - Detailed evidence (needs `efoId` + `ensemblId`)\n- `OpenTargets_get_evidence_by_datasource` - Evidence by data source\n- `gwas_get_snps_for_gene` \u002F `gwas_search_studies` - GWAS evidence\n- `gnomad_get_gene_constraints` - Genetic constraint (pLI, LOEUF)\n- `PubMed_search_articles` - Literature (returns plain list of dicts)\n- `OpenTargets_get_publications_by_target_ensemblID` - OT publications (uses `entityId`)\n\n### Phase 2: Druggability (0-25 pts)\n\nAssess whether the target is amenable to therapeutic intervention.\n\n**Key tools**:\n- `OpenTargets_get_target_tractability_by_ensemblID` - Tractability (SM, AB, PR, OC)\n- `OpenTargets_get_target_classes_by_ensemblID` - Target classification\n- `Pharos_get_target` - TDL: Tclin > Tchem > Tbio > Tdark\n- `DGIdb_get_gene_druggability` - Druggability categories\n- `alphafold_get_prediction` (param: `qualifier`) \u002F `alphafold_get_summary`\n- `ProteinsPlus_predict_binding_sites` - Pocket detection\n- `OpenTargets_get_chemical_probes_by_target_ensemblID` - Chemical probes\n- `OpenTargets_get_target_enabling_packages_by_ensemblID` - TEPs\n- `TCDB_get_transporter` - For SLC\u002FABC transporter targets: TC classification, family, PDB structures (param: `uniprot_accession`)\n- `TCDB_search_by_substrate` - Find transporters by substrate (param: `substrate_name`)\n\n### Phase 3: Chemical Matter (feeds Phase 2 scoring)\n\nIdentify existing chemical starting points for target validation.\n\n**Key tools**:\n- `ChEMBL_search_targets` + `ChEMBL_get_target_activities` - Bioactivity data (note: `target_chembl_id__exact` with double underscore)\n- `BindingDB_get_ligands_by_uniprot` - Binding data (affinity in nM)\n- `PubChem_search_assays_by_target_gene` + `PubChem_get_assay_active_compounds` - HTS data\n- `OpenTargets_get_associated_drugs_by_target_ensemblID` - Known drugs (`size` REQUIRED)\n- `ChEMBL_search_mechanisms` - Drug mechanisms\n- `DGIdb_get_gene_info` - Drug-gene interactions\n\n### Phase 4: Clinical Precedent (0-15 pts)\n\nAssess clinical validation from approved drugs and clinical trials.\n\n**Key tools**:\n- `FDA_get_mechanism_of_action_by_drug_name` \u002F `FDA_get_indications_by_drug_name`\n- `drugbank_get_targets_by_drug_name_or_drugbank_id` (ALL params required: `query`, `case_sensitive`, `exact_match`, `limit`)\n- `search_clinical_trials` (`query_term` REQUIRED)\n- `OpenTargets_get_drug_warnings_by_chemblId` \u002F `OpenTargets_get_drug_adverse_events_by_chemblId`\n\n### Phase 5: Safety (0-20 pts)\n\nIdentify safety risks from expression, genetics, and known adverse events.\n\n**Key tools**:\n- `OpenTargets_get_target_safety_profile_by_ensemblID` - Safety liabilities\n- `GTEx_get_median_gene_expression` - Tissue expression (`operation=\"median\"` REQUIRED)\n- `HPA_search_genes_by_query` \u002F `HPA_get_comprehensive_gene_details_by_ensembl_id`\n- `OpenTargets_get_biological_mouse_models_by_ensemblID` - KO phenotypes\n- `FDA_get_adverse_reactions_by_drug_name` \u002F `FDA_get_boxed_warning_info_by_drug_name`\n- `OpenTargets_get_target_homologues_by_ensemblID` - Paralog risks\n\n**Critical tissues to check**: heart, liver, kidney, brain, bone marrow.\n\n### Phase 6: Pathway Context\n\nUnderstand the target's role in biological networks and disease pathways.\n\n**Key tools**:\n- `Reactome_map_uniprot_to_pathways` (param: `id`, NOT `uniprot_id`)\n- `STRING_get_protein_interactions` (param: `protein_ids` as array, `species=9606`)\n- `intact_get_interactions` - Experimental PPI\n- `OpenTargets_get_target_gene_ontology_by_ensemblID` - GO terms\n- `STRING_functional_enrichment` - Enrichment analysis\n\n**Assess**: pathway redundancy, compensation risk, feedback loops.\n\n### Phase 7: Validation Evidence (0-10 pts)\n\nAssess existing functional validation data.\n\n**Key tools**:\n- `DepMap_get_gene_dependencies` - Essentiality (score \u003C -0.5 = essential)\n- `PubMed_search_articles` - Search for CRISPR\u002FsiRNA\u002Fknockout studies\n- `CTD_get_gene_diseases` - Gene-disease associations\n\n### Phase 8: Structural Insights\n\nLeverage structural biology for druggability and mechanism understanding.\n\n**Key tools**:\n- `UniProt_get_entry_by_accession` - Extract PDB cross-references\n- `get_protein_metadata_by_pdb_id` \u002F `pdbe_get_entry_summary` \u002F `pdbe_get_entry_quality`\n- `alphafold_get_prediction` \u002F `alphafold_get_summary` - pLDDT confidence\n- `ProteinsPlus_predict_binding_sites` - Druggable pockets\n- `InterPro_get_protein_domains` \u002F `InterPro_get_domain_details` - Domain architecture\n\n### Phase 9: Literature Deep Dive\n\nComprehensive collision-aware literature analysis.\n\n**Steps**:\n1. **Collision detection**: Search `\"{gene_symbol}\"[Title]` in PubMed; if >20% off-topic, add filters (AND protein OR gene OR receptor)\n2. **Publication metrics**: Total count, 5-year trend, drug-focused subset\n3. **Key reviews**: `review[pt]` filter in PubMed\n4. **Citation metrics**: `openalex_search_works` for impact data\n5. **Broader coverage**: `EuropePMC_search_articles`\n\n### Phase 10: Validation Roadmap (Synthesis)\n\nSynthesize all phases into actionable output:\n1. **Target Validation Score** (0-100) with component breakdown\n2. **Priority Tier** (1-4) assignment\n3. **GO\u002FNO-GO Recommendation** with justification\n4. **Recommended Validation Experiments**\n5. **Tool Compounds for Testing**\n6. **Biomarker Strategy**\n7. **Key Risks and Mitigations**\n\n---\n\n## Report Output\n\nCreate file: `[TARGET]_[DISEASE]_validation_report.md`\n\nUse the full template from **REPORT_TEMPLATE.md**. Key sections:\n- Executive Summary (score, tier, recommendation, key findings, critical risks)\n- Validation Scorecard (all 12 sub-scores with evidence)\n- Sections 1-14 covering each phase\n- Completeness Checklist (mandatory before finalizing)\n\nComplete the **Completeness Checklist** (in REPORT_TEMPLATE.md) before finalizing to verify all phases were covered, all scores justified, and negative results documented.\n","# Drug Target Validation Pipeline\n\nValidate drug target hypotheses using multi-dimensional computational evidence before committing to wet-lab work. Produces a quantitative Target Validation Score (0-100) with priority tier classification and GO\u002FNO-GO recommendation.\n\n## Reasoning Before Searching\n\nA valid drug target must pass 4 gates in order. Failing an early gate makes later gates irrelevant:\n\n1. **Genetic evidence linking it to disease**: Does human genetic data (GWAS, rare variant studies, Mendelian genetics) support this target's role? Genetic evidence is the strongest predictor of clinical success. Use OpenTargets and GWAS catalog before anything else. If no genetic link exists, the hypothesis is speculative — document this clearly.\n2. **Druggability**: Can a molecule reach and modulate the target? Check structure availability (PDB, AlphaFold), binding pocket prediction (ProteinsPlus), target class (kinase, GPCR, nuclear receptor = favorable; transcription factor, scaffold protein = difficult), and existing chemical probes.\n3. **Safety — essentiality in normal tissue**: Is the target expressed in critical tissues (heart, liver, bone marrow)? Is knockout lethal in mice? High expression in essential tissue or lethality in mouse models is a strong safety red flag even before any clinical data.\n4. **Competitive landscape**: Are other drugs already approved or in late-stage trials for this target? If so, the bar is differentiation, not first-in-class. Check ChEMBL, DrugBank, and ClinicalTrials.gov early.\n\nDo not proceed to Phase 3 (Chemical Matter) before completing Phase 1 (Disease Association). Gate 1 failures should prompt a NO-GO or pivot recommendation.\n\n**LOOK UP DON'T GUESS**: Never assume a target is druggable based on its protein family alone, never assume expression is low in a tissue without checking GTEx or HPA, never assume no competitors without searching ClinicalTrials.gov.\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## Key Principles\n\n1. **Report-first** - Create report file FIRST, then populate progressively\n2. **Target disambiguation FIRST** - Resolve all identifiers before analysis\n3. **Evidence grading** - Grade all evidence as T1 (experimental) to T4 (computational)\n4. **Disease-specific** - Tailor analysis to disease context when provided\n5. **Modality-aware** - Consider small molecule vs biologics tractability\n6. **Safety-first** - Prominently flag safety concerns early\n7. **Quantitative scoring** - Every dimension scored numerically (0-100 composite)\n8. **Negative results documented** - \"No data\" is data; empty sections are failures\n9. **Source references** - Every statement must cite tool\u002Fdatabase\n10. **English-first queries** - Always use English terms in tool calls; respond in user's language\n\n## When to Use\n\nApply when users ask about:\n- \"Is [target] a good drug target for [disease]?\"\n- Target validation, druggability assessment, or target prioritization\n- Safety risks of modulating a target\n- Chemical starting points for target validation\n- GO\u002FNO-GO recommendation for a target\n\n**Not for** (use other skills): general target biology (`tooluniverse-target-research`), drug compound profiling (`tooluniverse-drug-research`), variant interpretation (`tooluniverse-variant-interpretation`), disease research (`tooluniverse-disease-research`).\n\n## Input Parameters\n\n| Parameter | Required | Description | Example |\n|-----------|----------|-------------|---------|\n| **target** | Yes | Gene symbol, protein name, or UniProt ID | `EGFR`, `P00533` |\n| **disease** | No | Disease\u002Findication for context | `Non-small cell lung cancer` |\n| **modality** | No | Preferred therapeutic modality | `small molecule`, `antibody`, `PROTAC` |\n\n## Reference Files\n\n- **SCORING_CRITERIA.md** - Detailed scoring matrices, evidence grading, priority tiers, score calculation\n- **REPORT_TEMPLATE.md** - Full report template, completeness checklist, section format examples\n- **TOOL_REFERENCE.md** - Verified tool parameters, known corrections, fallback chains, modality-specific guidance, phase-by-phase tool lists\n- **QUICK_START.md** - Quick start guide\n\n---\n\n## Scoring Overview\n\n**Total: 0-100 points** across 5 dimensions (details in SCORING_CRITERIA.md):\n\n| Dimension | Max | Sub-dimensions |\n|-----------|-----|----------------|\n| Disease Association | 30 | Genetic (10) + Literature (10) + Pathway (10) |\n| Druggability | 25 | Structure (10) + Chemical matter (10) + Target class (5) |\n| Safety Profile | 20 | Expression (5) + Genetic validation (10) + ADRs (5) |\n| Clinical Precedent | 15 | Based on highest clinical stage achieved |\n| Validation Evidence | 10 | Functional studies (5) + Disease models (5) |\n\n**Priority Tiers**: 80-100 = Tier 1 (GO) | 60-79 = Tier 2 (CONDITIONAL GO) | 40-59 = Tier 3 (CAUTION) | 0-39 = Tier 4 (NO-GO)\n\n**Evidence Grades**: T1 (clinical proof) > T2 (functional studies) > T3 (associations) > T4 (predictions)\n\n---\n\n## Pipeline Phases\n\n### Phase 0: Target Disambiguation (ALWAYS FIRST)\n\nResolve target to ALL identifiers before any analysis.\n\n**Steps**:\n1. `MyGene_query_genes` - Get initial IDs (Ensembl, UniProt, Entrez)\n2. `ensembl_lookup_gene` - Get versioned Ensembl ID (species=\"homo_sapiens\" REQUIRED)\n3. `ensembl_get_xrefs` - Cross-references (HGNC, etc.)\n4. `OpenTargets_get_target_id_description_by_name` - Verify OT target\n5. `ChEMBL_search_targets` - Get ChEMBL target ID\n6. `UniProt_get_function_by_accession` - Function summary (returns list of strings)\n7. `UniProt_get_alternative_names_by_accession` - Collision detection\n\n**Output**: Table of verified identifiers (Gene Symbol, Ensembl, UniProt, Entrez, ChEMBL, HGNC) plus protein function and target class.\n\n### Phase 1: Disease Association (0-30 pts)\n\nQuantify target-disease association from genetic, literature, and pathway evidence.\n\n**Key tools**:\n- `OpenTargets_get_diseases_phenotypes_by_target_ensembl` - Disease associations\n- `OpenTargets_target_disease_evidence` - Detailed evidence (needs `efoId` + `ensemblId`)\n- `OpenTargets_get_evidence_by_datasource` - Evidence by data source\n- `gwas_get_snps_for_gene` \u002F `gwas_search_studies` - GWAS evidence\n- `gnomad_get_gene_constraints` - Genetic constraint (pLI, LOEUF)\n- `PubMed_search_articles` - Literature (returns plain list of dicts)\n- `OpenTargets_get_publications_by_target_ensemblID` - OT publications (uses `entityId`)\n\n### Phase 2: Druggability (0-25 pts)\n\nAssess whether the target is amenable to therapeutic intervention.\n\n**Key tools**:\n- `OpenTargets_get_target_tractability_by_ensemblID` - Tractability (SM, AB, PR, OC)\n- `OpenTargets_get_target_classes_by_ensemblID` - Target classification\n- `Pharos_get_target` - TDL: Tclin > Tchem > Tbio > Tdark\n- `DGIdb_get_gene_druggability` - Druggability categories\n- `alphafold_get_prediction` (param: `qualifier`) \u002F `alphafold_get_summary`\n- `ProteinsPlus_predict_binding_sites` - Pocket detection\n- `OpenTargets_get_chemical_probes_by_target_ensemblID` - Chemical probes\n- `OpenTargets_get_target_enabling_packages_by_ensemblID` - TEPs\n- `TCDB_get_transporter` - For SLC\u002FABC transporter targets: TC classification, family, PDB structures (param: `uniprot_accession`)\n- `TCDB_search_by_substrate` - Find transporters by substrate (param: `substrate_name`)\n\n### Phase 3: Chemical Matter (feeds Phase 2 scoring)\n\nIdentify existing chemical starting points for target validation.\n\n**Key tools**:\n- `ChEMBL_search_targets` + `ChEMBL_get_target_activities` - Bioactivity data (note: `target_chembl_id__exact` with double underscore)\n- `BindingDB_get_ligands_by_uniprot` - Binding data (affinity in nM)\n- `PubChem_search_assays_by_target_gene` + `PubChem_get_assay_active_compounds` - HTS data\n- `OpenTargets_get_associated_drugs_by_target_ensemblID` - Known drugs (`size` REQUIRED)\n- `ChEMBL_search_mechanisms` - Drug mechanisms\n- `DGIdb_get_gene_info` - Drug-gene interactions\n\n### Phase 4: Clinical Precedent (0-15 pts)\n\nAssess clinical validation from approved drugs and clinical trials.\n\n**Key tools**:\n- `FDA_get_mechanism_of_action_by_drug_name` \u002F `FDA_get_indications_by_drug_name`\n- `drugbank_get_targets_by_drug_name_or_drugbank_id` (ALL params required: `query`, `case_sensitive`, `exact_match`, `limit`)\n- `search_clinical_trials` (`query_term` REQUIRED)\n- `OpenTargets_get_drug_warnings_by_chemblId` \u002F `OpenTargets_get_drug_adverse_events_by_chemblId`\n\n### Phase 5: Safety (0-20 pts)\n\nIdentify safety risks from expression, genetics, and known adverse events.\n\n**Key tools**:\n- `OpenTargets_get_target_safety_profile_by_ensemblID` - Safety liabilities\n- `GTEx_get_median_gene_expression` - Tissue expression (`operation=\"median\"` REQUIRED)\n- `HPA_search_genes_by_query` \u002F `HPA_get_comprehensive_gene_details_by_ensembl_id`\n- `OpenTargets_get_biological_mouse_models_by_ensemblID` - KO phenotypes\n- `FDA_get_adverse_reactions_by_drug_name` \u002F `FDA_get_boxed_warning_info_by_drug_name`\n- `OpenTargets_get_target_homologues_by_ensemblID` - Paralog risks\n\n**Critical tissues to check**: heart, liver, kidney, brain, bone marrow.\n\n### Phase 6: Pathway Context\n\nUnderstand the target's role in biological networks and disease pathways.\n\n**Key tools**:\n- `Reactome_map_uniprot_to_pathways` (param: `id`, NOT `uniprot_id`)\n- `STRING_get_protein_interactions` (param: `protein_ids` as array, `species=9606`)\n- `intact_get_interactions` - Experimental PPI\n- `OpenTargets_get_target_gene_ontology_by_ensemblID` - GO terms\n- `STRING_functional_enrichment` - Enrichment analysis\n\n**Assess**: pathway redundancy, compensation risk, feedback loops.\n\n### Phase 7: Validation Evidence (0-10 pts)\n\nAssess existing functional validation data.\n\n**Key tools**:\n- `DepMap_get_gene_dependencies` - Essentiality (score \u003C -0.5 = essential)\n- `PubMed_search_articles` - Search for CRISPR\u002FsiRNA\u002Fknockout studies\n- `CTD_get_gene_diseases` - Gene-disease associations\n\n### Phase 8: Structural Insights\n\nLeverage structural biology for druggability and mechanism understanding.\n\n**Key tools**:\n- `UniProt_get_entry_by_accession` - Extract PDB cross-references\n- `get_protein_metadata_by_pdb_id` \u002F `pdbe_get_entry_summary` \u002F `pdbe_get_entry_quality`\n- `alphafold_get_prediction` \u002F `alphafold_get_summary` - pLDDT confidence\n- `ProteinsPlus_predict_binding_sites` - Druggable pockets\n- `InterPro_get_protein_domains` \u002F `InterPro_get_domain_details` - Domain architecture\n\n### Phase 9: Literature Deep Dive\n\nComprehensive collision-aware literature analysis.\n\n**Steps**:\n1. **Collision detection**: Search `\"{gene_symbol}\"[Title]` in PubMed; if >20% off-topic, add filters (AND protein OR gene OR receptor)\n2. **Publication metrics**: Total count, 5-year trend, drug-focused subset\n3. **Key reviews**: `review[pt]` filter in PubMed\n4. **Citation metrics**: `openalex_search_works` for impact data\n5. **Broader coverage**: `EuropePMC_search_articles`\n\n### Phase 10: Validation Roadmap (Synthesis)\n\nSynthesize all phases into actionable output:\n1. **Target Validation Score** (0-100) with component breakdown\n2. **Priority Tier** (1-4) assignment\n3. **GO\u002FNO-GO Recommendation** with justification\n4. **Recommended Validation Experiments**\n5. **Tool Compounds for Testing**\n6. **Biomarker Strategy**\n7. **Key Risks and Mitigations**\n\n---\n\n## Report Output\n\nCreate file: `[TARGET]_[DISEASE]_validation_report.md`\n\nUse the full template from **REPORT_TEMPLATE.md**. Key sections:\n- Executive Summary (score, tier, recommendation, key findings, critical risks)\n- Validation Scorecard (all 12 sub-scores with evidence)\n- Sections 1-14 covering each phase\n- Completeness Checklist (mandatory before finalizing)\n\nComplete the **Completeness Checklist** (in REPORT_TEMPLATE.md) before finalizing to verify all phases were covered, all scores justified, and negative results documented.\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Flibrary\u002Fskills\u002Ftooluniverse-drug-target-validation","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":56,"prompt":66,"zipAvailable":67},[57,60,63],{"tool":58,"command":59},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-drug-target-validation",{"tool":61,"command":62},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-drug-target-validation",{"tool":64,"command":65},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-drug-target-validation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-drug-target-validation\u002FSKILL.md",true,[69,75,79,83,89],{"path":70,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":73,"sourceHtmlUrl":74},"QUICK_START.md","REFERENCE","参考文档",3984,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-drug-target-validation\u002FQUICK_START.md",{"path":76,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":77,"sourceHtmlUrl":78},"REPORT_TEMPLATE.md",7662,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-drug-target-validation\u002FREPORT_TEMPLATE.md",{"path":80,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":81,"sourceHtmlUrl":82},"SCORING_CRITERIA.md",6481,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-drug-target-validation\u002FSCORING_CRITERIA.md",{"path":84,"resourceType":85,"resourceTypeDesc":86,"sizeBytes":87,"sourceHtmlUrl":88},"test_skill.py","SCRIPT","脚本",30039,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-drug-target-validation\u002Ftest_skill.py",{"path":90,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":91,"sourceHtmlUrl":92},"TOOL_REFERENCE.md",9287,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-drug-target-validation\u002FTOOL_REFERENCE.md",[94,115,146,173,187,203],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":44},"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",[],[101,102,103,104,105,106,107,108,109,37,110,111,112,113,114],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","context","repo","injection","execution","file",{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":126,"publishedAt":44},"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",[121],{"categoryNo":122,"categoryName":123,"taxonomyType":124,"taxonomyTypeDesc":125},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[127,128,129,130,131,132,133,134,135,136,137,138,139,140,37,141,142,143,144,145],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":147,"name":148,"nameZh":6,"description":149,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":150,"categories":151,"keywords":158,"publishedAt":44},"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",[152,155],{"categoryNo":153,"categoryName":154,"taxonomyType":124,"taxonomyTypeDesc":125},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":156,"categoryName":157,"taxonomyType":124,"taxonomyTypeDesc":125},"01JBSEEDCAT000000000000008","测试与质量",[159,160,161,162,163,164,165,166,167,168,128,169,170,171,172],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":174,"name":175,"nameZh":6,"description":176,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":177,"categories":178,"keywords":179,"publishedAt":44},"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",[],[175,180,181,182,183,184,185,186],"setup","report","project","installation","project setup","issues","state",{"skillNo":188,"name":189,"nameZh":6,"description":190,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":191,"categories":192,"keywords":194,"publishedAt":44},"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",[193],{"categoryNo":122,"categoryName":123,"taxonomyType":124,"taxonomyTypeDesc":125},[189,195,106,196,197,198,37,199,200,201,202],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":204,"name":180,"nameZh":6,"description":205,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":206,"categories":207,"keywords":208,"publishedAt":44},"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",[],[180,182,143,209,184,210],"files","interactive"]