[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DAVWZW00FD57CG2T0W558Y":3,"skill-same:01M6DAVWZW00FD57CG2T0W558Y":79},{"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":28,"linkOnly":29,"markdownContent":30,"markdownBody":31,"frontMatter":32,"refName":33,"commitSha":34,"skillDirectory":35,"forksCount":14,"repositoryHtmlUrl":36,"repositoryHomepageUrl":6,"ownerHtmlUrl":37,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":38,"install":39,"resources":52},"01M6DAVWZW00FD57CG2T0W558Y","tooluniverse-precision-oncology",null,"Provide actionable treatment recommendations for cancer patients based on molecular profile. Interprets tumor mutations, identifies FDA-approved therapies, finds resistance mechanisms, matches clinical trials. Use when oncologist asks about treatment options for specific mutations (EGFR, KRAS, BRAF, etc.), therapy resistance, or clinical trial eligibility.","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-oncology\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27],"tooluniverse precision oncology","profile","use","fda","mutations","options","molecular","recommendations","clinical","2026-11-10 10:12:30",false,"---\nname: tooluniverse-precision-oncology\ndescription: Provide actionable treatment recommendations for cancer patients based on molecular profile. Interprets tumor mutations, identifies FDA-approved therapies, finds resistance mechanisms, matches clinical trials. Use when oncologist asks about treatment options for specific mutations (EGFR, KRAS, BRAF, etc.), therapy resistance, or clinical trial eligibility.\n---\n\n# Precision Oncology Treatment Advisor\n\nProvide actionable treatment recommendations for cancer patients based on their molecular profile using CIViC, ClinVar, OpenTargets, ClinicalTrials.gov, and structure-based analysis.\n\n## Domain Reasoning\n\nTreatment selection follows a strict evidence hierarchy: FDA-approved for this specific mutation in this cancer type ranks highest, followed by approval for this mutation in any cancer (tumor-agnostic), then active clinical trials, and finally off-label use. Skipping this hierarchy to recommend off-label therapies when an approved option exists is a clinical error. Always check current NCCN guidelines and recent literature, as approvals change rapidly — a drug that was investigational last year may now be first-line.\n\nWhen looking up treatment for a specific mutation, search CIViC and OncoKB FIRST, not PubMed. These databases have curated evidence levels. PubMed is for when curated databases don't have the answer.\n\n## Treatment Selection Reasoning\n\n**Biomarker-to-drug logic** — When a biomarker is identified, the first-line targeted therapy follows established mappings. Always verify current approval status via OncoKB\u002FCIViC, but use this as a starting framework:\n- **NSCLC**: EGFR exon 19 del \u002F L858R → osimertinib (1L); ALK fusion → alectinib\u002Florlatinib; ROS1 fusion → crizotinib\u002Fentrectinib; KRAS G12C → sotorasib\u002Fadagrasib; MET exon 14 skip → capmatinib\u002Ftepotinib; RET fusion → selpercatinib; BRAF V600E → dabrafenib+trametinib; NTRK fusion → larotrectinib\u002Fentrectinib (tumor-agnostic)\n- **Breast**: HER2+ → trastuzumab+pertuzumab (1L), T-DXd (2L); HR+\u002FHER2- → CDK4\u002F6i (palbociclib\u002Fribociclib) + AI; BRCA1\u002F2 mut → olaparib\u002Ftalazoparib; PIK3CA mut → alpelisib+fulvestrant\n- **Colorectal**: BRAF V600E → encorafenib+cetuximab; MSI-H\u002FdMMR → pembrolizumab (tumor-agnostic); KRAS\u002FNRAS wild-type → cetuximab\u002Fpanitumumab (anti-EGFR)\n- **Melanoma**: BRAF V600E\u002FK → dabrafenib+trametinib or encorafenib+binimetinib; wild-type → immunotherapy (nivolumab+ipilimumab)\n- **Tumor-agnostic**: MSI-H\u002FdMMR → pembrolizumab; NTRK fusion → larotrectinib; TMB-H (>=10 mut\u002FMb) → pembrolizumab; RET fusion → selpercatinib\n\n**Resistance mechanism reasoning** — When a patient progresses on targeted therapy, distinguish primary resistance (never responded — check if the mutation was truly the driver, or if co-mutations like TP53\u002FRB1 abrogate response) from acquired resistance (responded then progressed — on-target mutations or bypass activation). Common patterns:\n- **EGFR TKIs**: 1st\u002F2nd-gen resistance → T790M (50-60%); osimertinib resistance → C797S (10-25%), MET amp (15-20%), HER2 amp, histologic transformation (SCLC ~5%)\n- **ALK TKIs**: crizotinib resistance → ALK secondary mutations (L1196M, G1269A); alectinib resistance → G1202R (solvent front); lorlatinib resistance → compound mutations\n- **BRAF inhibitors**: MAPK reactivation (MEK mutations, BRAF amplification, NRAS mutations), PI3K\u002FAKT bypass\n- **Anti-HER2**: HER2 truncation (p95HER2), PIK3CA activation, HER3 upregulation\n- **Immunotherapy (anti-PD1)**: B2M loss (MHC-I loss), JAK1\u002F2 loss-of-function (IFN-gamma signaling escape), WNT\u002Fbeta-catenin activation (T-cell exclusion)\nFor resistance workup: query `civic_search_evidence_items` with the drug name + \"resistance\", then `PubMed_search_articles` for recent mechanisms.\n\n## LOOK UP DON'T GUESS\n\n- FDA approval status for a mutation-drug pair: query `OncoKB_annotate_variant` and `civic_search_variants`; never assume approval status from memory.\n- Active clinical trials: search `search_clinical_trials` with the specific condition and mutation; do not cite trials from memory.\n- Resistance mechanisms for specific drugs: query `civic_search_evidence_items` and `PubMed_search_articles`; do not assume resistance pathways.\n- Variant frequency in TCGA: retrieve from `GDC_get_mutation_frequency` or `cBioPortal_get_mutations`; do not estimate prevalence.\n\n---\n\n**KEY PRINCIPLES**:\n1. **Report-first** - Create report file FIRST, update progressively\n2. **Evidence-graded** - Every recommendation has evidence level\n3. **Actionable output** - Prioritized treatment options, not data dumps\n4. **Clinical focus** - Answer \"what should we do?\" not \"what exists?\"\n5. **English-first queries** - Always use English terms in tool calls (mutations, drug names, cancer types), even if the user writes in another language. Only try original-language terms as a fallback. Respond in the user's language\n\n---\n\n## When to Use\n\n- \"Patient has [cancer] with [mutation] - what treatments?\"\n- \"What are options for EGFR-mutant lung cancer?\"\n- \"Patient failed [drug], what's next?\"\n- \"Clinical trials for KRAS G12C?\"\n- \"Why isn't [drug] working anymore?\"\n\n---\n\n## Phase 0: Tool Verification\n\n| Tool | WRONG | CORRECT |\n|------|-------|---------|\n| `civic_get_variant` | `variant_name` | `variant_id` (numeric, e.g., 4170) |\n| `civic_get_evidence_item` | `variant_id` | `id` (numeric) |\n| `OpenTargets_*` | `ensemblID` | `ensemblId` (camelCase) |\n| `search_clinical_trials` | `disease` | `condition` |\n\n---\n\n## Workflow Overview\n\n```\nInput: Cancer type + Molecular profile (mutations, fusions, amplifications)\n\nPhase 1: Profile Validation -> Resolve gene IDs (Ensembl, UniProt, ChEMBL)\nPhase 2: Variant Interpretation -> CIViC, ClinVar, COSMIC, GDC\u002FTCGA, DepMap, OncoKB, cBioPortal, HPA\nPhase 2.5: Tumor Expression -> CELLxGENE cell-type expression, ChIPAtlas regulatory context\nPhase 3: Treatment Options -> OpenTargets + DailyMed (approved), ChEMBL (off-label)\nPhase 3.5: Pathway & Network -> KEGG\u002FReactome pathways, IntAct interactions\nPhase 4: Resistance Analysis -> CIViC + PubMed + NvidiaNIM structure analysis\nPhase 5: Clinical Trials -> ClinicalTrials.gov search + eligibility\nPhase 5.5: Literature -> PubMed, BioRxiv\u002FMedRxiv preprints, OpenAlex citations\nPhase 6: Report Synthesis -> Executive summary + prioritized recommendations\n```\n\n---\n\n## Key Tools by Phase\n\n### Phase 1: Profile Validation\n- `MyGene_query_genes` - Resolve gene to Ensembl ID\n- `UniProt_search` - Get UniProt accession\n- `ChEMBL_search_targets` - Get ChEMBL target ID\n\n### Phase 2: Variant Interpretation\n- `civic_search_variants` \u002F `civic_get_variant` - CIViC evidence\n- `COSMIC_get_mutations_by_gene` \u002F `COSMIC_search_mutations` - Somatic mutations\n- `GDC_get_mutation_frequency` \u002F `GDC_get_ssm_by_gene` - TCGA patient data\n- `GDC_get_gene_expression` \u002F `GDC_get_cnv_data` - Expression and CNV\n- `GDC_get_survival` - Kaplan-Meier survival data by project and optional gene mutation filter\n- `GDC_get_clinical_data` - TCGA clinical metadata (stage, vital status, treatment, demographics)\n- `Progenetix_cnv_search` - Copy number variation biosamples by genomic region and cancer type (NCIt code)\n- `DepMap_get_gene_dependencies` \u002F `PharmacoDB_get_experiments` - Target essentiality\n- `OncoKB_annotate_variant` \u002F `OncoKB_get_gene_info` - Actionability\n- `cBioPortal_get_mutations` \u002F `cBioPortal_get_cancer_studies` - Cross-study data\n- `HPA_search_genes_by_query` \u002F `HPA_get_comparative_expression_by_gene_and_cellline` - Expression\n\n### Phase 2.5: Tumor Expression\n- `CELLxGENE_get_expression_data` \u002F `CELLxGENE_get_cell_metadata` - Cell-type expression\n\n### Phase 3: Treatment Options\n- `OpenTargets_get_associated_drugs_by_target_ensemblID` - Approved drugs (param: `ensemblId`, camelCase)\n- `DGIdb_get_drug_gene_interactions` - Drug-gene interactions (param: `genes` as array, e.g., `[\"EGFR\"]`). Comprehensive; covers inhibitors, antibodies, and investigational agents.\n- `DailyMed_search_spls` - FDA label details\n- `ChEMBL_get_drug_mechanisms` - Drug mechanism\n\n### Phase 3.5: Pathway & Network\n- `kegg_find_genes` \u002F `kegg_get_gene_info` - KEGG pathways\n- `reactome_disease_target_score` - Reactome disease relevance\n- `intact_get_interaction_network` - Protein interactions\n\n### Phase 4: Resistance Analysis\n- `civic_search_evidence_items` - Search by known resistance mutations individually (e.g., `molecular_profile=\"EGFR C797S\"`, `molecular_profile=\"MET Amplification\"`). The `significance` field in results indicates Resistance\u002FSensitivity — filter on it after retrieval.\n- `PubMed_search_articles` - Resistance literature (e.g., \"osimertinib resistance C797S combination therapy\")\n- `alphafold_get_prediction` \u002F `get_diffdock_info` - Structure-based analysis (AlphaFold for structure, DiffDock for docking)\n\n### Phase 5: Clinical Trials\n- `search_clinical_trials` - Find trials (param: `condition`, NOT `disease`)\n- `get_clinical_trial_eligibility_criteria` - Eligibility details\n\n### Phase 5.5: Safety & Pharmacogenomics\n- `FAERS_search_adverse_event_reports` - Real-world adverse events (param: `medicinalproduct`). Check for serious AEs, death rates, common toxicities.\n- `FAERS_count_death_related_by_drug` - Mortality signal for a drug\n- `FDA_get_warnings_and_cautions_by_drug_name` - FDA label safety info\n- `CPIC_list_guidelines` - Check for relevant PGx guidelines (e.g., DPYD for fluoropyrimidines in chemo regimens, UGT1A1 for irinotecan). No CPIC guidelines exist for EGFR TKIs.\n- `fda_pharmacogenomic_biomarkers` - FDA-labeled PGx biomarkers for the drug\n\n> **OncoKB demo mode**: Without `ONCOKB_API_TOKEN` env var, OncoKB only covers BRAF, TP53, ROS1. For other genes (EGFR, KRAS, ALK, etc.), set the API key or use CIViC as the primary evidence source.\n\n### Phase 6: Literature\n- `PubMed_search_articles` - Published evidence (use `limit`, `mindate`, `maxdate` for date filtering)\n- `BioRxiv_list_recent_preprints` \u002F `MedRxiv_get_preprint` - Preprints (flag as NOT peer-reviewed)\n- `openalex_search_works` - Citation analysis\n\n---\n\n## Cross-Skill References\n\nFor CYP interaction with cancer drugs, run: `python3 skills\u002Ftooluniverse-drug-drug-interaction\u002Fscripts\u002Fpharmacology_ref.py --type cyp_substrate --drug drugname`\n\n---\n\n## References\n\n- [TOOLS_REFERENCE.md](TOOLS_REFERENCE.md) - Complete tool documentation with parameters and examples\n- [API_USAGE_PATTERNS.md](API_USAGE_PATTERNS.md) - Detailed code examples for each phase\n- [TREATMENT_ALGORITHMS.md](TREATMENT_ALGORITHMS.md) - Evidence grading, treatment prioritization, cancer type mappings, DepMap interpretation\n- [REPORT_TEMPLATE.md](REPORT_TEMPLATE.md) - Report template with output tables\n- [EXAMPLES.md](EXAMPLES.md) - Worked examples (EGFR NSCLC, T790M resistance, KRAS G12C, no actionable mutations)\n- [CHECKLIST.md](CHECKLIST.md) - Quality and completeness checklist\n","# Precision Oncology Treatment Advisor\n\nProvide actionable treatment recommendations for cancer patients based on their molecular profile using CIViC, ClinVar, OpenTargets, ClinicalTrials.gov, and structure-based analysis.\n\n## Domain Reasoning\n\nTreatment selection follows a strict evidence hierarchy: FDA-approved for this specific mutation in this cancer type ranks highest, followed by approval for this mutation in any cancer (tumor-agnostic), then active clinical trials, and finally off-label use. Skipping this hierarchy to recommend off-label therapies when an approved option exists is a clinical error. Always check current NCCN guidelines and recent literature, as approvals change rapidly — a drug that was investigational last year may now be first-line.\n\nWhen looking up treatment for a specific mutation, search CIViC and OncoKB FIRST, not PubMed. These databases have curated evidence levels. PubMed is for when curated databases don't have the answer.\n\n## Treatment Selection Reasoning\n\n**Biomarker-to-drug logic** — When a biomarker is identified, the first-line targeted therapy follows established mappings. Always verify current approval status via OncoKB\u002FCIViC, but use this as a starting framework:\n- **NSCLC**: EGFR exon 19 del \u002F L858R → osimertinib (1L); ALK fusion → alectinib\u002Florlatinib; ROS1 fusion → crizotinib\u002Fentrectinib; KRAS G12C → sotorasib\u002Fadagrasib; MET exon 14 skip → capmatinib\u002Ftepotinib; RET fusion → selpercatinib; BRAF V600E → dabrafenib+trametinib; NTRK fusion → larotrectinib\u002Fentrectinib (tumor-agnostic)\n- **Breast**: HER2+ → trastuzumab+pertuzumab (1L), T-DXd (2L); HR+\u002FHER2- → CDK4\u002F6i (palbociclib\u002Fribociclib) + AI; BRCA1\u002F2 mut → olaparib\u002Ftalazoparib; PIK3CA mut → alpelisib+fulvestrant\n- **Colorectal**: BRAF V600E → encorafenib+cetuximab; MSI-H\u002FdMMR → pembrolizumab (tumor-agnostic); KRAS\u002FNRAS wild-type → cetuximab\u002Fpanitumumab (anti-EGFR)\n- **Melanoma**: BRAF V600E\u002FK → dabrafenib+trametinib or encorafenib+binimetinib; wild-type → immunotherapy (nivolumab+ipilimumab)\n- **Tumor-agnostic**: MSI-H\u002FdMMR → pembrolizumab; NTRK fusion → larotrectinib; TMB-H (>=10 mut\u002FMb) → pembrolizumab; RET fusion → selpercatinib\n\n**Resistance mechanism reasoning** — When a patient progresses on targeted therapy, distinguish primary resistance (never responded — check if the mutation was truly the driver, or if co-mutations like TP53\u002FRB1 abrogate response) from acquired resistance (responded then progressed — on-target mutations or bypass activation). Common patterns:\n- **EGFR TKIs**: 1st\u002F2nd-gen resistance → T790M (50-60%); osimertinib resistance → C797S (10-25%), MET amp (15-20%), HER2 amp, histologic transformation (SCLC ~5%)\n- **ALK TKIs**: crizotinib resistance → ALK secondary mutations (L1196M, G1269A); alectinib resistance → G1202R (solvent front); lorlatinib resistance → compound mutations\n- **BRAF inhibitors**: MAPK reactivation (MEK mutations, BRAF amplification, NRAS mutations), PI3K\u002FAKT bypass\n- **Anti-HER2**: HER2 truncation (p95HER2), PIK3CA activation, HER3 upregulation\n- **Immunotherapy (anti-PD1)**: B2M loss (MHC-I loss), JAK1\u002F2 loss-of-function (IFN-gamma signaling escape), WNT\u002Fbeta-catenin activation (T-cell exclusion)\nFor resistance workup: query `civic_search_evidence_items` with the drug name + \"resistance\", then `PubMed_search_articles` for recent mechanisms.\n\n## LOOK UP DON'T GUESS\n\n- FDA approval status for a mutation-drug pair: query `OncoKB_annotate_variant` and `civic_search_variants`; never assume approval status from memory.\n- Active clinical trials: search `search_clinical_trials` with the specific condition and mutation; do not cite trials from memory.\n- Resistance mechanisms for specific drugs: query `civic_search_evidence_items` and `PubMed_search_articles`; do not assume resistance pathways.\n- Variant frequency in TCGA: retrieve from `GDC_get_mutation_frequency` or `cBioPortal_get_mutations`; do not estimate prevalence.\n\n---\n\n**KEY PRINCIPLES**:\n1. **Report-first** - Create report file FIRST, update progressively\n2. **Evidence-graded** - Every recommendation has evidence level\n3. **Actionable output** - Prioritized treatment options, not data dumps\n4. **Clinical focus** - Answer \"what should we do?\" not \"what exists?\"\n5. **English-first queries** - Always use English terms in tool calls (mutations, drug names, cancer types), even if the user writes in another language. Only try original-language terms as a fallback. Respond in the user's language\n\n---\n\n## When to Use\n\n- \"Patient has [cancer] with [mutation] - what treatments?\"\n- \"What are options for EGFR-mutant lung cancer?\"\n- \"Patient failed [drug], what's next?\"\n- \"Clinical trials for KRAS G12C?\"\n- \"Why isn't [drug] working anymore?\"\n\n---\n\n## Phase 0: Tool Verification\n\n| Tool | WRONG | CORRECT |\n|------|-------|---------|\n| `civic_get_variant` | `variant_name` | `variant_id` (numeric, e.g., 4170) |\n| `civic_get_evidence_item` | `variant_id` | `id` (numeric) |\n| `OpenTargets_*` | `ensemblID` | `ensemblId` (camelCase) |\n| `search_clinical_trials` | `disease` | `condition` |\n\n---\n\n## Workflow Overview\n\n```\nInput: Cancer type + Molecular profile (mutations, fusions, amplifications)\n\nPhase 1: Profile Validation -> Resolve gene IDs (Ensembl, UniProt, ChEMBL)\nPhase 2: Variant Interpretation -> CIViC, ClinVar, COSMIC, GDC\u002FTCGA, DepMap, OncoKB, cBioPortal, HPA\nPhase 2.5: Tumor Expression -> CELLxGENE cell-type expression, ChIPAtlas regulatory context\nPhase 3: Treatment Options -> OpenTargets + DailyMed (approved), ChEMBL (off-label)\nPhase 3.5: Pathway & Network -> KEGG\u002FReactome pathways, IntAct interactions\nPhase 4: Resistance Analysis -> CIViC + PubMed + NvidiaNIM structure analysis\nPhase 5: Clinical Trials -> ClinicalTrials.gov search + eligibility\nPhase 5.5: Literature -> PubMed, BioRxiv\u002FMedRxiv preprints, OpenAlex citations\nPhase 6: Report Synthesis -> Executive summary + prioritized recommendations\n```\n\n---\n\n## Key Tools by Phase\n\n### Phase 1: Profile Validation\n- `MyGene_query_genes` - Resolve gene to Ensembl ID\n- `UniProt_search` - Get UniProt accession\n- `ChEMBL_search_targets` - Get ChEMBL target ID\n\n### Phase 2: Variant Interpretation\n- `civic_search_variants` \u002F `civic_get_variant` - CIViC evidence\n- `COSMIC_get_mutations_by_gene` \u002F `COSMIC_search_mutations` - Somatic mutations\n- `GDC_get_mutation_frequency` \u002F `GDC_get_ssm_by_gene` - TCGA patient data\n- `GDC_get_gene_expression` \u002F `GDC_get_cnv_data` - Expression and CNV\n- `GDC_get_survival` - Kaplan-Meier survival data by project and optional gene mutation filter\n- `GDC_get_clinical_data` - TCGA clinical metadata (stage, vital status, treatment, demographics)\n- `Progenetix_cnv_search` - Copy number variation biosamples by genomic region and cancer type (NCIt code)\n- `DepMap_get_gene_dependencies` \u002F `PharmacoDB_get_experiments` - Target essentiality\n- `OncoKB_annotate_variant` \u002F `OncoKB_get_gene_info` - Actionability\n- `cBioPortal_get_mutations` \u002F `cBioPortal_get_cancer_studies` - Cross-study data\n- `HPA_search_genes_by_query` \u002F `HPA_get_comparative_expression_by_gene_and_cellline` - Expression\n\n### Phase 2.5: Tumor Expression\n- `CELLxGENE_get_expression_data` \u002F `CELLxGENE_get_cell_metadata` - Cell-type expression\n\n### Phase 3: Treatment Options\n- `OpenTargets_get_associated_drugs_by_target_ensemblID` - Approved drugs (param: `ensemblId`, camelCase)\n- `DGIdb_get_drug_gene_interactions` - Drug-gene interactions (param: `genes` as array, e.g., `[\"EGFR\"]`). Comprehensive; covers inhibitors, antibodies, and investigational agents.\n- `DailyMed_search_spls` - FDA label details\n- `ChEMBL_get_drug_mechanisms` - Drug mechanism\n\n### Phase 3.5: Pathway & Network\n- `kegg_find_genes` \u002F `kegg_get_gene_info` - KEGG pathways\n- `reactome_disease_target_score` - Reactome disease relevance\n- `intact_get_interaction_network` - Protein interactions\n\n### Phase 4: Resistance Analysis\n- `civic_search_evidence_items` - Search by known resistance mutations individually (e.g., `molecular_profile=\"EGFR C797S\"`, `molecular_profile=\"MET Amplification\"`). The `significance` field in results indicates Resistance\u002FSensitivity — filter on it after retrieval.\n- `PubMed_search_articles` - Resistance literature (e.g., \"osimertinib resistance C797S combination therapy\")\n- `alphafold_get_prediction` \u002F `get_diffdock_info` - Structure-based analysis (AlphaFold for structure, DiffDock for docking)\n\n### Phase 5: Clinical Trials\n- `search_clinical_trials` - Find trials (param: `condition`, NOT `disease`)\n- `get_clinical_trial_eligibility_criteria` - Eligibility details\n\n### Phase 5.5: Safety & Pharmacogenomics\n- `FAERS_search_adverse_event_reports` - Real-world adverse events (param: `medicinalproduct`). Check for serious AEs, death rates, common toxicities.\n- `FAERS_count_death_related_by_drug` - Mortality signal for a drug\n- `FDA_get_warnings_and_cautions_by_drug_name` - FDA label safety info\n- `CPIC_list_guidelines` - Check for relevant PGx guidelines (e.g., DPYD for fluoropyrimidines in chemo regimens, UGT1A1 for irinotecan). No CPIC guidelines exist for EGFR TKIs.\n- `fda_pharmacogenomic_biomarkers` - FDA-labeled PGx biomarkers for the drug\n\n> **OncoKB demo mode**: Without `ONCOKB_API_TOKEN` env var, OncoKB only covers BRAF, TP53, ROS1. For other genes (EGFR, KRAS, ALK, etc.), set the API key or use CIViC as the primary evidence source.\n\n### Phase 6: Literature\n- `PubMed_search_articles` - Published evidence (use `limit`, `mindate`, `maxdate` for date filtering)\n- `BioRxiv_list_recent_preprints` \u002F `MedRxiv_get_preprint` - Preprints (flag as NOT peer-reviewed)\n- `openalex_search_works` - Citation analysis\n\n---\n\n## Cross-Skill References\n\nFor CYP interaction with cancer drugs, run: `python3 skills\u002Ftooluniverse-drug-drug-interaction\u002Fscripts\u002Fpharmacology_ref.py --type cyp_substrate --drug drugname`\n\n---\n\n## References\n\n- [TOOLS_REFERENCE.md](TOOLS_REFERENCE.md) - Complete tool documentation with parameters and examples\n- [API_USAGE_PATTERNS.md](API_USAGE_PATTERNS.md) - Detailed code examples for each phase\n- [TREATMENT_ALGORITHMS.md](TREATMENT_ALGORITHMS.md) - Evidence grading, treatment prioritization, cancer type mappings, DepMap interpretation\n- [REPORT_TEMPLATE.md](REPORT_TEMPLATE.md) - Report template with output tables\n- [EXAMPLES.md](EXAMPLES.md) - Worked examples (EGFR NSCLC, T790M resistance, KRAS G12C, no actionable mutations)\n- [CHECKLIST.md](CHECKLIST.md) - Quality and completeness checklist\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Flibrary\u002Fskills\u002Ftooluniverse-precision-oncology","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":40,"prompt":50,"zipAvailable":51},[41,44,47],{"tool":42,"command":43},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-precision-oncology",{"tool":45,"command":46},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-precision-oncology",{"tool":48,"command":49},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-precision-oncology","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-precision-oncology\u002FSKILL.md",true,[53,59,63,67,71,75],{"path":54,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":57,"sourceHtmlUrl":58},"API_USAGE_PATTERNS.md","REFERENCE","参考文档",16372,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-precision-oncology\u002FAPI_USAGE_PATTERNS.md",{"path":60,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":61,"sourceHtmlUrl":62},"CHECKLIST.md",3104,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-precision-oncology\u002FCHECKLIST.md",{"path":64,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":65,"sourceHtmlUrl":66},"EXAMPLES.md",11413,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-precision-oncology\u002FEXAMPLES.md",{"path":68,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":69,"sourceHtmlUrl":70},"REPORT_TEMPLATE.md",6046,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-precision-oncology\u002FREPORT_TEMPLATE.md",{"path":72,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":73,"sourceHtmlUrl":74},"TOOLS_REFERENCE.md",18964,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-precision-oncology\u002FTOOLS_REFERENCE.md",{"path":76,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":77,"sourceHtmlUrl":78},"TREATMENT_ALGORITHMS.md",2950,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-precision-oncology\u002FTREATMENT_ALGORITHMS.md",[80,100,131,158,172,188],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":28},"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",[],[87,88,89,90,24,91,92,93,94,21,95,96,97,98,99],"clarify requirements","clarify","requirements","risk","task","prompts","goal","scanning","context","repo","injection","execution","file",{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":111,"publishedAt":28},"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",[106],{"categoryNo":107,"categoryName":108,"taxonomyType":109,"taxonomyTypeDesc":110},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[112,113,114,115,116,117,118,119,120,121,122,123,124,125,21,126,127,128,129,130],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":132,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":135,"categories":136,"keywords":143,"publishedAt":28},"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",[137,140],{"categoryNo":138,"categoryName":139,"taxonomyType":109,"taxonomyTypeDesc":110},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":141,"categoryName":142,"taxonomyType":109,"taxonomyTypeDesc":110},"01JBSEEDCAT000000000000008","测试与质量",[144,145,146,147,148,149,150,151,152,153,113,154,155,156,157],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":159,"name":160,"nameZh":6,"description":161,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":162,"categories":163,"keywords":164,"publishedAt":28},"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",[],[160,165,166,167,168,169,170,171],"setup","report","project","installation","project setup","issues","state",{"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":179,"publishedAt":28},"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",[178],{"categoryNo":107,"categoryName":108,"taxonomyType":109,"taxonomyTypeDesc":110},[174,180,91,181,182,183,21,184,185,186,187],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":189,"name":165,"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":193,"publishedAt":28},"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",[],[165,167,128,194,169,195],"files","interactive"]