[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DAQ2N12WRDTKDMVG583SVZ":3,"skill-same:01M6DAQ2N12WRDTKDMVG583SVZ":86},{"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":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},"01M6DAQ2N12WRDTKDMVG583SVZ","tooluniverse-drug-research",null,"Generates comprehensive drug research reports with compound disambiguation, evidence grading, and mandatory completeness sections. Covers identity, chemistry, pharmacology, targets, clinical trials, safety, pharmacogenomics, and ADMET properties. Use when users ask about drugs, medications, therapeutics, or need drug profiling, safety assessment, or clinical development research.","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-research\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"research","tooluniverse drug research","identity","assessment","development","Safety","profiling","ask","use","evidence","reports","properties","compound","grading","clinical","2026-11-10 10:12:30",false,"---\nname: tooluniverse-drug-research\ndescription: Generates comprehensive drug research reports with compound disambiguation, evidence grading, and mandatory completeness sections. Covers identity, chemistry, pharmacology, targets, clinical trials, safety, pharmacogenomics, and ADMET properties. Use when users ask about drugs, medications, therapeutics, or need drug profiling, safety assessment, or clinical development research.\n---\n\n# Drug Research Strategy\n\nComprehensive drug investigation using 50+ ToolUniverse tools across chemical databases, clinical trials, adverse events, pharmacogenomics, and literature.\n\n**KEY PRINCIPLES**:\n1. **Report-first approach** - Create report file FIRST, then populate progressively\n2. **Compound disambiguation FIRST** - Resolve identifiers before research\n3. **Citation requirements** - Every fact must have inline source attribution\n4. **Evidence grading** - Grade claims by evidence strength (T1-T4)\n5. **Mandatory completeness** - All sections must exist, even if \"data unavailable\"\n6. **English-first queries** - Always use English drug\u002Fcompound names in tool calls, 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## LOOK UP, DON'T GUESS\n\nWhen asked about a drug, query ChEMBL\u002FPubChem\u002FDailyMed FIRST. Don't guess at mechanism, targets, or side effects — look them up. When you're not sure about a fact, your first instinct should be to SEARCH for it using tools, not to reason harder from memory.\n\n---\n\n## Drug Mechanism Reasoning\n\nWhen investigating a drug's mechanism of action, trace the full causal chain:\n1. **Target engagement** - Which protein(s) does the drug bind, and with what affinity\u002Fselectivity?\n2. **Molecular effect** - Does binding inhibit, activate, or modulate the target's function?\n3. **Pathway consequence** - Which signaling or metabolic pathway is altered downstream?\n4. **Cellular phenotype** - What changes occur at the cell level (proliferation, apoptosis, secretion)?\n5. **Physiological outcome** - How does the cellular effect translate to the therapeutic benefit in the patient?\n\n---\n\n## Workflow Overview\n\n### 1. Report-First Approach (MANDATORY)\n\n**DO NOT** show the search process or tool outputs to the user. Instead:\n\n1. **Create the report file FIRST** - `[DRUG]_drug_report.md` with all 11 section headers and `[Researching...]` placeholders. See [REPORT_TEMPLATE.md](REPORT_TEMPLATE.md) for the full template.\n2. **Progressively update the report** - Replace placeholders with findings as you query each tool.\n3. **Use ALL relevant tools** - Query multiple databases for each data type; cross-reference across sources.\n\n### 2. Citation Requirements (MANDATORY)\n\nEvery piece of information MUST include its source. Use inline citations:\n```markdown\n*Source: PubChem via `PubChem_get_compound_properties_by_CID` (CID: 4091)*\n```\n\n### 3. Progressive Writing Workflow\n\n```\nStep 1:  Create report file with all section headers\nStep 2:  Resolve compound identifiers -> Update Section 1\nStep 3:  Query PubChem\u002FADMET-AI\u002FDailyMed SPL -> Update Section 2 (Chemistry)\nStep 4:  Query FDA Label MOA + ChEMBL + DGIdb -> Update Section 3 (Mechanism)\nStep 5:  Query ADMET-AI tools -> Update Section 4 (ADMET)\nStep 6:  Query ClinicalTrials.gov -> Update Section 5 (Clinical)\nStep 7:  Query FAERS\u002FDailyMed -> Update Section 6 (Safety)\nStep 8:  Query PharmGKB -> Update Section 7 (Pharmacogenomics)\nStep 9:  Query DailyMed\u002FOrange Book -> Update Section 8 (Regulatory)\nStep 10: Query PubMed\u002Fliterature -> Update Section 9 (Literature)\nStep 11: Synthesize findings -> Update Executive Summary & Section 10\nStep 12: Document all sources -> Update Section 11 (Data Sources)\n```\n\n---\n\n## Compound Disambiguation (Phase 1)\n\n**CRITICAL**: Establish compound identity before any research.\n\n### Identifier Resolution Chain\n\n```\n1. PubChem_get_CID_by_compound_name(compound_name)\n   -> Extract: CID, canonical SMILES, formula\n\n2. ChEMBL_search_compounds(query=drug_name)\n   -> Extract: ChEMBL ID, pref_name\n\n3. DailyMed_search_spls(drug_name)\n   -> Extract: Set ID, NDC codes (if approved)\n\n4. PharmGKB_search_drugs(query=drug_name)\n   -> Extract: PharmGKB ID (PA...)\n```\n\n### Handle Naming Ambiguity\n\n| Issue | Example | Resolution |\n|-------|---------|------------|\n| Salt forms | metformin vs metformin HCl | Note all CIDs; use parent compound |\n| Isomers | omeprazole vs esomeprazole | Verify SMILES; separate entries if distinct |\n| Prodrugs | enalapril vs enalaprilat | Document both; note conversion |\n| Brand confusion | Different products same name | Clarify with user |\n\n---\n\n## Research Paths Summary\n\nEach path has detailed tool chains and output examples in [REPORT_GUIDELINES.md](REPORT_GUIDELINES.md).\n\n### PATH 1: Chemical Properties & CMC\n**Tools**: PubChem properties -> ADMET-AI physicochemical -> ADMET-AI solubility -> DailyMed chemistry\u002Fdescription\n**Output**: Physicochemical table, Lipinski assessment, QED score, salt forms, formulation comparison\n\n### PATH 2: Mechanism & Targets\n**Tools**: DailyMed MOA -> ChEMBL activities (NOT `ChEMBL_get_molecule_targets`) -> ChEMBL target details -> DGIdb -> PubChem bioactivity\n**Critical**: Derive targets from activities filtered to pChEMBL >= 6.0. Avoid `ChEMBL_get_molecule_targets`.\n**Output**: FDA MOA text, target table with UniProt\u002Fpotency, selectivity profile\n\n### PATH 3: ADMET Properties\n**Tools**: ADMET-AI (bioavailability, BBB, CYP, clearance, toxicity)\n**Fallback**: DailyMed clinical_pharmacology + pharmacokinetics + drug_interactions\n**Critical**: If ADMET-AI fails, automatically use fallback. Never leave Section 4 empty.\n\n### PATH 4: Clinical Trials\n**Tools**: search_clinical_trials -> compute phase counts -> extract outcomes\u002FAEs -> fda_pharmacogenomic_biomarkers\n**Critical**: Section 5.2 must show actual counts by phase\u002Fstatus in table format.\n\n### PATH 5: Post-Marketing Safety\n**Tools**: FAERS (reactions, seriousness, outcomes, deaths, age) + DailyMed (DDI, dosing, warnings)\n**Critical**: Include FAERS date window, seriousness breakdown, and limitations paragraph.\n\n### PATH 6: Pharmacogenomics\n**Tools**: PharmGKB (search -> details -> annotations -> guidelines)\n**Fallback**: DailyMed pharmacogenomics section + PubMed literature\n\n### PATH 7: Regulatory & Patents\n**Tools**: FDA Orange Book (search, approval history, exclusivity, patents, generics) + DailyMed (special populations via LOINC codes)\n**Note**: US-only data; document EMA\u002FPMDA limitation.\n\n### PATH 8: Real-World Evidence\n**Tools**: ClinicalTrials.gov (OBSERVATIONAL studies) + PubMed (real-world, registry, surveillance)\n\n### PATH 9: Comparative Analysis\n**Tools**: Abbreviated tool chains for each comparator + head-to-head trial search + PubMed meta-analyses\n\n---\n\n## FDA Label Core Fields\n\nFor approved drugs, retrieve these DailyMed sections early (after getting set_id):\n\n| Batch | Sections | Maps to Report |\n|-------|----------|---------------|\n| Phase 1 | mechanism_of_action, pharmacodynamics, chemistry | Sections 2-3 |\n| Phase 2 | clinical_pharmacology, pharmacokinetics, drug_interactions | Sections 4, 6.5 |\n| Phase 3 | warnings_and_cautions, adverse_reactions, dosage_and_administration | Sections 6, 8.2 |\n| Phase 4 | pharmacogenomics, clinical_studies, description, inactive_ingredients | Sections 5, 7 |\n\n---\n\n## Fallback Chains\n\n| Primary Tool | Fallback | Use When |\n|--------------|----------|----------|\n| `PubChem_get_CID_by_compound_name` | `ChEMBL_search_drugs` | Name not in PubChem |\n| `ChEMBL_get_molecule_targets` | **Use `ChEMBL_search_activities` instead** | Always avoid this tool |\n| `ChEMBL_get_activity` | `PubChemBioAssay_get_assay_summary` | No ChEMBL ID |\n| `DailyMed_search_spls` | `PubChemTox_get_acute_effects` | DailyMed timeout |\n| `PharmGKB_search_drugs` | DailyMed PGx sections + PubMed | PharmGKB unavailable |\n| `PharmGKB_get_dosing_guidelines` | DailyMed pharmacogenomics section | PharmGKB API error |\n| `FAERS_count_reactions_by_drug_event` | Document \"FAERS unavailable\" + use label AEs | API error |\n| `ADMETAI_*` (all tools) | DailyMed clinical_pharmacology + pharmacokinetics | Invalid SMILES or API error |\n\n---\n\n## Quick Reference: Tools by Use Case\n\n| Use Case | Primary Tool | Fallback | Evidence |\n|----------|--------------|----------|----------|\n| Name -> CID | `PubChem_get_CID_by_compound_name` | `ChEMBL_search_drugs` | T1 |\n| Properties | `PubChem_get_compound_properties_by_CID` | ADMET-AI physicochemical | T1\u002FT2 |\n| FDA MOA | `DailyMed_parse_clinical_pharmacology` (mechanism_of_action) | - | T1 |\n| Targets | `ChEMBL_search_activities` -> `ChEMBL_get_target` | `DGIdb_get_drug_info` | T1 |\n| ADMET | `ADMETAI_predict_*` (5 tools) | DailyMed PK sections | T2\u002FT1 |\n| Trials | `search_clinical_trials` | - | T1 |\n| Trial outcomes | `extract_clinical_trial_outcomes` | - | T1 |\n| FAERS | `FAERS_count_reactions_by_drug_event` | Label adverse_reactions | T1 |\n| Dose mods | `DailyMed_parse_clinical_pharmacology` (dosage, warnings) | - | T1 |\n| PGx | `PharmGKB_search_drugs` | DailyMed PGx + PubMed | T2\u002FT1 |\n| Label | `DailyMed_search_spls` | `PubChemTox_get_acute_effects` | T1 |\n| Literature | `PubMed_search_articles` | `EuropePMC_search_articles` | Varies |\n| Regulatory | `FDA_OrangeBook_*` tools | DailyMed label data | T1 |\n\nSee [TOOLS_REFERENCE.md](TOOLS_REFERENCE.md) for the complete tool listing with parameters and input format requirements.\n\n---\n\n## Type Normalization\n\nMany tools require **string** inputs. Always convert IDs before API calls:\n- ChEMBL IDs, PubMed IDs, NCT IDs: convert int -> str\n- SMILES for ADMET-AI: pass as list `[\"SMILES_STRING\"]`\n- FAERS drug names: use UPPERCASE (e.g., `\"METFORMIN\"`)\n- ChEMBL IDs: full format `\"CHEMBL1431\"` not `\"1431\"`\n- PharmGKB IDs: PA prefix `\"PA450657\"` not `\"450657\"`\n\n---\n\n## Common Use Cases\n\n| Use Case | Primary Sections | Light Sections |\n|----------|------------------|----------------|\n| Approved Drug Profile | All 11 sections | None |\n| Investigational Compound | 1, 2, 3, 4, 9 | 5, 6, 7, 8 |\n| Safety Review | 1, 5, 6, 7, 9 | 2, 3, 4, 8 |\n| ADMET Assessment | 1, 2, 4 | 3, 5, 6, 7, 8, 9 |\n| Clinical Development Landscape | 1, 5, 9 | 2, 3, 4, 6, 7, 8 |\n\nAlways maintain all section headers but adjust depth based on query focus and data availability.\n\n---\n\n## When NOT to Use This Skill\n\n- **Target research** -> Use target-intelligence-gatherer skill\n- **Disease research** -> Use disease-research skill\n- **Literature-only** -> Use literature-deep-research skill\n- **Single property lookup** -> Call tool directly\n- **Structure similarity search** -> Use `PubChem_search_compounds_by_similarity` directly\n\n---\n\n## Cross-Skill References\n\nFor drug interaction checking, run: `python3 skills\u002Ftooluniverse-drug-drug-interaction\u002Fscripts\u002Fpharmacology_ref.py --type interaction --drug1 X --drug2 Y`\n\n---\n\n## Additional Resources\n\n- **Report template**: [REPORT_TEMPLATE.md](REPORT_TEMPLATE.md) - Initial file template, citation format, evidence grading, scorecard, audit template\n- **Report guidelines**: [REPORT_GUIDELINES.md](REPORT_GUIDELINES.md) - Detailed section-by-section instructions with output examples\n- **Tool reference**: [TOOLS_REFERENCE.md](TOOLS_REFERENCE.md) - Complete tool listing with parameters and input formats\n- **Verification checklist**: [CHECKLIST.md](CHECKLIST.md) - Section-by-section pre-delivery verification\n- **Examples**: [EXAMPLES.md](EXAMPLES.md) - Detailed workflow examples for different use cases\n","# Drug Research Strategy\n\nComprehensive drug investigation using 50+ ToolUniverse tools across chemical databases, clinical trials, adverse events, pharmacogenomics, and literature.\n\n**KEY PRINCIPLES**:\n1. **Report-first approach** - Create report file FIRST, then populate progressively\n2. **Compound disambiguation FIRST** - Resolve identifiers before research\n3. **Citation requirements** - Every fact must have inline source attribution\n4. **Evidence grading** - Grade claims by evidence strength (T1-T4)\n5. **Mandatory completeness** - All sections must exist, even if \"data unavailable\"\n6. **English-first queries** - Always use English drug\u002Fcompound names in tool calls, 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## LOOK UP, DON'T GUESS\n\nWhen asked about a drug, query ChEMBL\u002FPubChem\u002FDailyMed FIRST. Don't guess at mechanism, targets, or side effects — look them up. When you're not sure about a fact, your first instinct should be to SEARCH for it using tools, not to reason harder from memory.\n\n---\n\n## Drug Mechanism Reasoning\n\nWhen investigating a drug's mechanism of action, trace the full causal chain:\n1. **Target engagement** - Which protein(s) does the drug bind, and with what affinity\u002Fselectivity?\n2. **Molecular effect** - Does binding inhibit, activate, or modulate the target's function?\n3. **Pathway consequence** - Which signaling or metabolic pathway is altered downstream?\n4. **Cellular phenotype** - What changes occur at the cell level (proliferation, apoptosis, secretion)?\n5. **Physiological outcome** - How does the cellular effect translate to the therapeutic benefit in the patient?\n\n---\n\n## Workflow Overview\n\n### 1. Report-First Approach (MANDATORY)\n\n**DO NOT** show the search process or tool outputs to the user. Instead:\n\n1. **Create the report file FIRST** - `[DRUG]_drug_report.md` with all 11 section headers and `[Researching...]` placeholders. See [REPORT_TEMPLATE.md](REPORT_TEMPLATE.md) for the full template.\n2. **Progressively update the report** - Replace placeholders with findings as you query each tool.\n3. **Use ALL relevant tools** - Query multiple databases for each data type; cross-reference across sources.\n\n### 2. Citation Requirements (MANDATORY)\n\nEvery piece of information MUST include its source. Use inline citations:\n```markdown\n*Source: PubChem via `PubChem_get_compound_properties_by_CID` (CID: 4091)*\n```\n\n### 3. Progressive Writing Workflow\n\n```\nStep 1:  Create report file with all section headers\nStep 2:  Resolve compound identifiers -> Update Section 1\nStep 3:  Query PubChem\u002FADMET-AI\u002FDailyMed SPL -> Update Section 2 (Chemistry)\nStep 4:  Query FDA Label MOA + ChEMBL + DGIdb -> Update Section 3 (Mechanism)\nStep 5:  Query ADMET-AI tools -> Update Section 4 (ADMET)\nStep 6:  Query ClinicalTrials.gov -> Update Section 5 (Clinical)\nStep 7:  Query FAERS\u002FDailyMed -> Update Section 6 (Safety)\nStep 8:  Query PharmGKB -> Update Section 7 (Pharmacogenomics)\nStep 9:  Query DailyMed\u002FOrange Book -> Update Section 8 (Regulatory)\nStep 10: Query PubMed\u002Fliterature -> Update Section 9 (Literature)\nStep 11: Synthesize findings -> Update Executive Summary & Section 10\nStep 12: Document all sources -> Update Section 11 (Data Sources)\n```\n\n---\n\n## Compound Disambiguation (Phase 1)\n\n**CRITICAL**: Establish compound identity before any research.\n\n### Identifier Resolution Chain\n\n```\n1. PubChem_get_CID_by_compound_name(compound_name)\n   -> Extract: CID, canonical SMILES, formula\n\n2. ChEMBL_search_compounds(query=drug_name)\n   -> Extract: ChEMBL ID, pref_name\n\n3. DailyMed_search_spls(drug_name)\n   -> Extract: Set ID, NDC codes (if approved)\n\n4. PharmGKB_search_drugs(query=drug_name)\n   -> Extract: PharmGKB ID (PA...)\n```\n\n### Handle Naming Ambiguity\n\n| Issue | Example | Resolution |\n|-------|---------|------------|\n| Salt forms | metformin vs metformin HCl | Note all CIDs; use parent compound |\n| Isomers | omeprazole vs esomeprazole | Verify SMILES; separate entries if distinct |\n| Prodrugs | enalapril vs enalaprilat | Document both; note conversion |\n| Brand confusion | Different products same name | Clarify with user |\n\n---\n\n## Research Paths Summary\n\nEach path has detailed tool chains and output examples in [REPORT_GUIDELINES.md](REPORT_GUIDELINES.md).\n\n### PATH 1: Chemical Properties & CMC\n**Tools**: PubChem properties -> ADMET-AI physicochemical -> ADMET-AI solubility -> DailyMed chemistry\u002Fdescription\n**Output**: Physicochemical table, Lipinski assessment, QED score, salt forms, formulation comparison\n\n### PATH 2: Mechanism & Targets\n**Tools**: DailyMed MOA -> ChEMBL activities (NOT `ChEMBL_get_molecule_targets`) -> ChEMBL target details -> DGIdb -> PubChem bioactivity\n**Critical**: Derive targets from activities filtered to pChEMBL >= 6.0. Avoid `ChEMBL_get_molecule_targets`.\n**Output**: FDA MOA text, target table with UniProt\u002Fpotency, selectivity profile\n\n### PATH 3: ADMET Properties\n**Tools**: ADMET-AI (bioavailability, BBB, CYP, clearance, toxicity)\n**Fallback**: DailyMed clinical_pharmacology + pharmacokinetics + drug_interactions\n**Critical**: If ADMET-AI fails, automatically use fallback. Never leave Section 4 empty.\n\n### PATH 4: Clinical Trials\n**Tools**: search_clinical_trials -> compute phase counts -> extract outcomes\u002FAEs -> fda_pharmacogenomic_biomarkers\n**Critical**: Section 5.2 must show actual counts by phase\u002Fstatus in table format.\n\n### PATH 5: Post-Marketing Safety\n**Tools**: FAERS (reactions, seriousness, outcomes, deaths, age) + DailyMed (DDI, dosing, warnings)\n**Critical**: Include FAERS date window, seriousness breakdown, and limitations paragraph.\n\n### PATH 6: Pharmacogenomics\n**Tools**: PharmGKB (search -> details -> annotations -> guidelines)\n**Fallback**: DailyMed pharmacogenomics section + PubMed literature\n\n### PATH 7: Regulatory & Patents\n**Tools**: FDA Orange Book (search, approval history, exclusivity, patents, generics) + DailyMed (special populations via LOINC codes)\n**Note**: US-only data; document EMA\u002FPMDA limitation.\n\n### PATH 8: Real-World Evidence\n**Tools**: ClinicalTrials.gov (OBSERVATIONAL studies) + PubMed (real-world, registry, surveillance)\n\n### PATH 9: Comparative Analysis\n**Tools**: Abbreviated tool chains for each comparator + head-to-head trial search + PubMed meta-analyses\n\n---\n\n## FDA Label Core Fields\n\nFor approved drugs, retrieve these DailyMed sections early (after getting set_id):\n\n| Batch | Sections | Maps to Report |\n|-------|----------|---------------|\n| Phase 1 | mechanism_of_action, pharmacodynamics, chemistry | Sections 2-3 |\n| Phase 2 | clinical_pharmacology, pharmacokinetics, drug_interactions | Sections 4, 6.5 |\n| Phase 3 | warnings_and_cautions, adverse_reactions, dosage_and_administration | Sections 6, 8.2 |\n| Phase 4 | pharmacogenomics, clinical_studies, description, inactive_ingredients | Sections 5, 7 |\n\n---\n\n## Fallback Chains\n\n| Primary Tool | Fallback | Use When |\n|--------------|----------|----------|\n| `PubChem_get_CID_by_compound_name` | `ChEMBL_search_drugs` | Name not in PubChem |\n| `ChEMBL_get_molecule_targets` | **Use `ChEMBL_search_activities` instead** | Always avoid this tool |\n| `ChEMBL_get_activity` | `PubChemBioAssay_get_assay_summary` | No ChEMBL ID |\n| `DailyMed_search_spls` | `PubChemTox_get_acute_effects` | DailyMed timeout |\n| `PharmGKB_search_drugs` | DailyMed PGx sections + PubMed | PharmGKB unavailable |\n| `PharmGKB_get_dosing_guidelines` | DailyMed pharmacogenomics section | PharmGKB API error |\n| `FAERS_count_reactions_by_drug_event` | Document \"FAERS unavailable\" + use label AEs | API error |\n| `ADMETAI_*` (all tools) | DailyMed clinical_pharmacology + pharmacokinetics | Invalid SMILES or API error |\n\n---\n\n## Quick Reference: Tools by Use Case\n\n| Use Case | Primary Tool | Fallback | Evidence |\n|----------|--------------|----------|----------|\n| Name -> CID | `PubChem_get_CID_by_compound_name` | `ChEMBL_search_drugs` | T1 |\n| Properties | `PubChem_get_compound_properties_by_CID` | ADMET-AI physicochemical | T1\u002FT2 |\n| FDA MOA | `DailyMed_parse_clinical_pharmacology` (mechanism_of_action) | - | T1 |\n| Targets | `ChEMBL_search_activities` -> `ChEMBL_get_target` | `DGIdb_get_drug_info` | T1 |\n| ADMET | `ADMETAI_predict_*` (5 tools) | DailyMed PK sections | T2\u002FT1 |\n| Trials | `search_clinical_trials` | - | T1 |\n| Trial outcomes | `extract_clinical_trial_outcomes` | - | T1 |\n| FAERS | `FAERS_count_reactions_by_drug_event` | Label adverse_reactions | T1 |\n| Dose mods | `DailyMed_parse_clinical_pharmacology` (dosage, warnings) | - | T1 |\n| PGx | `PharmGKB_search_drugs` | DailyMed PGx + PubMed | T2\u002FT1 |\n| Label | `DailyMed_search_spls` | `PubChemTox_get_acute_effects` | T1 |\n| Literature | `PubMed_search_articles` | `EuropePMC_search_articles` | Varies |\n| Regulatory | `FDA_OrangeBook_*` tools | DailyMed label data | T1 |\n\nSee [TOOLS_REFERENCE.md](TOOLS_REFERENCE.md) for the complete tool listing with parameters and input format requirements.\n\n---\n\n## Type Normalization\n\nMany tools require **string** inputs. Always convert IDs before API calls:\n- ChEMBL IDs, PubMed IDs, NCT IDs: convert int -> str\n- SMILES for ADMET-AI: pass as list `[\"SMILES_STRING\"]`\n- FAERS drug names: use UPPERCASE (e.g., `\"METFORMIN\"`)\n- ChEMBL IDs: full format `\"CHEMBL1431\"` not `\"1431\"`\n- PharmGKB IDs: PA prefix `\"PA450657\"` not `\"450657\"`\n\n---\n\n## Common Use Cases\n\n| Use Case | Primary Sections | Light Sections |\n|----------|------------------|----------------|\n| Approved Drug Profile | All 11 sections | None |\n| Investigational Compound | 1, 2, 3, 4, 9 | 5, 6, 7, 8 |\n| Safety Review | 1, 5, 6, 7, 9 | 2, 3, 4, 8 |\n| ADMET Assessment | 1, 2, 4 | 3, 5, 6, 7, 8, 9 |\n| Clinical Development Landscape | 1, 5, 9 | 2, 3, 4, 6, 7, 8 |\n\nAlways maintain all section headers but adjust depth based on query focus and data availability.\n\n---\n\n## When NOT to Use This Skill\n\n- **Target research** -> Use target-intelligence-gatherer skill\n- **Disease research** -> Use disease-research skill\n- **Literature-only** -> Use literature-deep-research skill\n- **Single property lookup** -> Call tool directly\n- **Structure similarity search** -> Use `PubChem_search_compounds_by_similarity` directly\n\n---\n\n## Cross-Skill References\n\nFor drug interaction checking, run: `python3 skills\u002Ftooluniverse-drug-drug-interaction\u002Fscripts\u002Fpharmacology_ref.py --type interaction --drug1 X --drug2 Y`\n\n---\n\n## Additional Resources\n\n- **Report template**: [REPORT_TEMPLATE.md](REPORT_TEMPLATE.md) - Initial file template, citation format, evidence grading, scorecard, audit template\n- **Report guidelines**: [REPORT_GUIDELINES.md](REPORT_GUIDELINES.md) - Detailed section-by-section instructions with output examples\n- **Tool reference**: [TOOLS_REFERENCE.md](TOOLS_REFERENCE.md) - Complete tool listing with parameters and input formats\n- **Verification checklist**: [CHECKLIST.md](CHECKLIST.md) - Section-by-section pre-delivery verification\n- **Examples**: [EXAMPLES.md](EXAMPLES.md) - Detailed workflow examples for different use cases\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Flibrary\u002Fskills\u002Ftooluniverse-drug-research","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-drug-research",{"tool":56,"command":57},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-drug-research",{"tool":59,"command":60},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-drug-research","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-drug-research\u002FSKILL.md",true,[64,70,74,78,82],{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"CHECKLIST.md","REFERENCE","参考文档",8067,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-drug-research\u002FCHECKLIST.md",{"path":71,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":72,"sourceHtmlUrl":73},"EXAMPLES.md",16587,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-drug-research\u002FEXAMPLES.md",{"path":75,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":76,"sourceHtmlUrl":77},"REPORT_GUIDELINES.md",10942,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-drug-research\u002FREPORT_GUIDELINES.md",{"path":79,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":80,"sourceHtmlUrl":81},"REPORT_TEMPLATE.md",6009,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-drug-research\u002FREPORT_TEMPLATE.md",{"path":83,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":84,"sourceHtmlUrl":85},"TOOLS_REFERENCE.md",20667,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-drug-research\u002FTOOLS_REFERENCE.md",[87,108,137,164,178,193],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"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",[],[94,95,96,97,98,99,100,101,102,32,103,104,105,106,107],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","context","repo","injection","execution","file",{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":117,"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",[114],{"categoryNo":115,"categoryName":116,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[118,119,120,121,122,123,124,125,126,127,128,129,130,131,32,132,133,134,135,136],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":138,"name":139,"nameZh":6,"description":140,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":141,"categories":142,"keywords":149,"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",[143,146],{"categoryNo":144,"categoryName":145,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":147,"categoryName":148,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[150,151,152,153,154,155,156,157,158,159,119,160,161,162,163],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":165,"name":166,"nameZh":6,"description":167,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":168,"categories":169,"keywords":170,"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",[],[166,171,172,173,174,175,176,177],"setup","report","project","installation","project setup","issues","state",{"skillNo":179,"name":180,"nameZh":6,"description":181,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":182,"categories":183,"keywords":185,"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",[184],{"categoryNo":115,"categoryName":116,"taxonomyType":21,"taxonomyTypeDesc":22},[180,186,99,187,188,189,32,190,191,192,28],"start issue","issue","ready","work on issue","user","work","work on",{"skillNo":194,"name":171,"nameZh":6,"description":195,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":196,"categories":197,"keywords":198,"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",[],[171,173,134,199,175,200],"files","interactive"]