[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DAM0QZR27664S69AVZFD4T":3,"skill-same:01M6DAM0QZR27664S69AVZFD4T":91},{"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":38,"linkOnly":39,"markdownContent":40,"markdownBody":41,"frontMatter":42,"refName":43,"commitSha":44,"skillDirectory":45,"forksCount":14,"repositoryHtmlUrl":46,"repositoryHomepageUrl":6,"ownerHtmlUrl":47,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":48,"install":49,"resources":62},"01M6DAM0QZR27664S69AVZFD4T","tooluniverse-adverse-event-detection",null,"Detect and analyze adverse drug event signals using FDA FAERS data, drug labels, disproportionality analysis (PRR, ROR, IC), and biomedical evidence. Generates quantitative safety signal scores (0-100) with evidence grading. Use for post-market surveillance, pharmacovigilance, drug safety assessment, adverse event investigation, and regulatory decision support.","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-adverse-event-detection\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37],"tooluniverse adverse event detection","detection","decision support","biomedical","grading","signals","Market","evidence","fda","regulatory","use","support","decision","analyze","investigation","analysis","Safety","data","assessment","2026-11-10 10:12:30",false,"---\nname: tooluniverse-adverse-event-detection\ndescription: Detect and analyze adverse drug event signals using FDA FAERS data, drug labels, disproportionality analysis (PRR, ROR, IC), and biomedical evidence. Generates quantitative safety signal scores (0-100) with evidence grading. Use for post-market surveillance, pharmacovigilance, drug safety assessment, adverse event investigation, and regulatory decision support.\n---\n\n## COMPUTE, DON'T DESCRIBE\nWhen analysis requires computation (statistics, data processing, scoring, enrichment), write and run Python code via Bash. Don't describe what you would do — execute it and report actual results. Use ToolUniverse tools to retrieve data, then Python (pandas, scipy, statsmodels, matplotlib) to analyze it.\n\n# Adverse Drug Event Signal Detection & Analysis\n\nAutomated pipeline for detecting, quantifying, and contextualizing adverse drug event signals using FAERS disproportionality analysis, FDA label mining, mechanism-based prediction, and literature evidence. Produces a quantitative Safety Signal Score (0-100) for regulatory and clinical decision-making.\n\n**KEY PRINCIPLES**:\n1. **Signal quantification first** - Every adverse event must have PRR\u002FROR\u002FIC with confidence intervals\n2. **Serious events priority** - Deaths, hospitalizations, life-threatening events always analyzed first\n3. **Multi-source triangulation** - FAERS + FDA labels + OpenTargets + DrugBank + literature\n4. **Context-aware assessment** - Distinguish drug-specific vs class-wide vs confounding signals\n5. **Report-first approach** - Create report file FIRST, update progressively\n6. **Evidence grading mandatory** - T1 (regulatory\u002Fboxed warning) through T4 (computational)\n7. **English-first queries** - Always use English drug names in tool calls, respond in user's language\n\n**REASONING STRATEGY — Start Here**:\nStart with the signal: What adverse event was reported more than expected? (PRR >= 2.0, N >= 3, lower CI > 1.0 is the threshold). Then ask three questions in order:\n1. **Biologically plausible?** Given the drug's mechanism of action and targets, does this adverse event make sense? An off-target kinase inhibitor causing cardiac events is plausible; a topical agent causing systemic toxicity needs more scrutiny. LOOK UP DON'T GUESS — use `OpenTargets_get_drug_mechanisms_of_action_by_chemblId` and `drugbank_get_targets_by_drug_name_or_drugbank_id` to check targets before asserting plausibility.\n2. **Timing consistent?** Acute reactions (within hours\u002Fdays) suggest immune or direct pharmacologic mechanism. Delayed reactions (weeks\u002Fmonths) suggest cumulative toxicity or idiosyncratic response. Check FAERS time-to-onset distribution.\n3. **Could confounders explain it?** Patients taking this drug likely have the underlying disease — compare against background rate in that population, not the general population. Class-wide signals (appearing for all drugs in the class) suggest mechanism-based rather than molecule-specific toxicity.\n\n**Causality Assessment — Naranjo Algorithm Reasoning**:\nWhen determining whether an adverse event is drug-caused (not just associated), apply these steps systematically. LOOK UP DON'T GUESS — search FAERS and FDA labels for each criterion:\n1. **Prior reports?** Are there previous conclusive reports of this reaction? Check FDA label (`FDA_get_adverse_reactions_by_drug_name`) and literature (`PubMed_search_articles`). Yes = +1.\n2. **Temporal relationship?** Did the AE appear after drug administration? Onset within expected pharmacokinetic window (1-5 half-lives) = +2. Use `FAERS_stratify_by_demographics` for time-to-onset data.\n3. **Dechallenge?** Did the AE improve when the drug was stopped? Positive dechallenge = +1. Look for rechallenge\u002Fdechallenge case reports in literature.\n4. **Rechallenge?** Did the AE reappear when the drug was restarted? Positive rechallenge = +2 (strongest single piece of evidence for causality).\n5. **Alternative causes?** Could the underlying disease, concomitant drugs, or other factors explain the AE? Check `drugbank_get_drug_interactions_by_drug_name_or_id` for interacting drugs.\n6. **Dose-response?** Did the reaction worsen with higher doses or improve with lower doses? Dose-dependent AEs suggest on-target toxicity.\n7. **Drug level confirmation?** Was the drug detected in body fluids at toxic concentrations?\n- Score: Definite (>=9), Probable (5-8), Possible (1-4), Doubtful (\u003C=0).\n- Even without individual patient data, you can estimate causality from aggregate FAERS signals + label evidence + mechanistic plausibility.\n\n**Reference files** (in this directory):\n- `PHASE_DETAILS.md` - Detailed tool calls, code examples, and output templates per phase\n- `REPORT_TEMPLATE.md` - Full report template and completeness checklist\n- `TOOL_REFERENCE.md` - Tool parameter reference and fallback chains\n- `QUICK_START.md` - Quick examples and common drug names\n\n---\n\n## When to Use\n\nApply when user asks:\n- \"What are the safety signals for [drug]?\"\n- \"Detect adverse events for [drug]\"\n- \"Is [drug] associated with [adverse event]?\"\n- \"What are the FAERS signals for [drug]?\"\n- \"Compare safety of [drug A] vs [drug B] for [adverse event]\"\n- \"What are the serious adverse events for [drug]?\"\n- \"Are there emerging safety signals for [drug]?\"\n- \"Post-market surveillance report for [drug]\"\n- \"Pharmacovigilance signal detection for [drug]\"\n\n**Differentiation from tooluniverse-pharmacovigilance**: This skill focuses specifically on **signal detection and quantification** using disproportionality analysis (PRR, ROR, IC) with statistical rigor, produces a quantitative **Safety Signal Score (0-100)**, and performs **comparative safety analysis** across drug classes.\n\n---\n\n## Workflow Overview\n\n```\nPhase 0: Input Parsing & Drug Disambiguation\n  Parse drug name, resolve to ChEMBL ID, DrugBank ID\n  Identify drug class, mechanism, and approved indications\n    |\nPhase 1: FAERS Adverse Event Profiling\n  Top adverse events by frequency\n  Seriousness and outcome distributions\n  Demographics (age, sex, country)\n    |\nPhase 2: Disproportionality Analysis (Signal Detection)\n  Calculate PRR, ROR, IC with 95% CI for each AE\n  Apply signal detection criteria\n  Classify signal strength (Strong\u002FModerate\u002FWeak\u002FNone)\n    |\nPhase 3: FDA Label Safety Information\n  Boxed warnings, contraindications\n  Warnings and precautions, adverse reactions\n  Drug interactions, special populations\n    |\nPhase 4: Mechanism-Based Adverse Event Context\n  Target-based AE prediction (OpenTargets safety)\n  Off-target effects, ADMET predictions\n  Drug class effects comparison\n    |\nPhase 5: Comparative Safety Analysis\n  Compare to drugs in same class\n  Identify unique vs class-wide signals\n  Head-to-head disproportionality comparison\n    |\nPhase 6: Drug-Drug Interactions & Risk Factors\n  Known DDIs causing AEs\n  Pharmacogenomic risk factors (PharmGKB)\n  FDA PGx biomarkers\n    |\nPhase 7: Literature Evidence\n  PubMed safety studies, case reports\n  OpenAlex citation analysis\n  Preprint emerging signals (EuropePMC)\n    |\nPhase 8: Risk Assessment & Safety Signal Score\n  Calculate Safety Signal Score (0-100)\n  Evidence grading (T1-T4) for each signal\n  Clinical significance assessment\n    |\nPhase 9: Report Synthesis & Recommendations\n  Monitoring recommendations\n  Risk mitigation strategies\n  Completeness checklist\n```\n\n---\n\n## Phase Summaries\n\n### Phase 0: Input Parsing & Drug Disambiguation\nResolve drug name to ChEMBL ID, DrugBank ID. Get mechanism of action, blackbox warning status, targets, and approved indications.\n- **Tools**: `OpenTargets_get_drug_chembId_by_generic_name`, `OpenTargets_get_drug_mechanisms_of_action_by_chemblId`, `OpenTargets_get_drug_blackbox_status_by_chembl_ID`, `drugbank_get_safety_by_drug_name_or_drugbank_id`, `drugbank_get_targets_by_drug_name_or_drugbank_id`, `OpenTargets_get_drug_indications_by_chemblId`\n\n### Phase 1: FAERS Adverse Event Profiling\nQuery FAERS for top adverse events, seriousness distribution, outcomes, demographics, and death-related events. Filter serious events by type (death, hospitalization, life-threatening). Get MedDRA hierarchy rollup.\n- **Tools**: `FAERS_count_reactions_by_drug_event`, `FAERS_count_seriousness_by_drug_event`, `FAERS_count_outcomes_by_drug_event`, `FAERS_count_patient_age_distribution`, `FAERS_count_death_related_by_drug`, `FAERS_count_reportercountry_by_drug_event`, `FAERS_filter_serious_events`, `FAERS_rollup_meddra_hierarchy`\n\n### Phase 2: Disproportionality Analysis (Signal Detection)\n**CRITICAL PHASE**. For each top adverse event (at least 15-20), calculate PRR, ROR, IC with 95% CI. Classify signal strength. Stratify strong signals by demographics.\n- **Tools**: `FAERS_calculate_disproportionality`, `FAERS_stratify_by_demographics`\n- **MedDRA term level note**: `FAERS_count_reactions_by_drug_event` filters by MedDRA Lowest Level Term (`reactionmeddraverse`) while `FAERS_calculate_disproportionality` uses Preferred Terms. Case counts can differ dramatically — always use disproportionality analysis as the primary signal metric, not raw counts.\n- **Signal criteria**: PRR >= 2.0 AND lower CI > 1.0 AND N >= 3\n- **Strength**: Strong (PRR >= 5), Moderate (PRR 3-5), Weak (PRR 2-3)\n- See `PHASE_DETAILS.md` for full signal classification table\n\n### Phase 3: FDA Label Safety Information\nExtract boxed warnings, contraindications, warnings\u002Fprecautions, adverse reactions, drug interactions, and special population info. Note: `{error: {code: \"NOT_FOUND\"}}` is normal when a section does not exist.\n- **Tools**: `FDA_get_boxed_warning_info_by_drug_name`, `FDA_get_contraindications_by_drug_name`, `FDA_get_warnings_by_drug_name`, `FDA_get_adverse_reactions_by_drug_name`, `FDA_get_drug_interactions_by_drug_name`, `FDA_get_pregnancy_or_breastfeeding_info_by_drug_name`, `FDA_get_geriatric_use_info_by_drug_name`, `FDA_get_pediatric_use_info_by_drug_name`, `FDA_get_pharmacogenomics_info_by_drug_name`\n\n### Phase 4: Mechanism-Based Adverse Event Context\nGet target safety profile, OpenTargets adverse events, ADMET toxicity predictions (if SMILES available), and drug warnings.\n- **Tools**: `OpenTargets_get_target_safety_profile_by_ensemblID`, `OpenTargets_get_drug_adverse_events_by_chemblId`, `ADMETAI_predict_toxicity`, `ADMETAI_predict_CYP_interactions`, `OpenTargets_get_drug_warnings_by_chemblId`\n\n### Phase 5: Comparative Safety Analysis\nHead-to-head comparison with class members using `FAERS_compare_drugs`. Aggregate class AEs. Identify class-wide vs drug-specific signals.\n- **Tools**: `FAERS_compare_drugs`, `FAERS_count_additive_adverse_reactions`, `FAERS_count_additive_seriousness_classification`\n\n### Phase 6: Drug-Drug Interactions & Risk Factors\nExtract DDIs from FDA label, DrugBank, and DailyMed. Query PharmGKB for pharmacogenomic risk factors and dosing guidelines. Check FDA PGx biomarkers.\n- **Tools**: `FDA_get_drug_interactions_by_drug_name`, `drugbank_get_drug_interactions_by_drug_name_or_id`, `DailyMed_parse_drug_interactions`, `PharmGKB_search_drugs`, `PharmGKB_get_drug_details`, `PharmGKB_get_dosing_guidelines`, `fda_pharmacogenomic_biomarkers`\n\n### Phase 7: Literature Evidence\nSearch PubMed, OpenAlex, and EuropePMC for safety studies, case reports, and preprints.\n- **Tools**: `PubMed_search_articles`, `openalex_search_works`, `EuropePMC_search_articles`\n\n### Phase 8: Risk Assessment & Safety Signal Score\nCalculate Safety Signal Score (0-100) from four components: FAERS signal strength (0-35), serious AEs (0-30), FDA label warnings (0-25), literature evidence (0-10). Grade each signal T1-T4. See `PHASE_DETAILS.md` for scoring rubric.\n\n### Phase 9: Report Synthesis\nGenerate comprehensive markdown report with executive summary, all phase outputs, monitoring recommendations, risk mitigation strategies, patient counseling points, and completeness checklist. See `REPORT_TEMPLATE.md` for full template.\n\n---\n\n## Edge Cases\n\n- **No FAERS reports**: Skip Phases 1-2; rely on FDA label, mechanism predictions, literature\n- **Generic vs Brand name**: Try both in FAERS; use `OpenTargets_get_drug_chembId_by_generic_name` to resolve\n- **Drug combinations**: Use `FAERS_count_additive_adverse_reactions` for aggregate class analysis\n- **Confounding by indication**: Compare AE profile to the disease being treated; note limitation in report\n- **Drugs with boxed warnings**: Score component automatically 25\u002F25 for label warnings; prioritize boxed warning events\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# Adverse Drug Event Signal Detection & Analysis\n\nAutomated pipeline for detecting, quantifying, and contextualizing adverse drug event signals using FAERS disproportionality analysis, FDA label mining, mechanism-based prediction, and literature evidence. Produces a quantitative Safety Signal Score (0-100) for regulatory and clinical decision-making.\n\n**KEY PRINCIPLES**:\n1. **Signal quantification first** - Every adverse event must have PRR\u002FROR\u002FIC with confidence intervals\n2. **Serious events priority** - Deaths, hospitalizations, life-threatening events always analyzed first\n3. **Multi-source triangulation** - FAERS + FDA labels + OpenTargets + DrugBank + literature\n4. **Context-aware assessment** - Distinguish drug-specific vs class-wide vs confounding signals\n5. **Report-first approach** - Create report file FIRST, update progressively\n6. **Evidence grading mandatory** - T1 (regulatory\u002Fboxed warning) through T4 (computational)\n7. **English-first queries** - Always use English drug names in tool calls, respond in user's language\n\n**REASONING STRATEGY — Start Here**:\nStart with the signal: What adverse event was reported more than expected? (PRR >= 2.0, N >= 3, lower CI > 1.0 is the threshold). Then ask three questions in order:\n1. **Biologically plausible?** Given the drug's mechanism of action and targets, does this adverse event make sense? An off-target kinase inhibitor causing cardiac events is plausible; a topical agent causing systemic toxicity needs more scrutiny. LOOK UP DON'T GUESS — use `OpenTargets_get_drug_mechanisms_of_action_by_chemblId` and `drugbank_get_targets_by_drug_name_or_drugbank_id` to check targets before asserting plausibility.\n2. **Timing consistent?** Acute reactions (within hours\u002Fdays) suggest immune or direct pharmacologic mechanism. Delayed reactions (weeks\u002Fmonths) suggest cumulative toxicity or idiosyncratic response. Check FAERS time-to-onset distribution.\n3. **Could confounders explain it?** Patients taking this drug likely have the underlying disease — compare against background rate in that population, not the general population. Class-wide signals (appearing for all drugs in the class) suggest mechanism-based rather than molecule-specific toxicity.\n\n**Causality Assessment — Naranjo Algorithm Reasoning**:\nWhen determining whether an adverse event is drug-caused (not just associated), apply these steps systematically. LOOK UP DON'T GUESS — search FAERS and FDA labels for each criterion:\n1. **Prior reports?** Are there previous conclusive reports of this reaction? Check FDA label (`FDA_get_adverse_reactions_by_drug_name`) and literature (`PubMed_search_articles`). Yes = +1.\n2. **Temporal relationship?** Did the AE appear after drug administration? Onset within expected pharmacokinetic window (1-5 half-lives) = +2. Use `FAERS_stratify_by_demographics` for time-to-onset data.\n3. **Dechallenge?** Did the AE improve when the drug was stopped? Positive dechallenge = +1. Look for rechallenge\u002Fdechallenge case reports in literature.\n4. **Rechallenge?** Did the AE reappear when the drug was restarted? Positive rechallenge = +2 (strongest single piece of evidence for causality).\n5. **Alternative causes?** Could the underlying disease, concomitant drugs, or other factors explain the AE? Check `drugbank_get_drug_interactions_by_drug_name_or_id` for interacting drugs.\n6. **Dose-response?** Did the reaction worsen with higher doses or improve with lower doses? Dose-dependent AEs suggest on-target toxicity.\n7. **Drug level confirmation?** Was the drug detected in body fluids at toxic concentrations?\n- Score: Definite (>=9), Probable (5-8), Possible (1-4), Doubtful (\u003C=0).\n- Even without individual patient data, you can estimate causality from aggregate FAERS signals + label evidence + mechanistic plausibility.\n\n**Reference files** (in this directory):\n- `PHASE_DETAILS.md` - Detailed tool calls, code examples, and output templates per phase\n- `REPORT_TEMPLATE.md` - Full report template and completeness checklist\n- `TOOL_REFERENCE.md` - Tool parameter reference and fallback chains\n- `QUICK_START.md` - Quick examples and common drug names\n\n---\n\n## When to Use\n\nApply when user asks:\n- \"What are the safety signals for [drug]?\"\n- \"Detect adverse events for [drug]\"\n- \"Is [drug] associated with [adverse event]?\"\n- \"What are the FAERS signals for [drug]?\"\n- \"Compare safety of [drug A] vs [drug B] for [adverse event]\"\n- \"What are the serious adverse events for [drug]?\"\n- \"Are there emerging safety signals for [drug]?\"\n- \"Post-market surveillance report for [drug]\"\n- \"Pharmacovigilance signal detection for [drug]\"\n\n**Differentiation from tooluniverse-pharmacovigilance**: This skill focuses specifically on **signal detection and quantification** using disproportionality analysis (PRR, ROR, IC) with statistical rigor, produces a quantitative **Safety Signal Score (0-100)**, and performs **comparative safety analysis** across drug classes.\n\n---\n\n## Workflow Overview\n\n```\nPhase 0: Input Parsing & Drug Disambiguation\n  Parse drug name, resolve to ChEMBL ID, DrugBank ID\n  Identify drug class, mechanism, and approved indications\n    |\nPhase 1: FAERS Adverse Event Profiling\n  Top adverse events by frequency\n  Seriousness and outcome distributions\n  Demographics (age, sex, country)\n    |\nPhase 2: Disproportionality Analysis (Signal Detection)\n  Calculate PRR, ROR, IC with 95% CI for each AE\n  Apply signal detection criteria\n  Classify signal strength (Strong\u002FModerate\u002FWeak\u002FNone)\n    |\nPhase 3: FDA Label Safety Information\n  Boxed warnings, contraindications\n  Warnings and precautions, adverse reactions\n  Drug interactions, special populations\n    |\nPhase 4: Mechanism-Based Adverse Event Context\n  Target-based AE prediction (OpenTargets safety)\n  Off-target effects, ADMET predictions\n  Drug class effects comparison\n    |\nPhase 5: Comparative Safety Analysis\n  Compare to drugs in same class\n  Identify unique vs class-wide signals\n  Head-to-head disproportionality comparison\n    |\nPhase 6: Drug-Drug Interactions & Risk Factors\n  Known DDIs causing AEs\n  Pharmacogenomic risk factors (PharmGKB)\n  FDA PGx biomarkers\n    |\nPhase 7: Literature Evidence\n  PubMed safety studies, case reports\n  OpenAlex citation analysis\n  Preprint emerging signals (EuropePMC)\n    |\nPhase 8: Risk Assessment & Safety Signal Score\n  Calculate Safety Signal Score (0-100)\n  Evidence grading (T1-T4) for each signal\n  Clinical significance assessment\n    |\nPhase 9: Report Synthesis & Recommendations\n  Monitoring recommendations\n  Risk mitigation strategies\n  Completeness checklist\n```\n\n---\n\n## Phase Summaries\n\n### Phase 0: Input Parsing & Drug Disambiguation\nResolve drug name to ChEMBL ID, DrugBank ID. Get mechanism of action, blackbox warning status, targets, and approved indications.\n- **Tools**: `OpenTargets_get_drug_chembId_by_generic_name`, `OpenTargets_get_drug_mechanisms_of_action_by_chemblId`, `OpenTargets_get_drug_blackbox_status_by_chembl_ID`, `drugbank_get_safety_by_drug_name_or_drugbank_id`, `drugbank_get_targets_by_drug_name_or_drugbank_id`, `OpenTargets_get_drug_indications_by_chemblId`\n\n### Phase 1: FAERS Adverse Event Profiling\nQuery FAERS for top adverse events, seriousness distribution, outcomes, demographics, and death-related events. Filter serious events by type (death, hospitalization, life-threatening). Get MedDRA hierarchy rollup.\n- **Tools**: `FAERS_count_reactions_by_drug_event`, `FAERS_count_seriousness_by_drug_event`, `FAERS_count_outcomes_by_drug_event`, `FAERS_count_patient_age_distribution`, `FAERS_count_death_related_by_drug`, `FAERS_count_reportercountry_by_drug_event`, `FAERS_filter_serious_events`, `FAERS_rollup_meddra_hierarchy`\n\n### Phase 2: Disproportionality Analysis (Signal Detection)\n**CRITICAL PHASE**. For each top adverse event (at least 15-20), calculate PRR, ROR, IC with 95% CI. Classify signal strength. Stratify strong signals by demographics.\n- **Tools**: `FAERS_calculate_disproportionality`, `FAERS_stratify_by_demographics`\n- **MedDRA term level note**: `FAERS_count_reactions_by_drug_event` filters by MedDRA Lowest Level Term (`reactionmeddraverse`) while `FAERS_calculate_disproportionality` uses Preferred Terms. Case counts can differ dramatically — always use disproportionality analysis as the primary signal metric, not raw counts.\n- **Signal criteria**: PRR >= 2.0 AND lower CI > 1.0 AND N >= 3\n- **Strength**: Strong (PRR >= 5), Moderate (PRR 3-5), Weak (PRR 2-3)\n- See `PHASE_DETAILS.md` for full signal classification table\n\n### Phase 3: FDA Label Safety Information\nExtract boxed warnings, contraindications, warnings\u002Fprecautions, adverse reactions, drug interactions, and special population info. Note: `{error: {code: \"NOT_FOUND\"}}` is normal when a section does not exist.\n- **Tools**: `FDA_get_boxed_warning_info_by_drug_name`, `FDA_get_contraindications_by_drug_name`, `FDA_get_warnings_by_drug_name`, `FDA_get_adverse_reactions_by_drug_name`, `FDA_get_drug_interactions_by_drug_name`, `FDA_get_pregnancy_or_breastfeeding_info_by_drug_name`, `FDA_get_geriatric_use_info_by_drug_name`, `FDA_get_pediatric_use_info_by_drug_name`, `FDA_get_pharmacogenomics_info_by_drug_name`\n\n### Phase 4: Mechanism-Based Adverse Event Context\nGet target safety profile, OpenTargets adverse events, ADMET toxicity predictions (if SMILES available), and drug warnings.\n- **Tools**: `OpenTargets_get_target_safety_profile_by_ensemblID`, `OpenTargets_get_drug_adverse_events_by_chemblId`, `ADMETAI_predict_toxicity`, `ADMETAI_predict_CYP_interactions`, `OpenTargets_get_drug_warnings_by_chemblId`\n\n### Phase 5: Comparative Safety Analysis\nHead-to-head comparison with class members using `FAERS_compare_drugs`. Aggregate class AEs. Identify class-wide vs drug-specific signals.\n- **Tools**: `FAERS_compare_drugs`, `FAERS_count_additive_adverse_reactions`, `FAERS_count_additive_seriousness_classification`\n\n### Phase 6: Drug-Drug Interactions & Risk Factors\nExtract DDIs from FDA label, DrugBank, and DailyMed. Query PharmGKB for pharmacogenomic risk factors and dosing guidelines. Check FDA PGx biomarkers.\n- **Tools**: `FDA_get_drug_interactions_by_drug_name`, `drugbank_get_drug_interactions_by_drug_name_or_id`, `DailyMed_parse_drug_interactions`, `PharmGKB_search_drugs`, `PharmGKB_get_drug_details`, `PharmGKB_get_dosing_guidelines`, `fda_pharmacogenomic_biomarkers`\n\n### Phase 7: Literature Evidence\nSearch PubMed, OpenAlex, and EuropePMC for safety studies, case reports, and preprints.\n- **Tools**: `PubMed_search_articles`, `openalex_search_works`, `EuropePMC_search_articles`\n\n### Phase 8: Risk Assessment & Safety Signal Score\nCalculate Safety Signal Score (0-100) from four components: FAERS signal strength (0-35), serious AEs (0-30), FDA label warnings (0-25), literature evidence (0-10). Grade each signal T1-T4. See `PHASE_DETAILS.md` for scoring rubric.\n\n### Phase 9: Report Synthesis\nGenerate comprehensive markdown report with executive summary, all phase outputs, monitoring recommendations, risk mitigation strategies, patient counseling points, and completeness checklist. See `REPORT_TEMPLATE.md` for full template.\n\n---\n\n## Edge Cases\n\n- **No FAERS reports**: Skip Phases 1-2; rely on FDA label, mechanism predictions, literature\n- **Generic vs Brand name**: Try both in FAERS; use `OpenTargets_get_drug_chembId_by_generic_name` to resolve\n- **Drug combinations**: Use `FAERS_count_additive_adverse_reactions` for aggregate class analysis\n- **Confounding by indication**: Compare AE profile to the disease being treated; note limitation in report\n- **Drugs with boxed warnings**: Score component automatically 25\u002F25 for label warnings; prioritize boxed warning events\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Flibrary\u002Fskills\u002Ftooluniverse-adverse-event-detection","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":50,"prompt":60,"zipAvailable":61},[51,54,57],{"tool":52,"command":53},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-adverse-event-detection",{"tool":55,"command":56},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-adverse-event-detection",{"tool":58,"command":59},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-adverse-event-detection","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-adverse-event-detection\u002FSKILL.md",true,[63,69,73,77,81,87],{"path":64,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":67,"sourceHtmlUrl":68},"agents\u002Fopenai.yaml","REFERENCE","参考文档",82,"https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions\u002Fyuri-os\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmotion-design\u002Fagents\u002Fopenai.yaml",{"path":70,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":71,"sourceHtmlUrl":72},"PHASE_DETAILS.md",13623,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-adverse-event-detection\u002FPHASE_DETAILS.md",{"path":74,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":75,"sourceHtmlUrl":76},"QUICK_START.md",4211,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-adverse-event-detection\u002FQUICK_START.md",{"path":78,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":79,"sourceHtmlUrl":80},"REPORT_TEMPLATE.md",3766,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-adverse-event-detection\u002FREPORT_TEMPLATE.md",{"path":82,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":85,"sourceHtmlUrl":86},"test_adverse_event_detection.py","SCRIPT","脚本",39180,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-adverse-event-detection\u002Ftest_adverse_event_detection.py",{"path":88,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":89,"sourceHtmlUrl":90},"TOOL_REFERENCE.md",8544,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-adverse-event-detection\u002FTOOL_REFERENCE.md",[92,113,142,169,183,199],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":38},"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",[],[99,100,101,102,103,104,105,106,107,29,108,109,110,111,112],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","context","repo","injection","execution","file",{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":124,"publishedAt":38},"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",[119],{"categoryNo":120,"categoryName":121,"taxonomyType":122,"taxonomyTypeDesc":123},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[125,126,31,127,128,32,129,130,131,132,133,134,135,136,29,137,138,139,140,141],"openmm md","how","pick","linux","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":143,"name":144,"nameZh":6,"description":145,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":146,"categories":147,"keywords":154,"publishedAt":38},"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",[148,151],{"categoryNo":149,"categoryName":150,"taxonomyType":122,"taxonomyTypeDesc":123},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":152,"categoryName":153,"taxonomyType":122,"taxonomyTypeDesc":123},"01JBSEEDCAT000000000000008","测试与质量",[155,156,157,158,159,160,161,162,163,164,126,165,166,167,168],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":170,"name":171,"nameZh":6,"description":172,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":173,"categories":174,"keywords":175,"publishedAt":38},"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",[],[171,176,177,178,179,180,181,182],"setup","report","project","installation","project setup","issues","state",{"skillNo":184,"name":185,"nameZh":6,"description":186,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":187,"categories":188,"keywords":190,"publishedAt":38},"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",[189],{"categoryNo":120,"categoryName":121,"taxonomyType":122,"taxonomyTypeDesc":123},[185,191,104,192,193,194,29,195,196,197,198],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":200,"name":176,"nameZh":6,"description":201,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":202,"categories":203,"keywords":204,"publishedAt":38},"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",[],[176,178,139,205,180,206],"files","interactive"]