[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DAYKDN1QCZGBTV4MJ90RM2":3,"skill-same:01M6DAYKDN1QCZGBTV4MJ90RM2":61},{"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":36,"linkOnly":37,"markdownContent":38,"markdownBody":39,"frontMatter":40,"refName":41,"commitSha":42,"skillDirectory":43,"forksCount":14,"repositoryHtmlUrl":44,"repositoryHomepageUrl":6,"ownerHtmlUrl":45,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":46,"install":47,"resources":60},"01M6DAYKDN1QCZGBTV4MJ90RM2","tooluniverse-toxicology",null,"Assess chemical and drug toxicity via adverse outcome pathways, real-world adverse event signals, and toxicogenomic evidence. Integrates AOPWiki (AOPWiki_list_aops, AOPWiki_get_aop) for mechanism- level pathway tracing, FAERS for post-market adverse event quantification, OpenFDA for label mining, and CTD for chemical-gene-disease evidence. Produces structured toxicity reports with evidence grading (T1-T4). Use when asked about toxicity mechanisms, adverse outcome pathways, AOP mapping, FAERS signal detection, or chemical-disease relationships for drugs or environmental chemicals.","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-toxicology\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35],"tooluniverse toxicology","world","environmental","chemical","get","structured","grading","signals","relationships","tracing","Market","reports","evidence","use","outcome","list","detection","2026-11-10 10:12:30",false,"---\nname: tooluniverse-toxicology\ndescription: >\n  Assess chemical and drug toxicity via adverse outcome pathways, real-world adverse event signals,\n  and toxicogenomic evidence. Integrates AOPWiki (AOPWiki_list_aops, AOPWiki_get_aop) for mechanism-\n  level pathway tracing, FAERS for post-market adverse event quantification, OpenFDA for label mining,\n  and CTD for chemical-gene-disease evidence. Produces structured toxicity reports with evidence\n  grading (T1-T4). Use when asked about toxicity mechanisms, adverse outcome pathways, AOP mapping,\n  FAERS signal detection, or chemical-disease relationships for drugs or environmental chemicals.\n---\n\n# Toxicology Assessment via Adverse Outcome Pathways & Signal Detection\n\nSystematic toxicology analysis that links molecular initiating events (MIEs) through adverse outcome\npathways (AOPs) to apical adverse outcomes, then triangulates with real-world FAERS signals, FDA\nlabel data, and toxicogenomic associations.\n\n## Domain Reasoning\n\nToxicity has many mechanisms, and the first interpretive question is temporal: is this acute toxicity (immediate effect from a high dose) or chronic toxicity (cumulative damage from long-term low-dose exposure)? Acute and chronic toxicity operate through different mechanisms — acute hepatotoxicity may reflect direct mitochondrial damage, while chronic hepatotoxicity may involve fibrosis from repeated low-level inflammation. They also have different regulatory frameworks: acute toxicity is captured by LD50 and emergency protocols, while chronic toxicity requires long-term carcinogenicity and repeat-dose studies.\n\n## LOOK UP DON'T GUESS\n\n- Adverse outcome pathways for a chemical: query `AOPWiki_list_aops` and `AOPWiki_get_aop`; do not describe mechanisms from memory.\n- FAERS adverse event signals: retrieve from `FAERS_count_reactions_by_drug_event` and `FAERS_calculate_disproportionality`; never estimate PRR values.\n- FDA label warnings: call `DailyMed_parse_adverse_reactions` and related tools; do not state boxed warnings from memory.\n- CTD chemical-gene and chemical-disease associations: query `CTD_get_chemical_gene_interactions` and `CTD_get_chemical_diseases`; do not infer gene targets without database evidence.\n\n---\n\n## COMPUTE, DON'T DESCRIBE\nWhen analysis requires computation (statistics, data processing, scoring, enrichment), write and run Python code via Bash. Don't describe what you would do — execute it and report actual results. Use ToolUniverse tools to retrieve data, then Python (pandas, scipy, statsmodels, matplotlib) to analyze it.\n\n## When to Use This Skill\n\n**Triggers**:\n- \"What are the toxicity mechanisms for [drug\u002Fchemical]?\"\n- \"Find adverse outcome pathways for [chemical]\"\n- \"What AOPs are relevant to [target\u002Forgan\u002Feffect]?\"\n- \"FAERS signal analysis for [drug]\"\n- \"Toxicogenomic profile for [chemical]\"\n- \"What is the mechanism of hepatotoxicity \u002F cardiotoxicity \u002F neurotoxicity for [drug]?\"\n\n**Use Cases**:\n1. **AOP Tracing**: Map chemical MIE through key events to apical outcome using AOPWiki\n2. **Real-World Signal Detection**: Quantify FAERS adverse event signals with PRR\u002FROR\n3. **Label Safety Mining**: Extract FDA boxed warnings, contraindications, nonclinical toxicology\n4. **Toxicogenomics**: Chemical-gene-disease associations from CTD\n5. **Integrated Mechanism Report**: Combine AOP pathway + real-world signals into unified narrative\n\n---\n\n## KEY PRINCIPLES\n\n1. **AOP-first thinking** - Frame all toxicity in terms of MIE → Key Events → Adverse Outcome\n2. **Report-first approach** - Create report file FIRST, update progressively\n3. **Evidence grading mandatory** - T1 (regulatory\u002Fclinical) through T4 (computational\u002FAOP annotation)\n4. **Distinguish mechanism from signal** - AOPWiki = mechanism; FAERS = real-world signal\n5. **Disambiguation first** - Resolve drug\u002Fchemical identity before any queries\n6. **English-first queries** - Always use English names in tool calls\n\n---\n\n## Evidence Grading\n\n| Tier | Symbol | Criteria |\n|------|--------|----------|\n| T1 | [T1] | FDA boxed warning, clinical trial toxicity finding, regulatory label |\n| T2 | [T2] | FAERS signal PRR > 2, AOP with high biological plausibility, CTD curated |\n| T3 | [T3] | CTD inferred association, AOP annotation with moderate plausibility |\n| T4 | [T4] | Text-mined CTD entry, early-stage AOP annotation |\n\n---\n\n## Workflow Overview\n\n```\nChemical\u002FDrug Query\n|\n+-- PHASE 0: Disambiguation\n|   Resolve name -> identifiers (ChEMBL, PubChem CID, SMILES)\n|\n+-- PHASE 1: Adverse Outcome Pathway Mapping (AOPWiki)\n|   List AOPs by keyword; retrieve key events, MIEs, and biological plausibility scores\n|\n+-- PHASE 2: Real-World Adverse Event Signals (FAERS)\n|   Top reactions by drug; disproportionality (PRR); serious event filter\n|\n+-- PHASE 3: FDA Label Safety Mining\n|   Boxed warnings, contraindications, nonclinical toxicology, adverse reactions\n|\n+-- PHASE 4: Toxicogenomics (CTD)\n|   Chemical-gene interactions; chemical-disease associations\n|\n+-- SYNTHESIS: Integrated Toxicology Report\n    AOP-linked mechanism + FAERS signal + CTD gene targets + Risk classification\n```\n\n---\n\n## Phase 0: Disambiguation\n\n**Objective**: Establish compound identity before any database queries.\n\nTools:\n- `PubChem_get_CID_by_compound_name` (`name`: str) — get CID + SMILES\n- `ChEMBL_search_drugs` (`query`: str) — get ChEMBL ID and max phase\n\nCapture: generic name, SMILES, PubChem CID, ChEMBL ID, drug class.\n\n---\n\n## Phase 1: Adverse Outcome Pathway Mapping\n\n**Objective**: Find AOPs relevant to the chemical's known or suspected toxicity mechanisms.\n\n### Tools\n\n**AOPWiki_list_aops**:\n- **Input**: `keyword` (str) — e.g., organ (\"liver\", \"kidney\"), effect (\"apoptosis\", \"inflammation\"), or target (\"AhR\", \"PPARalpha\")\n- **Output**: List of AOP IDs, titles, and short descriptions\n- **Use**: Discovery scan to identify candidate AOPs\n\n**AOPWiki_get_aop**:\n- **Input**: `aop_id` (int) — ID from list_aops result\n- **Output**: Full AOP details including MIE, key events (KEs), key event relationships (KERs), biological plausibility, and weight-of-evidence\n- **Use**: Retrieve mechanistic pathway details for selected AOPs\n\n### Workflow\n\n1. Query `AOPWiki_list_aops` with organ-level keyword (e.g., \"hepatotoxicity\", \"nephrotoxicity\")\n2. Query again with mechanism-level keyword (e.g., \"oxidative stress\", \"mitochondria\")\n3. Select top 3-5 most relevant AOPs by title relevance\n4. Call `AOPWiki_get_aop` for each selected AOP\n5. Extract: MIE (molecular initiating event), key events in order, apical adverse outcome, biological plausibility score\n\n### Decision Logic\n\n- **AOP found**: Extract full pathway; note plausibility level (high\u002Fmoderate\u002Flow)\n- **No direct AOP match**: Try broader organ or mechanism terms; document as \"no AOP directly mapped\"\n- **Multiple AOPs**: Report all; highlight shared key events as high-confidence mechanisms\n\n### AOP Table Format\n\n| AOP ID | Title | MIE | Apical Outcome | Plausibility |\n|--------|-------|-----|----------------|-------------|\n| 123 | ... | ... | ... | High |\n\n---\n\n## Phase 2: Real-World Adverse Event Signals (FAERS)\n\n**Objective**: Quantify observed adverse events with statistical signal measures.\n\n### Tools\n\n**FAERS_count_reactions_by_drug_event**:\n- **Input**: `drug_name` (str), `limit` (int, default 50)\n- **Output**: Top adverse reactions with counts\n- **Note**: param is `drug_name` not `drug`\n\n**FAERS_calculate_disproportionality**:\n- **Input**: `drug_name` (str), `reaction_meddra_pt` (str)\n- **Output**: PRR, ROR, IC with confidence intervals\n\n**FAERS_filter_serious_events**:\n- **Input**: `drug_name` (str), `serious_type` (str: \"death\", \"hospitalization\", \"life-threatening\")\n- **Output**: Serious event count and case details\n\n**FAERS_stratify_by_demographics**:\n- **Input**: `drug_name` (str), `reaction_meddra_pt` (str)\n- **Output**: Age\u002Fsex breakdown for specific reaction\n\n### Workflow\n\n1. Get top 25 reactions via `FAERS_count_reactions_by_drug_event`\n2. Filter to organ-system clusters matching the AOP outcomes from Phase 1\n3. Calculate PRR for top 10 reactions via `FAERS_calculate_disproportionality`\n4. Check serious events (deaths, hospitalizations) for highest-PRR reactions\n\n### Signal Thresholds\n\n| Signal Strength | PRR | Case Count |\n|----------------|-----|------------|\n| Strong | > 3.0 | >= 5 |\n| Moderate | 2.0-3.0 | >= 3 |\n| Weak | 1.5-2.0 | >= 3 |\n| None | \u003C 1.5 | any |\n\n---\n\n## Phase 3: FDA Label Safety Mining\n\n**Objective**: Extract regulatory safety findings from approved drug labels.\n\n### Tools\n\n- `DailyMed_parse_adverse_reactions` (`drug_name`: str)\n- `DailyMed_parse_contraindications` (`drug_name`: str)\n- `DailyMed_parse_clinical_pharmacology` (`drug_name`: str)\n- `DailyMed_parse_drug_interactions` (`drug_name`: str)\n\n**Note**: These tools apply to FDA-approved drugs only. Environmental chemicals will have no label data — document explicitly.\n\n### Workflow\n\n1. Extract adverse reactions and note which match FAERS signals\n2. Extract contraindications (highest evidence tier [T1])\n3. Note pharmacological mechanism from clinical pharmacology section\n\n---\n\n## Phase 4: Toxicogenomics (CTD)\n\n**Objective**: Map chemical-gene interactions and chemical-disease associations.\n\n### Tools\n\n**CTD_get_chemical_gene_interactions**:\n- **Input**: `input_terms` (str) — chemical name or MeSH ID\n- **Output**: Gene targets with interaction type (increases\u002Fdecreases expression)\n- **Use**: Find molecular targets mediating toxicity\n\n**CTD_get_chemical_diseases**:\n- **Input**: `input_terms` (str) — chemical name or MeSH ID\n- **Output**: Disease associations with evidence type (curated\u002Finferred)\n- **Use**: Find downstream disease endpoints\n\n### Workflow\n\n1. Query CTD with compound name; note curated (higher confidence) vs inferred entries\n2. Cross-reference gene targets with Phase 1 AOP key events\n3. Note which CTD disease endpoints match AOP apical outcomes\n\n---\n\n## Synthesis: Integrated Toxicology Report\n\n**Structure**:\n\n```\n# Toxicology Report: [Compound Name]\n**Generated**: YYYY-MM-DD\n\n## Executive Summary\nRisk tier: CRITICAL \u002F HIGH \u002F MEDIUM \u002F LOW \u002F INSUFFICIENT DATA\nKey finding summary (2-3 sentences)\n\n## 1. Compound Identity\n(disambiguation table)\n\n## 2. Adverse Outcome Pathways [T3-T4]\n(AOP table; pathway diagrams in text form)\n\n## 3. Real-World Adverse Event Signals [T1-T2]\n(FAERS top reactions + PRR table + serious events)\n\n## 4. FDA Label Safety [T1]\n(boxed warnings, contraindications, adverse reactions)\n\n## 5. Toxicogenomics [T2-T4]\n(CTD gene targets + disease associations)\n\n## 6. Mechanistic Integration\n(How AOP key events map to observed FAERS signals and CTD gene targets)\n\n## 7. Risk Classification\n(Final tier with rationale)\n\n## Data Gaps & Limitations\n(Missing data, confidence caveats)\n```\n\n### Risk Classification\n\n| Tier | Criteria |\n|------|----------|\n| CRITICAL | FDA boxed warning OR FAERS PRR > 5 with deaths OR multiple T1 findings |\n| HIGH | FAERS PRR 3-5 serious events OR FDA warning (non-boxed) OR high-plausibility AOP |\n| MEDIUM | FAERS PRR 2-3 OR CTD curated associations OR moderate-plausibility AOP |\n| LOW | All signals \u003C PRR 2; no regulatory warnings; low-plausibility AOP only |\n| INSUFFICIENT DATA | Fewer than 3 phases returned usable data |\n\n---\n\n## Fallback Chains\n\n| Primary Tool | Fallback 1 | Fallback 2 |\n|--------------|------------|------------|\n| `AOPWiki_list_aops` | Broaden keyword | Search by organ system |\n| `FAERS_count_reactions_by_drug_event` | `OpenFDA_search_drug_events` | Literature search |\n| `DailyMed_parse_adverse_reactions` | `OpenFDA_search_drug_events` | FAERS serious events |\n| `CTD_get_chemical_diseases` | `CTD_get_chemical_gene_interactions` | PubMed search |\n\n---\n\n## Tool Parameter Reference (Critical)\n\n| Tool | WRONG | CORRECT |\n|------|-------|---------|\n| `FAERS_count_reactions_by_drug_event` | `drug` | `drug_name` |\n| `AOPWiki_list_aops` | `query` | `keyword` |\n| `CTD_get_chemical_gene_interactions` | `chemical` | `input_terms` |\n| `CTD_get_chemical_diseases` | `chemical` | `input_terms` |\n\n---\n\n## Limitations\n\n- **AOPWiki**: AOPs are in development; many lack high plausibility scores\n- **FAERS**: Observational data; confounding by indication; underreporting bias\n- **CTD**: Inferred associations have high false-positive rate\n- **DailyMed**: FDA-approved drugs only; no environmental chemical coverage\n- **Environmental chemicals**: Primarily Phase 1 (AOP) + Phase 4 (CTD) data available\n\n---\n\n## References\n\n- AOPWiki: https:\u002F\u002Faopwiki.org\n- FAERS: https:\u002F\u002Fwww.fda.gov\u002Fdrugs\u002Fquestions-and-answers-fdas-adverse-event-reporting-system-faers\n- CTD: http:\u002F\u002Fctdbase.org\n- DailyMed: https:\u002F\u002Fdailymed.nlm.nih.gov\n- OpenFDA: https:\u002F\u002Fopen.fda.gov\n","# Toxicology Assessment via Adverse Outcome Pathways & Signal Detection\n\nSystematic toxicology analysis that links molecular initiating events (MIEs) through adverse outcome\npathways (AOPs) to apical adverse outcomes, then triangulates with real-world FAERS signals, FDA\nlabel data, and toxicogenomic associations.\n\n## Domain Reasoning\n\nToxicity has many mechanisms, and the first interpretive question is temporal: is this acute toxicity (immediate effect from a high dose) or chronic toxicity (cumulative damage from long-term low-dose exposure)? Acute and chronic toxicity operate through different mechanisms — acute hepatotoxicity may reflect direct mitochondrial damage, while chronic hepatotoxicity may involve fibrosis from repeated low-level inflammation. They also have different regulatory frameworks: acute toxicity is captured by LD50 and emergency protocols, while chronic toxicity requires long-term carcinogenicity and repeat-dose studies.\n\n## LOOK UP DON'T GUESS\n\n- Adverse outcome pathways for a chemical: query `AOPWiki_list_aops` and `AOPWiki_get_aop`; do not describe mechanisms from memory.\n- FAERS adverse event signals: retrieve from `FAERS_count_reactions_by_drug_event` and `FAERS_calculate_disproportionality`; never estimate PRR values.\n- FDA label warnings: call `DailyMed_parse_adverse_reactions` and related tools; do not state boxed warnings from memory.\n- CTD chemical-gene and chemical-disease associations: query `CTD_get_chemical_gene_interactions` and `CTD_get_chemical_diseases`; do not infer gene targets without database evidence.\n\n---\n\n## COMPUTE, DON'T DESCRIBE\nWhen analysis requires computation (statistics, data processing, scoring, enrichment), write and run Python code via Bash. Don't describe what you would do — execute it and report actual results. Use ToolUniverse tools to retrieve data, then Python (pandas, scipy, statsmodels, matplotlib) to analyze it.\n\n## When to Use This Skill\n\n**Triggers**:\n- \"What are the toxicity mechanisms for [drug\u002Fchemical]?\"\n- \"Find adverse outcome pathways for [chemical]\"\n- \"What AOPs are relevant to [target\u002Forgan\u002Feffect]?\"\n- \"FAERS signal analysis for [drug]\"\n- \"Toxicogenomic profile for [chemical]\"\n- \"What is the mechanism of hepatotoxicity \u002F cardiotoxicity \u002F neurotoxicity for [drug]?\"\n\n**Use Cases**:\n1. **AOP Tracing**: Map chemical MIE through key events to apical outcome using AOPWiki\n2. **Real-World Signal Detection**: Quantify FAERS adverse event signals with PRR\u002FROR\n3. **Label Safety Mining**: Extract FDA boxed warnings, contraindications, nonclinical toxicology\n4. **Toxicogenomics**: Chemical-gene-disease associations from CTD\n5. **Integrated Mechanism Report**: Combine AOP pathway + real-world signals into unified narrative\n\n---\n\n## KEY PRINCIPLES\n\n1. **AOP-first thinking** - Frame all toxicity in terms of MIE → Key Events → Adverse Outcome\n2. **Report-first approach** - Create report file FIRST, update progressively\n3. **Evidence grading mandatory** - T1 (regulatory\u002Fclinical) through T4 (computational\u002FAOP annotation)\n4. **Distinguish mechanism from signal** - AOPWiki = mechanism; FAERS = real-world signal\n5. **Disambiguation first** - Resolve drug\u002Fchemical identity before any queries\n6. **English-first queries** - Always use English names in tool calls\n\n---\n\n## Evidence Grading\n\n| Tier | Symbol | Criteria |\n|------|--------|----------|\n| T1 | [T1] | FDA boxed warning, clinical trial toxicity finding, regulatory label |\n| T2 | [T2] | FAERS signal PRR > 2, AOP with high biological plausibility, CTD curated |\n| T3 | [T3] | CTD inferred association, AOP annotation with moderate plausibility |\n| T4 | [T4] | Text-mined CTD entry, early-stage AOP annotation |\n\n---\n\n## Workflow Overview\n\n```\nChemical\u002FDrug Query\n|\n+-- PHASE 0: Disambiguation\n|   Resolve name -> identifiers (ChEMBL, PubChem CID, SMILES)\n|\n+-- PHASE 1: Adverse Outcome Pathway Mapping (AOPWiki)\n|   List AOPs by keyword; retrieve key events, MIEs, and biological plausibility scores\n|\n+-- PHASE 2: Real-World Adverse Event Signals (FAERS)\n|   Top reactions by drug; disproportionality (PRR); serious event filter\n|\n+-- PHASE 3: FDA Label Safety Mining\n|   Boxed warnings, contraindications, nonclinical toxicology, adverse reactions\n|\n+-- PHASE 4: Toxicogenomics (CTD)\n|   Chemical-gene interactions; chemical-disease associations\n|\n+-- SYNTHESIS: Integrated Toxicology Report\n    AOP-linked mechanism + FAERS signal + CTD gene targets + Risk classification\n```\n\n---\n\n## Phase 0: Disambiguation\n\n**Objective**: Establish compound identity before any database queries.\n\nTools:\n- `PubChem_get_CID_by_compound_name` (`name`: str) — get CID + SMILES\n- `ChEMBL_search_drugs` (`query`: str) — get ChEMBL ID and max phase\n\nCapture: generic name, SMILES, PubChem CID, ChEMBL ID, drug class.\n\n---\n\n## Phase 1: Adverse Outcome Pathway Mapping\n\n**Objective**: Find AOPs relevant to the chemical's known or suspected toxicity mechanisms.\n\n### Tools\n\n**AOPWiki_list_aops**:\n- **Input**: `keyword` (str) — e.g., organ (\"liver\", \"kidney\"), effect (\"apoptosis\", \"inflammation\"), or target (\"AhR\", \"PPARalpha\")\n- **Output**: List of AOP IDs, titles, and short descriptions\n- **Use**: Discovery scan to identify candidate AOPs\n\n**AOPWiki_get_aop**:\n- **Input**: `aop_id` (int) — ID from list_aops result\n- **Output**: Full AOP details including MIE, key events (KEs), key event relationships (KERs), biological plausibility, and weight-of-evidence\n- **Use**: Retrieve mechanistic pathway details for selected AOPs\n\n### Workflow\n\n1. Query `AOPWiki_list_aops` with organ-level keyword (e.g., \"hepatotoxicity\", \"nephrotoxicity\")\n2. Query again with mechanism-level keyword (e.g., \"oxidative stress\", \"mitochondria\")\n3. Select top 3-5 most relevant AOPs by title relevance\n4. Call `AOPWiki_get_aop` for each selected AOP\n5. Extract: MIE (molecular initiating event), key events in order, apical adverse outcome, biological plausibility score\n\n### Decision Logic\n\n- **AOP found**: Extract full pathway; note plausibility level (high\u002Fmoderate\u002Flow)\n- **No direct AOP match**: Try broader organ or mechanism terms; document as \"no AOP directly mapped\"\n- **Multiple AOPs**: Report all; highlight shared key events as high-confidence mechanisms\n\n### AOP Table Format\n\n| AOP ID | Title | MIE | Apical Outcome | Plausibility |\n|--------|-------|-----|----------------|-------------|\n| 123 | ... | ... | ... | High |\n\n---\n\n## Phase 2: Real-World Adverse Event Signals (FAERS)\n\n**Objective**: Quantify observed adverse events with statistical signal measures.\n\n### Tools\n\n**FAERS_count_reactions_by_drug_event**:\n- **Input**: `drug_name` (str), `limit` (int, default 50)\n- **Output**: Top adverse reactions with counts\n- **Note**: param is `drug_name` not `drug`\n\n**FAERS_calculate_disproportionality**:\n- **Input**: `drug_name` (str), `reaction_meddra_pt` (str)\n- **Output**: PRR, ROR, IC with confidence intervals\n\n**FAERS_filter_serious_events**:\n- **Input**: `drug_name` (str), `serious_type` (str: \"death\", \"hospitalization\", \"life-threatening\")\n- **Output**: Serious event count and case details\n\n**FAERS_stratify_by_demographics**:\n- **Input**: `drug_name` (str), `reaction_meddra_pt` (str)\n- **Output**: Age\u002Fsex breakdown for specific reaction\n\n### Workflow\n\n1. Get top 25 reactions via `FAERS_count_reactions_by_drug_event`\n2. Filter to organ-system clusters matching the AOP outcomes from Phase 1\n3. Calculate PRR for top 10 reactions via `FAERS_calculate_disproportionality`\n4. Check serious events (deaths, hospitalizations) for highest-PRR reactions\n\n### Signal Thresholds\n\n| Signal Strength | PRR | Case Count |\n|----------------|-----|------------|\n| Strong | > 3.0 | >= 5 |\n| Moderate | 2.0-3.0 | >= 3 |\n| Weak | 1.5-2.0 | >= 3 |\n| None | \u003C 1.5 | any |\n\n---\n\n## Phase 3: FDA Label Safety Mining\n\n**Objective**: Extract regulatory safety findings from approved drug labels.\n\n### Tools\n\n- `DailyMed_parse_adverse_reactions` (`drug_name`: str)\n- `DailyMed_parse_contraindications` (`drug_name`: str)\n- `DailyMed_parse_clinical_pharmacology` (`drug_name`: str)\n- `DailyMed_parse_drug_interactions` (`drug_name`: str)\n\n**Note**: These tools apply to FDA-approved drugs only. Environmental chemicals will have no label data — document explicitly.\n\n### Workflow\n\n1. Extract adverse reactions and note which match FAERS signals\n2. Extract contraindications (highest evidence tier [T1])\n3. Note pharmacological mechanism from clinical pharmacology section\n\n---\n\n## Phase 4: Toxicogenomics (CTD)\n\n**Objective**: Map chemical-gene interactions and chemical-disease associations.\n\n### Tools\n\n**CTD_get_chemical_gene_interactions**:\n- **Input**: `input_terms` (str) — chemical name or MeSH ID\n- **Output**: Gene targets with interaction type (increases\u002Fdecreases expression)\n- **Use**: Find molecular targets mediating toxicity\n\n**CTD_get_chemical_diseases**:\n- **Input**: `input_terms` (str) — chemical name or MeSH ID\n- **Output**: Disease associations with evidence type (curated\u002Finferred)\n- **Use**: Find downstream disease endpoints\n\n### Workflow\n\n1. Query CTD with compound name; note curated (higher confidence) vs inferred entries\n2. Cross-reference gene targets with Phase 1 AOP key events\n3. Note which CTD disease endpoints match AOP apical outcomes\n\n---\n\n## Synthesis: Integrated Toxicology Report\n\n**Structure**:\n\n```\n# Toxicology Report: [Compound Name]\n**Generated**: YYYY-MM-DD\n\n## Executive Summary\nRisk tier: CRITICAL \u002F HIGH \u002F MEDIUM \u002F LOW \u002F INSUFFICIENT DATA\nKey finding summary (2-3 sentences)\n\n## 1. Compound Identity\n(disambiguation table)\n\n## 2. Adverse Outcome Pathways [T3-T4]\n(AOP table; pathway diagrams in text form)\n\n## 3. Real-World Adverse Event Signals [T1-T2]\n(FAERS top reactions + PRR table + serious events)\n\n## 4. FDA Label Safety [T1]\n(boxed warnings, contraindications, adverse reactions)\n\n## 5. Toxicogenomics [T2-T4]\n(CTD gene targets + disease associations)\n\n## 6. Mechanistic Integration\n(How AOP key events map to observed FAERS signals and CTD gene targets)\n\n## 7. Risk Classification\n(Final tier with rationale)\n\n## Data Gaps & Limitations\n(Missing data, confidence caveats)\n```\n\n### Risk Classification\n\n| Tier | Criteria |\n|------|----------|\n| CRITICAL | FDA boxed warning OR FAERS PRR > 5 with deaths OR multiple T1 findings |\n| HIGH | FAERS PRR 3-5 serious events OR FDA warning (non-boxed) OR high-plausibility AOP |\n| MEDIUM | FAERS PRR 2-3 OR CTD curated associations OR moderate-plausibility AOP |\n| LOW | All signals \u003C PRR 2; no regulatory warnings; low-plausibility AOP only |\n| INSUFFICIENT DATA | Fewer than 3 phases returned usable data |\n\n---\n\n## Fallback Chains\n\n| Primary Tool | Fallback 1 | Fallback 2 |\n|--------------|------------|------------|\n| `AOPWiki_list_aops` | Broaden keyword | Search by organ system |\n| `FAERS_count_reactions_by_drug_event` | `OpenFDA_search_drug_events` | Literature search |\n| `DailyMed_parse_adverse_reactions` | `OpenFDA_search_drug_events` | FAERS serious events |\n| `CTD_get_chemical_diseases` | `CTD_get_chemical_gene_interactions` | PubMed search |\n\n---\n\n## Tool Parameter Reference (Critical)\n\n| Tool | WRONG | CORRECT |\n|------|-------|---------|\n| `FAERS_count_reactions_by_drug_event` | `drug` | `drug_name` |\n| `AOPWiki_list_aops` | `query` | `keyword` |\n| `CTD_get_chemical_gene_interactions` | `chemical` | `input_terms` |\n| `CTD_get_chemical_diseases` | `chemical` | `input_terms` |\n\n---\n\n## Limitations\n\n- **AOPWiki**: AOPs are in development; many lack high plausibility scores\n- **FAERS**: Observational data; confounding by indication; underreporting bias\n- **CTD**: Inferred associations have high false-positive rate\n- **DailyMed**: FDA-approved drugs only; no environmental chemical coverage\n- **Environmental chemicals**: Primarily Phase 1 (AOP) + Phase 4 (CTD) data available\n\n---\n\n## References\n\n- AOPWiki: https:\u002F\u002Faopwiki.org\n- FAERS: https:\u002F\u002Fwww.fda.gov\u002Fdrugs\u002Fquestions-and-answers-fdas-adverse-event-reporting-system-faers\n- CTD: http:\u002F\u002Fctdbase.org\n- DailyMed: https:\u002F\u002Fdailymed.nlm.nih.gov\n- OpenFDA: https:\u002F\u002Fopen.fda.gov\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Flibrary\u002Fskills\u002Ftooluniverse-toxicology","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":48,"prompt":58,"zipAvailable":59},[49,52,55],{"tool":50,"command":51},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-toxicology",{"tool":53,"command":54},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-toxicology",{"tool":56,"command":57},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-toxicology","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-toxicology\u002FSKILL.md",true,[],[62,83,114,141,155,171],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":36},"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",[],[69,70,71,72,73,74,75,76,77,32,78,79,80,81,82],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","context","repo","injection","execution","file",{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":94,"publishedAt":36},"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",[89],{"categoryNo":90,"categoryName":91,"taxonomyType":92,"taxonomyTypeDesc":93},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[95,96,97,98,99,100,101,102,103,104,105,106,107,108,32,109,110,111,112,113],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":126,"publishedAt":36},"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",[120,123],{"categoryNo":121,"categoryName":122,"taxonomyType":92,"taxonomyTypeDesc":93},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":124,"categoryName":125,"taxonomyType":92,"taxonomyTypeDesc":93},"01JBSEEDCAT000000000000008","测试与质量",[127,128,129,130,131,132,133,134,135,136,96,137,138,139,140],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":142,"name":143,"nameZh":6,"description":144,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":145,"categories":146,"keywords":147,"publishedAt":36},"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",[],[143,148,149,150,151,152,153,154],"setup","report","project","installation","project setup","issues","state",{"skillNo":156,"name":157,"nameZh":6,"description":158,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":159,"categories":160,"keywords":162,"publishedAt":36},"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",[161],{"categoryNo":90,"categoryName":91,"taxonomyType":92,"taxonomyTypeDesc":93},[157,163,74,164,165,166,32,167,168,169,170],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":172,"name":148,"nameZh":6,"description":173,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":174,"categories":175,"keywords":176,"publishedAt":36},"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",[],[148,150,111,177,152,178],"files","interactive"]