[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DASBCKE18Q739MTMY12FEN":3,"skill-same:01M6DASBCKE18Q739MTMY12FEN":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":28,"linkOnly":29,"markdownContent":30,"markdownBody":31,"frontMatter":32,"refName":33,"commitSha":34,"skillDirectory":35,"forksCount":14,"repositoryHtmlUrl":36,"repositoryHomepageUrl":6,"ownerHtmlUrl":37,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":38,"install":39,"resources":52},"01M6DASBCKE18Q739MTMY12FEN","tooluniverse-infectious-disease",null,"Rapid pathogen characterization and drug repurposing analysis for infectious disease outbreaks. Identifies pathogen taxonomy, essential proteins, predicts structures, and screens existing drugs via docking. Use when facing novel pathogens, emerging infections, or needing rapid therapeutic options during outbreaks.","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-infectious-disease\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27],"tooluniverse infectious disease","analysis","taxonomy","use","options","pathogens","proteins","docking","essential","2026-11-10 10:12:30",false,"---\nname: tooluniverse-infectious-disease\ndescription: Rapid pathogen characterization and drug repurposing analysis for infectious disease outbreaks. Identifies pathogen taxonomy, essential proteins, predicts structures, and screens existing drugs via docking. Use when facing novel pathogens, emerging infections, or needing rapid therapeutic options during outbreaks.\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# Infectious Disease Outbreak Intelligence\n\nRapid response system for emerging pathogens using taxonomy analysis, target identification, structure prediction, and computational drug repurposing.\n\n**KEY PRINCIPLES**:\n1. **Speed is critical** - Optimize for rapid actionable intelligence\n2. **Target essential proteins** - Focus on conserved, essential viral\u002Fbacterial proteins\n3. **Leverage existing drugs** - Prioritize FDA-approved compounds for repurposing\n4. **Structure-guided** - Use NvidiaNIM for rapid structure prediction and docking\n5. **Evidence-graded** - Grade repurposing candidates by evidence strength\n6. **Actionable output** - Prioritized drug candidates with rationale\n7. **English-first queries** - Always use English terms in tool calls; respond in user's language\n\n**REASONING STRATEGY — Start Here**:\nStart with pathogen identification: What type of organism? (virus, bacteria, fungus, parasite). Then ask:\n- What are the essential proteins? (required for replication or viability — cannot be mutated away)\n- Which are surface-exposed? (accessible to drugs and antibodies)\n- Which are conserved across strains? (targeting conserved regions prevents resistance escape)\nThese three questions define your drug targets and vaccine candidates. Organisms in the same genus share targets — look up drug precedent for related pathogens before predicting from scratch.\n\n**LOOK UP DON'T GUESS**: Never assume a pathogen's taxonomy, genome size, or protein function. Always call `BVBRC_search_taxonomy` or `UniProt_search` first. Even well-known pathogens have strains with different drug susceptibility profiles — look up the specific strain when known.\n\n---\n\n## When to Use\n\nApply when user asks:\n- \"New pathogen detected - what drugs might work?\"\n- \"Emerging virus [X] - therapeutic options?\"\n- \"Drug repurposing candidates for [pathogen]\"\n- \"What do we know about [novel coronavirus\u002Fbacteria]?\"\n- \"Essential targets in [pathogen] for drug development\"\n- \"Can we repurpose [drug] against [pathogen]?\"\n\n---\n\n## Critical Workflow Requirements\n\n### 1. Report-First Approach (MANDATORY)\n\n1. Create `[PATHOGEN]_outbreak_intelligence.md` FIRST with section headers\n2. Progressively update as data is gathered\n3. Output separate files: `[PATHOGEN]_drug_candidates.csv`, `[PATHOGEN]_target_proteins.csv`\n\n### 2. Citation Requirements (MANDATORY)\n\nEvery finding must have inline source attribution:\n```markdown\n### Target: RNA-dependent RNA polymerase (RdRp)\n- **UniProt**: P0DTD1 (NSP12)\n- **Essentiality**: Required for replication\n*Source: UniProt via `UniProt_search`, literature review*\n```\n\n---\n\n## Phase 0: Tool Verification\n\n### Known Parameter Corrections\n\n| Tool | WRONG Parameter | CORRECT Parameter |\n|------|-----------------|-------------------|\n| `NCBIDatasets_get_taxonomy` | `name` | `tax_id` (integer) or use `BVBRC_search_taxonomy` for keyword search |\n| `UniProt_search` | `name` | `query` |\n| `ChEMBL_search_targets` | `query`, `target` | `pref_name__contains` (substring match) |\n| `get_diffdock_info` | `protein_file` | `protein` (content) |\n| `drugbank_full_search` | _(may fail)_ | Use `drugbank_vocab_search` as primary DrugBank lookup |\n\n> **PubMed tip**: Use `sort=\"relevance\"` (default) not `sort=\"pub_date\"` — date-sorted queries can return empty for narrow topics. Tool name: `PubMed_search_articles`.\n> **FDA labels**: Use `FDA_get_drug_label_info_by_field_value` with targeted `return_fields` to avoid oversized responses from `OpenFDA_search_drug_labels`.\n\n---\n\n## Workflow Overview\n\n```\nPhase 1: Pathogen Identification\n├── Taxonomic classification (NCBI Taxonomy)\n├── Closest relatives (for knowledge transfer)\n├── Genome\u002Fproteome availability\n└── OUTPUT: Pathogen profile\n    |\nPhase 2: Target Identification\n├── Essential genes\u002Fproteins (UniProt)\n├── Conservation across strains\n├── Druggability assessment (ChEMBL)\n└── OUTPUT: Prioritized target list (scored by essentiality\u002Fconservation\u002Fdruggability\u002Fprecedent)\n    |\nPhase 3: Structure Prediction (NvidiaNIM)\n├── AlphaFold2\u002FESMFold for targets\n├── Binding site identification\n├── Quality assessment (pLDDT)\n└── OUTPUT: Target structures (docking-ready if pLDDT > 70)\n    |\nPhase 4: Drug Repurposing Screen\n├── Approved drugs for related pathogens (ChEMBL)\n├── Broad-spectrum antivirals\u002Fantibiotics\n├── Docking screen (get_diffdock_info)\n└── OUTPUT: Ranked candidate drugs\n    |\nPhase 4.5: Pathway Analysis\n├── KEGG: Pathogen metabolism pathways\n├── Essential metabolic targets\n├── Host-pathogen interaction pathways\n└── OUTPUT: Pathway-based drug targets\n    |\nPhase 5: Literature Intelligence\n├── PubMed: Published outbreak reports\n├── BioRxiv\u002FMedRxiv: Recent preprints (CRITICAL for outbreaks)\n├── ArXiv: Computational\u002FML preprints\n├── OpenAlex: Citation tracking\n├── ClinicalTrials.gov: Active trials\n└── OUTPUT: Evidence synthesis\n    |\nPhase 6: Report Synthesis\n├── Top drug candidates with evidence grades\n├── Clinical trial opportunities\n├── Recommended immediate actions\n└── OUTPUT: Final report\n```\n\n---\n\n## Phase Summaries\n\n### Phase 1: Pathogen Identification\nClassify via NCBI Taxonomy (query param). Identify related pathogens with existing drugs for knowledge transfer. Determine genome\u002Fproteome availability.\n\n**Knowledge transfer principle**: Drugs effective against related pathogens are the highest-priority repurposing candidates. A protease inhibitor for SARS-CoV-1 is immediately relevant to SARS-CoV-2. Look up the related pathogen's approved drugs in ChEMBL before generating candidates from first principles.\n\n### Phase 2: Target Identification\nSearch UniProt for pathogen proteins (reviewed). Check ChEMBL for drug precedent. Score targets by: Essentiality (30%), Conservation (25%), Druggability (25%), Drug precedent (20%). Aim for 5+ targets.\n\n### Phase 3: Structure Prediction\nUse NvidiaNIM AlphaFold2 for top 3 targets. Assess pLDDT confidence. Only dock structures with pLDDT > 70 (active site > 90 preferred). Fallback: alphafold_get_prediction or ESMFold_predict_structure.\n\n### Phase 4: Drug Repurposing Screen\nSource candidates from: related pathogen drugs, broad-spectrum antivirals, target class drugs (DGIdb). Dock top 20+ candidates via get_diffdock_info. Rank by docking score and evidence tier.\n\n### Phase 4.5: Pathway Analysis\nUse KEGG to identify essential metabolic pathways. Map host-pathogen interaction points. Identify pathway-based drug targets beyond direct protein inhibition.\n\n### Phase 5: Literature Intelligence\nSearch PubMed (peer-reviewed), BioRxiv\u002FMedRxiv (preprints - critical for outbreaks), ArXiv (computational), ClinicalTrials.gov (active trials). Track citations via OpenAlex. Note: preprints are NOT peer-reviewed.\n\n### Phase 6: Report Synthesis\nAggregate all findings into final report. Grade every candidate. Provide 3+ immediate actions, clinical trial opportunities, and research priorities.\n\n---\n\n## Evidence Grading\n\n| Tier | Symbol | Criteria | Example |\n|------|--------|----------|---------|\n| **T1** | [T1] | FDA approved for this pathogen | Remdesivir for COVID |\n| **T2** | [T2] | Clinical trial evidence OR approved for related pathogen | Favipiravir |\n| **T3** | [T3] | In vitro activity OR strong docking + mechanism | Sofosbuvir |\n| **T4** | [T4] | Computational prediction only | Novel docking hits |\n\n---\n\n## Completeness Checklist\n\n### Phase 1: Pathogen ID\n- [ ] Taxonomic classification complete\n- [ ] Related pathogens identified\n- [ ] Genome\u002Fproteome availability noted\n\n### Phase 2: Targets\n- [ ] 5+ targets identified\n- [ ] Essentiality documented\n- [ ] Conservation assessed\n- [ ] Drug precedent checked\n\n### Phase 3: Structures\n- [ ] Structures predicted for top 3 targets\n- [ ] pLDDT confidence reported\n- [ ] Binding sites identified\n\n### Phase 4: Drug Screen\n- [ ] 20+ candidates screened\n- [ ] FDA-approved drugs prioritized\n- [ ] Docking scores reported\n- [ ] Top 5 candidates detailed\n\n### Phase 5: Literature\n- [ ] Recent papers summarized\n- [ ] Active trials listed\n- [ ] Resistance data noted\n\n### Phase 6: Recommendations\n- [ ] 3+ immediate actions\n- [ ] Clinical trial opportunities\n- [ ] Research priorities\n\n---\n\n## Fallback Chains\n\n| Primary Tool | Fallback 1 | Fallback 2 |\n|--------------|------------|------------|\n| `NvidiaNIM_alphafold2` | `alphafold_get_prediction` | `ESMFold_predict_structure` |\n| `get_diffdock_info` | `NvidiaNIM_boltz2` | Manual docking |\n| `NCBIDatasets_suggest_taxonomy` | `UniProtTaxonomy_get_taxon` | Manual classification |\n| `ChEMBL_search_drugs` | `drugbank_vocab_search` | PubChem bioassays |\n\n---\n\n## References\n\n| File | Contents |\n|------|----------|\n| [TOOLS_REFERENCE.md](TOOLS_REFERENCE.md) | Complete tool documentation |\n| [phase_details.md](phase_details.md) | Detailed code examples and procedures for each phase |\n| [report_template.md](report_template.md) | Report template with section headers, checklist, and evidence grading |\n| [CHECKLIST.md](CHECKLIST.md) | Pre-delivery verification checklist (quality, citations, docking) |\n| [EXAMPLES.md](EXAMPLES.md) | Full worked examples (coronavirus, CRKP, limited-info scenarios) |\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# Infectious Disease Outbreak Intelligence\n\nRapid response system for emerging pathogens using taxonomy analysis, target identification, structure prediction, and computational drug repurposing.\n\n**KEY PRINCIPLES**:\n1. **Speed is critical** - Optimize for rapid actionable intelligence\n2. **Target essential proteins** - Focus on conserved, essential viral\u002Fbacterial proteins\n3. **Leverage existing drugs** - Prioritize FDA-approved compounds for repurposing\n4. **Structure-guided** - Use NvidiaNIM for rapid structure prediction and docking\n5. **Evidence-graded** - Grade repurposing candidates by evidence strength\n6. **Actionable output** - Prioritized drug candidates with rationale\n7. **English-first queries** - Always use English terms in tool calls; respond in user's language\n\n**REASONING STRATEGY — Start Here**:\nStart with pathogen identification: What type of organism? (virus, bacteria, fungus, parasite). Then ask:\n- What are the essential proteins? (required for replication or viability — cannot be mutated away)\n- Which are surface-exposed? (accessible to drugs and antibodies)\n- Which are conserved across strains? (targeting conserved regions prevents resistance escape)\nThese three questions define your drug targets and vaccine candidates. Organisms in the same genus share targets — look up drug precedent for related pathogens before predicting from scratch.\n\n**LOOK UP DON'T GUESS**: Never assume a pathogen's taxonomy, genome size, or protein function. Always call `BVBRC_search_taxonomy` or `UniProt_search` first. Even well-known pathogens have strains with different drug susceptibility profiles — look up the specific strain when known.\n\n---\n\n## When to Use\n\nApply when user asks:\n- \"New pathogen detected - what drugs might work?\"\n- \"Emerging virus [X] - therapeutic options?\"\n- \"Drug repurposing candidates for [pathogen]\"\n- \"What do we know about [novel coronavirus\u002Fbacteria]?\"\n- \"Essential targets in [pathogen] for drug development\"\n- \"Can we repurpose [drug] against [pathogen]?\"\n\n---\n\n## Critical Workflow Requirements\n\n### 1. Report-First Approach (MANDATORY)\n\n1. Create `[PATHOGEN]_outbreak_intelligence.md` FIRST with section headers\n2. Progressively update as data is gathered\n3. Output separate files: `[PATHOGEN]_drug_candidates.csv`, `[PATHOGEN]_target_proteins.csv`\n\n### 2. Citation Requirements (MANDATORY)\n\nEvery finding must have inline source attribution:\n```markdown\n### Target: RNA-dependent RNA polymerase (RdRp)\n- **UniProt**: P0DTD1 (NSP12)\n- **Essentiality**: Required for replication\n*Source: UniProt via `UniProt_search`, literature review*\n```\n\n---\n\n## Phase 0: Tool Verification\n\n### Known Parameter Corrections\n\n| Tool | WRONG Parameter | CORRECT Parameter |\n|------|-----------------|-------------------|\n| `NCBIDatasets_get_taxonomy` | `name` | `tax_id` (integer) or use `BVBRC_search_taxonomy` for keyword search |\n| `UniProt_search` | `name` | `query` |\n| `ChEMBL_search_targets` | `query`, `target` | `pref_name__contains` (substring match) |\n| `get_diffdock_info` | `protein_file` | `protein` (content) |\n| `drugbank_full_search` | _(may fail)_ | Use `drugbank_vocab_search` as primary DrugBank lookup |\n\n> **PubMed tip**: Use `sort=\"relevance\"` (default) not `sort=\"pub_date\"` — date-sorted queries can return empty for narrow topics. Tool name: `PubMed_search_articles`.\n> **FDA labels**: Use `FDA_get_drug_label_info_by_field_value` with targeted `return_fields` to avoid oversized responses from `OpenFDA_search_drug_labels`.\n\n---\n\n## Workflow Overview\n\n```\nPhase 1: Pathogen Identification\n├── Taxonomic classification (NCBI Taxonomy)\n├── Closest relatives (for knowledge transfer)\n├── Genome\u002Fproteome availability\n└── OUTPUT: Pathogen profile\n    |\nPhase 2: Target Identification\n├── Essential genes\u002Fproteins (UniProt)\n├── Conservation across strains\n├── Druggability assessment (ChEMBL)\n└── OUTPUT: Prioritized target list (scored by essentiality\u002Fconservation\u002Fdruggability\u002Fprecedent)\n    |\nPhase 3: Structure Prediction (NvidiaNIM)\n├── AlphaFold2\u002FESMFold for targets\n├── Binding site identification\n├── Quality assessment (pLDDT)\n└── OUTPUT: Target structures (docking-ready if pLDDT > 70)\n    |\nPhase 4: Drug Repurposing Screen\n├── Approved drugs for related pathogens (ChEMBL)\n├── Broad-spectrum antivirals\u002Fantibiotics\n├── Docking screen (get_diffdock_info)\n└── OUTPUT: Ranked candidate drugs\n    |\nPhase 4.5: Pathway Analysis\n├── KEGG: Pathogen metabolism pathways\n├── Essential metabolic targets\n├── Host-pathogen interaction pathways\n└── OUTPUT: Pathway-based drug targets\n    |\nPhase 5: Literature Intelligence\n├── PubMed: Published outbreak reports\n├── BioRxiv\u002FMedRxiv: Recent preprints (CRITICAL for outbreaks)\n├── ArXiv: Computational\u002FML preprints\n├── OpenAlex: Citation tracking\n├── ClinicalTrials.gov: Active trials\n└── OUTPUT: Evidence synthesis\n    |\nPhase 6: Report Synthesis\n├── Top drug candidates with evidence grades\n├── Clinical trial opportunities\n├── Recommended immediate actions\n└── OUTPUT: Final report\n```\n\n---\n\n## Phase Summaries\n\n### Phase 1: Pathogen Identification\nClassify via NCBI Taxonomy (query param). Identify related pathogens with existing drugs for knowledge transfer. Determine genome\u002Fproteome availability.\n\n**Knowledge transfer principle**: Drugs effective against related pathogens are the highest-priority repurposing candidates. A protease inhibitor for SARS-CoV-1 is immediately relevant to SARS-CoV-2. Look up the related pathogen's approved drugs in ChEMBL before generating candidates from first principles.\n\n### Phase 2: Target Identification\nSearch UniProt for pathogen proteins (reviewed). Check ChEMBL for drug precedent. Score targets by: Essentiality (30%), Conservation (25%), Druggability (25%), Drug precedent (20%). Aim for 5+ targets.\n\n### Phase 3: Structure Prediction\nUse NvidiaNIM AlphaFold2 for top 3 targets. Assess pLDDT confidence. Only dock structures with pLDDT > 70 (active site > 90 preferred). Fallback: alphafold_get_prediction or ESMFold_predict_structure.\n\n### Phase 4: Drug Repurposing Screen\nSource candidates from: related pathogen drugs, broad-spectrum antivirals, target class drugs (DGIdb). Dock top 20+ candidates via get_diffdock_info. Rank by docking score and evidence tier.\n\n### Phase 4.5: Pathway Analysis\nUse KEGG to identify essential metabolic pathways. Map host-pathogen interaction points. Identify pathway-based drug targets beyond direct protein inhibition.\n\n### Phase 5: Literature Intelligence\nSearch PubMed (peer-reviewed), BioRxiv\u002FMedRxiv (preprints - critical for outbreaks), ArXiv (computational), ClinicalTrials.gov (active trials). Track citations via OpenAlex. Note: preprints are NOT peer-reviewed.\n\n### Phase 6: Report Synthesis\nAggregate all findings into final report. Grade every candidate. Provide 3+ immediate actions, clinical trial opportunities, and research priorities.\n\n---\n\n## Evidence Grading\n\n| Tier | Symbol | Criteria | Example |\n|------|--------|----------|---------|\n| **T1** | [T1] | FDA approved for this pathogen | Remdesivir for COVID |\n| **T2** | [T2] | Clinical trial evidence OR approved for related pathogen | Favipiravir |\n| **T3** | [T3] | In vitro activity OR strong docking + mechanism | Sofosbuvir |\n| **T4** | [T4] | Computational prediction only | Novel docking hits |\n\n---\n\n## Completeness Checklist\n\n### Phase 1: Pathogen ID\n- [ ] Taxonomic classification complete\n- [ ] Related pathogens identified\n- [ ] Genome\u002Fproteome availability noted\n\n### Phase 2: Targets\n- [ ] 5+ targets identified\n- [ ] Essentiality documented\n- [ ] Conservation assessed\n- [ ] Drug precedent checked\n\n### Phase 3: Structures\n- [ ] Structures predicted for top 3 targets\n- [ ] pLDDT confidence reported\n- [ ] Binding sites identified\n\n### Phase 4: Drug Screen\n- [ ] 20+ candidates screened\n- [ ] FDA-approved drugs prioritized\n- [ ] Docking scores reported\n- [ ] Top 5 candidates detailed\n\n### Phase 5: Literature\n- [ ] Recent papers summarized\n- [ ] Active trials listed\n- [ ] Resistance data noted\n\n### Phase 6: Recommendations\n- [ ] 3+ immediate actions\n- [ ] Clinical trial opportunities\n- [ ] Research priorities\n\n---\n\n## Fallback Chains\n\n| Primary Tool | Fallback 1 | Fallback 2 |\n|--------------|------------|------------|\n| `NvidiaNIM_alphafold2` | `alphafold_get_prediction` | `ESMFold_predict_structure` |\n| `get_diffdock_info` | `NvidiaNIM_boltz2` | Manual docking |\n| `NCBIDatasets_suggest_taxonomy` | `UniProtTaxonomy_get_taxon` | Manual classification |\n| `ChEMBL_search_drugs` | `drugbank_vocab_search` | PubChem bioassays |\n\n---\n\n## References\n\n| File | Contents |\n|------|----------|\n| [TOOLS_REFERENCE.md](TOOLS_REFERENCE.md) | Complete tool documentation |\n| [phase_details.md](phase_details.md) | Detailed code examples and procedures for each phase |\n| [report_template.md](report_template.md) | Report template with section headers, checklist, and evidence grading |\n| [CHECKLIST.md](CHECKLIST.md) | Pre-delivery verification checklist (quality, citations, docking) |\n| [EXAMPLES.md](EXAMPLES.md) | Full worked examples (coronavirus, CRKP, limited-info scenarios) |\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Flibrary\u002Fskills\u002Ftooluniverse-infectious-disease","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":40,"prompt":50,"zipAvailable":51},[41,44,47],{"tool":42,"command":43},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-infectious-disease",{"tool":45,"command":46},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-infectious-disease",{"tool":48,"command":49},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-infectious-disease","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-infectious-disease\u002FSKILL.md",true,[53,59,63,67,71,75,79,83,87],{"path":54,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":57,"sourceHtmlUrl":58},"agents\u002Fopenai.yaml","REFERENCE","参考文档",243,"https:\u002F\u002Fgithub.com\u002Fsapsapshen\u002Fai-memory-router\u002Fblob\u002Fmain\u002Fskills-store\u002Fglobal\u002Fswift-concurrency-expert\u002Fagents\u002Fopenai.yaml",{"path":60,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":61,"sourceHtmlUrl":62},"CHECKLIST.md",6643,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-infectious-disease\u002FCHECKLIST.md",{"path":64,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":65,"sourceHtmlUrl":66},"EXAMPLES.md",13195,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-infectious-disease\u002FEXAMPLES.md",{"path":68,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":69,"sourceHtmlUrl":70},"phase_details.md",6806,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-infectious-disease\u002Fphase_details.md",{"path":72,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":73,"sourceHtmlUrl":74},"references\u002Fapproachable-concurrency.md",2471,"https:\u002F\u002Fgithub.com\u002Fsapsapshen\u002Fai-memory-router\u002Fblob\u002Fmain\u002Fskills-store\u002Fglobal\u002Fswift-concurrency-expert\u002Freferences\u002Fapproachable-concurrency.md",{"path":76,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":77,"sourceHtmlUrl":78},"references\u002Fswift-6-2-concurrency.md",10673,"https:\u002F\u002Fgithub.com\u002Fsapsapshen\u002Fai-memory-router\u002Fblob\u002Fmain\u002Fskills-store\u002Fglobal\u002Fswift-concurrency-expert\u002Freferences\u002Fswift-6-2-concurrency.md",{"path":80,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":81,"sourceHtmlUrl":82},"references\u002Fswiftui-concurrency-tour-wwdc.md",1645,"https:\u002F\u002Fgithub.com\u002Fsapsapshen\u002Fai-memory-router\u002Fblob\u002Fmain\u002Fskills-store\u002Fglobal\u002Fswift-concurrency-expert\u002Freferences\u002Fswiftui-concurrency-tour-wwdc.md",{"path":84,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":85,"sourceHtmlUrl":86},"report_template.md",2450,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-infectious-disease\u002Freport_template.md",{"path":88,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":89,"sourceHtmlUrl":90},"TOOLS_REFERENCE.md",14877,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-infectious-disease\u002FTOOLS_REFERENCE.md",[92,112,143,170,184,200],{"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":28},"01M6DF7D7478R55P46REYH4QAC","clarify-requirements","Resolve genuine pre-execution ambiguity by scanning repo context, generating 1-6 grounded options, and asking 1-3 focused questions via AskUserQuestion. NOT for mid-task use (injection risk); NOT when the goal is already unambiguous; use to disambiguate vague prompts before any file edits.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fworkspace-hooks\u002Fskills\u002Fclarify-requirements\u002FSKILL.md",[],[99,100,101,102,23,103,104,105,106,22,107,108,109,110,111],"clarify requirements","clarify","requirements","risk","task","prompts","goal","scanning","context","repo","injection","execution","file",{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":123,"publishedAt":28},"01M6DF79CA4BHJS66J8EZDBPWJ","openmm-md","Run FREE, open-source, Windows-native GPU molecular dynamics via the openmm-md MCP (OpenMM + CUDA on the local NVIDIA GPU). Use for protein \u002F protein-ligand MD when you want a free stack or are on Windows without a Schrodinger license. Covers the full workflow (prepare, solvate, minimize, equilibrate, production, analyze, mmgbsa) AND an honest decision guide vs Schrodinger Desmond, including how to run Desmond legitimately on Linux or a cloud GPU with a real license. This is a deliberately LESSER free alternative and does NOT replace the schrodinger MCP tools. Do NOT use it to pick a free tool when a validated FEP+, WaterMap, IFD-MD, or Prime MM-GBSA result is actually required.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fmcp\u002Fopenmm-md-mcp\u002Fskill\u002Fopenmm-md\u002FSKILL.md",[118],{"categoryNo":119,"categoryName":120,"taxonomyType":121,"taxonomyTypeDesc":122},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[124,125,126,127,128,129,130,131,132,133,134,135,136,137,22,138,139,140,141,142],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":144,"name":145,"nameZh":6,"description":146,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":147,"categories":148,"keywords":155,"publishedAt":28},"01M6DF76C1MG85VEWP8VZCBNMN","visual-review","Take screenshots of web pages and UI using Playwright for visual review and iteration","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fvisual-review\u002FSKILL.md",[149,152],{"categoryNo":150,"categoryName":151,"taxonomyType":121,"taxonomyTypeDesc":122},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":153,"categoryName":154,"taxonomyType":121,"taxonomyTypeDesc":122},"01JBSEEDCAT000000000000008","测试与质量",[156,157,158,159,160,161,162,163,164,165,125,166,167,168,169],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":171,"name":172,"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":28},"01M6DF73AQVCBZKEN0YXEX9FXP","status","Diagnostic status report — shows metaswarm installation state, project setup, and potential issues","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstatus\u002FSKILL.md",[],[172,177,178,179,180,181,182,183],"setup","report","project","installation","project setup","issues","state",{"skillNo":185,"name":186,"nameZh":6,"description":187,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":188,"categories":189,"keywords":191,"publishedAt":28},"01M6DF6X6C2XB0P6GX76P7TTYV","start","Use when starting work on any task, when the user mentions metaswarm, or when the user wants to begin tracked development work","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstart\u002FSKILL.md",[190],{"categoryNo":119,"categoryName":120,"taxonomyType":121,"taxonomyTypeDesc":122},[186,192,103,193,194,195,22,196,197,198,199],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":201,"name":177,"nameZh":6,"description":202,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":203,"categories":204,"keywords":205,"publishedAt":28},"01M6DF6QMJ9AJKFKHHKRT005PQ","Interactive project setup — detects your project, configures metaswarm, writes project-local files","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fsetup\u002FSKILL.md",[],[177,179,140,206,181,207],"files","interactive"]