[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DATH54CQ9AFMHVNY0SYRX7":3,"skill-same:01M6DATH54CQ9AFMHVNY0SYRX7":90},{"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":33,"linkOnly":34,"markdownContent":35,"markdownBody":36,"frontMatter":37,"refName":38,"commitSha":39,"skillDirectory":40,"forksCount":14,"repositoryHtmlUrl":41,"repositoryHomepageUrl":6,"ownerHtmlUrl":42,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":43,"install":44,"resources":57},"01M6DATH54CQ9AFMHVNY0SYRX7","tooluniverse-multiomic-disease-characterization",null,"Comprehensive multi-omics disease characterization integrating genomics, transcriptomics, proteomics, pathway, and therapeutic layers for systems-level understanding. Produces a detailed multi-omics report with quantitative confidence scoring (0-100), cross-layer gene concordance analysis, biomarker candidates, therapeutic opportunities, and mechanistic hypotheses. Uses 80+ ToolUniverse tools across 8 analysis layers. Use when users ask about disease mechanisms, multi-omics analysis, systems biology of disease, biomarker discovery, or therapeutic target identification from a disease perspective.","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-multiomic-disease-characterization\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32],"tooluniverse multiomic disease characterization","report","Tools","analysis","discovery","ask","use","confidence scoring","scoring","across","genomics","proteomics","systems biology","systems","2026-11-10 10:12:30",false,"---\nname: tooluniverse-multiomic-disease-characterization\ndescription: Comprehensive multi-omics disease characterization integrating genomics, transcriptomics, proteomics, pathway, and therapeutic layers for systems-level understanding. Produces a detailed multi-omics report with quantitative confidence scoring (0-100), cross-layer gene concordance analysis, biomarker candidates, therapeutic opportunities, and mechanistic hypotheses. Uses 80+ ToolUniverse tools across 8 analysis layers. Use when users ask about disease mechanisms, multi-omics analysis, systems biology of disease, biomarker discovery, or therapeutic target identification from a disease perspective.\n---\n\n# Multi-Omics Disease Characterization Pipeline\n\nCharacterize diseases across multiple molecular layers (genomics, transcriptomics, proteomics, pathways) to provide systems-level understanding of disease mechanisms, identify therapeutic opportunities, and discover biomarker candidates.\n\n**KEY PRINCIPLES**:\n1. **Report-first approach** - Create report file FIRST, then populate progressively\n2. **Disease disambiguation FIRST** - Resolve all identifiers before omics analysis\n3. **Layer-by-layer analysis** - Systematically cover all omics layers\n4. **Cross-layer integration** - Identify genes\u002Ftargets appearing in multiple layers\n5. **Evidence grading** - Grade all evidence as T1 (human\u002Fclinical) to T4 (computational)\n6. **Tissue context** - Emphasize disease-relevant tissues\u002Forgans\n7. **Quantitative scoring** - Multi-Omics Confidence Score (0-100)\n8. **Druggable focus** - Prioritize targets with therapeutic potential\n9. **Biomarker identification** - Highlight diagnostic\u002Fprognostic markers\n10. **Mechanistic synthesis** - Generate testable hypotheses\n11. **Source references** - Every statement must cite tool\u002Fdatabase\n12. **Completeness checklist** - Mandatory section showing analysis coverage\n13. **English-first queries** - Always use English terms in tool calls. Respond in user's language\n\nMulti-omics disease characterization asks: what molecular layers are dysregulated? Genomic mutations → transcriptomic changes → proteomic effects → metabolomic consequences. Concordance across layers strengthens the finding. Discordance reveals regulatory complexity.\n\n## LOOK UP, DON'T GUESS\nWhen uncertain about any scientific fact, SEARCH databases first rather than reasoning from memory. A database-verified answer is always more reliable than a guess.\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\nApply when users:\n- Ask about disease mechanisms across omics layers\n- Need multi-omics characterization of a disease\n- Want to understand disease at the systems biology level\n- Ask \"What pathways\u002Fgenes\u002Fproteins are involved in [disease]?\"\n- Need biomarker discovery for a disease\n- Want to identify druggable targets from disease profiling\n- Ask for integrated genomics + transcriptomics + proteomics analysis\n- Need cross-layer concordance analysis\n- Ask about disease network biology \u002F hub genes\n\n**NOT for** (use other skills instead):\n- Single gene\u002Ftarget validation -> Use `tooluniverse-drug-target-validation`\n- Drug safety profiling -> Use `tooluniverse-adverse-event-detection`\n- General disease overview -> Use `tooluniverse-disease-research`\n- Variant interpretation -> Use `tooluniverse-variant-interpretation`\n- GWAS-specific analysis -> Use `tooluniverse-gwas-*` skills\n- Pathway-only analysis -> Use `tooluniverse-systems-biology`\n\n---\n\n## Input Parameters\n\n| Parameter | Required | Description | Example |\n|-----------|----------|-------------|---------|\n| **disease** | Yes | Disease name, OMIM ID, EFO ID, or MONDO ID | `Alzheimer disease`, `MONDO_0004975` |\n| **tissue** | No | Tissue\u002Forgan of interest | `brain`, `liver`, `blood` |\n| **focus_layers** | No | Specific omics layers to emphasize | `genomics`, `transcriptomics`, `pathways` |\n\n---\n\n## Pipeline Overview\n\nThe pipeline runs 9 phases sequentially. Each phase uses specific tools documented in detail in `tool-reference.md`.\n\n### Phase 0: Disease Disambiguation (ALWAYS FIRST)\nResolve disease to standard identifiers (MONDO\u002FEFO) for all downstream queries.\n- Primary tool: `OpenTargets_get_disease_id_description_by_name`\n- Get description, synonyms, therapeutic areas, disease hierarchy, cross-references\n- **CRITICAL**: Disease IDs use underscore format (e.g., `MONDO_0004975`), NOT colon\n- If ambiguous, present top 3-5 options and ask user to select\n\n### Phase 1: Genomics Layer\nIdentify genetic variants, GWAS associations, and genetically implicated genes.\n- Tools: `gwas_search_associations` (use `efo_id` for precision, not free-text `disease_trait`), `gwas_get_snps_for_gene`, ClinVar, OpenTargets associated targets\n- `gnomad_get_gene_constraints` — gene constraint metrics (pLI, oe_lof) to interpret whether LoF variants are tolerated vs. haploinsufficient\n- Get top 10-15 genes with genetic evidence scores; track Ensembl IDs for downstream phases\n\n### Phase 2: Transcriptomics Layer\nIdentify differentially expressed genes, tissue-specific expression, and expression-based biomarkers.\n- `GTEx_get_expression_summary` — baseline expression across 54 tissues (accepts `gene_symbol` directly)\n- Tools: Expression Atlas, HPA (tissue expression), EuropePMC scores\n- Check expression in disease-relevant tissues for top genes from Phase 1\n\n### Phase 3: Proteomics & Interaction Layer\nMap protein-protein interactions, identify hub genes, and characterize interaction networks.\n- `UniProt_get_function_by_accession` — protein function narrative (essential for mechanistic context)\n- Tools: `STRING_get_network` (param: `identifiers`, `species`=9606), `intact_get_interactions`, HumanBase\n- Build PPI network from top 15-20 genes; identify hub genes by degree centrality\n\n### Phase 4: Pathway & Network Layer\nIdentify enriched biological pathways and cross-pathway connections.\n- `ReactomeAnalysis_pathway_enrichment` — identifiers are **newline-separated** (`\\n`), NOT space-separated\n- `enrichr_gene_enrichment_analysis` — param: `gene_list` (array), `libs` (array). NOTE: `data` field is a JSON string that needs parsing\n- `kegg_search_pathway` — pathway keyword search\n\n### Phase 5: Gene Ontology & Functional Annotation\nCharacterize biological processes, molecular functions, and cellular components.\n- Tools: Enrichr (GO libraries), QuickGO, GO annotations, OpenTargets GO\n- Run GO enrichment for all 3 aspects (BP, MF, CC)\n\n### Phase 6: Therapeutic Landscape\nMap approved drugs, druggable targets, repurposing opportunities, and clinical trials.\n- `DGIdb_get_drug_gene_interactions` — drug interactions by gene (param: `genes` as array). Often more comprehensive than OpenTargets for drug-gene data.\n- OpenTargets drugs\u002Ftractability (use **EFO IDs** like `EFO_0000384` for Crohn's, not MONDO — MONDO IDs may return null for drug queries)\n- `search_clinical_trials` — `query_term` is REQUIRED\n\n### Phase 7: Multi-Omics Integration\nIntegrate findings across all layers. See `integration-scoring.md` for full details.\n- Cross-layer gene concordance: count layers per gene, score multi-layer hub genes\n- Direction concordance: genetics + expression agreement\n- Biomarker identification: diagnostic, prognostic, predictive\n- Mechanistic hypothesis generation\n\n### Phase 8: Report Finalization\nWrite executive summary, calculate confidence score, verify completeness.\n- See `integration-scoring.md` for quality checklist and scoring formula\n\n---\n\n## Key Tool Parameter Notes\n\nThese are the most common parameter pitfalls:\n- `OpenTargets` disease IDs: underscore format (`MONDO_0004975`), NOT colon\n- `STRING` `protein_ids`: must be **array** (`['APOE']`), not string\n- `enrichr` `libs`: must be **array** (`['KEGG_2021_Human']`)\n- `HPA_get_rna_expression_by_source`: ALL 3 params required (`gene_name`, `source_type`, `source_name`)\n- `humanbase_ppi_analysis`: ALL params required (`gene_list`, `tissue`, `max_node`, `interaction`, `string_mode`)\n- `expression_atlas_disease_target_score`: `pageSize` is REQUIRED\n- `search_clinical_trials`: `query_term` is REQUIRED even if `condition` is provided\n\nFor full tool parameters and per-phase workflows, see `tool-reference.md`.\n\n---\n\n## Reference Files\n\nAll detailed content is in reference files in this directory:\n\n| File | Contents |\n|------|----------|\n| `tool-reference.md` | Full tool parameters, inputs\u002Foutputs, per-phase workflows, quick reference table |\n| `report-template.md` | Complete report markdown template with all sections and checklists |\n| `integration-scoring.md` | Confidence score formula (0-100), evidence grading (T1-T4), integration procedures, quality checklist |\n| `response-formats.md` | Verified JSON response structures for key tools |\n| `use-patterns.md` | Common use patterns, edge case handling, fallback strategies |\n","# Multi-Omics Disease Characterization Pipeline\n\nCharacterize diseases across multiple molecular layers (genomics, transcriptomics, proteomics, pathways) to provide systems-level understanding of disease mechanisms, identify therapeutic opportunities, and discover biomarker candidates.\n\n**KEY PRINCIPLES**:\n1. **Report-first approach** - Create report file FIRST, then populate progressively\n2. **Disease disambiguation FIRST** - Resolve all identifiers before omics analysis\n3. **Layer-by-layer analysis** - Systematically cover all omics layers\n4. **Cross-layer integration** - Identify genes\u002Ftargets appearing in multiple layers\n5. **Evidence grading** - Grade all evidence as T1 (human\u002Fclinical) to T4 (computational)\n6. **Tissue context** - Emphasize disease-relevant tissues\u002Forgans\n7. **Quantitative scoring** - Multi-Omics Confidence Score (0-100)\n8. **Druggable focus** - Prioritize targets with therapeutic potential\n9. **Biomarker identification** - Highlight diagnostic\u002Fprognostic markers\n10. **Mechanistic synthesis** - Generate testable hypotheses\n11. **Source references** - Every statement must cite tool\u002Fdatabase\n12. **Completeness checklist** - Mandatory section showing analysis coverage\n13. **English-first queries** - Always use English terms in tool calls. Respond in user's language\n\nMulti-omics disease characterization asks: what molecular layers are dysregulated? Genomic mutations → transcriptomic changes → proteomic effects → metabolomic consequences. Concordance across layers strengthens the finding. Discordance reveals regulatory complexity.\n\n## LOOK UP, DON'T GUESS\nWhen uncertain about any scientific fact, SEARCH databases first rather than reasoning from memory. A database-verified answer is always more reliable than a guess.\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\nApply when users:\n- Ask about disease mechanisms across omics layers\n- Need multi-omics characterization of a disease\n- Want to understand disease at the systems biology level\n- Ask \"What pathways\u002Fgenes\u002Fproteins are involved in [disease]?\"\n- Need biomarker discovery for a disease\n- Want to identify druggable targets from disease profiling\n- Ask for integrated genomics + transcriptomics + proteomics analysis\n- Need cross-layer concordance analysis\n- Ask about disease network biology \u002F hub genes\n\n**NOT for** (use other skills instead):\n- Single gene\u002Ftarget validation -> Use `tooluniverse-drug-target-validation`\n- Drug safety profiling -> Use `tooluniverse-adverse-event-detection`\n- General disease overview -> Use `tooluniverse-disease-research`\n- Variant interpretation -> Use `tooluniverse-variant-interpretation`\n- GWAS-specific analysis -> Use `tooluniverse-gwas-*` skills\n- Pathway-only analysis -> Use `tooluniverse-systems-biology`\n\n---\n\n## Input Parameters\n\n| Parameter | Required | Description | Example |\n|-----------|----------|-------------|---------|\n| **disease** | Yes | Disease name, OMIM ID, EFO ID, or MONDO ID | `Alzheimer disease`, `MONDO_0004975` |\n| **tissue** | No | Tissue\u002Forgan of interest | `brain`, `liver`, `blood` |\n| **focus_layers** | No | Specific omics layers to emphasize | `genomics`, `transcriptomics`, `pathways` |\n\n---\n\n## Pipeline Overview\n\nThe pipeline runs 9 phases sequentially. Each phase uses specific tools documented in detail in `tool-reference.md`.\n\n### Phase 0: Disease Disambiguation (ALWAYS FIRST)\nResolve disease to standard identifiers (MONDO\u002FEFO) for all downstream queries.\n- Primary tool: `OpenTargets_get_disease_id_description_by_name`\n- Get description, synonyms, therapeutic areas, disease hierarchy, cross-references\n- **CRITICAL**: Disease IDs use underscore format (e.g., `MONDO_0004975`), NOT colon\n- If ambiguous, present top 3-5 options and ask user to select\n\n### Phase 1: Genomics Layer\nIdentify genetic variants, GWAS associations, and genetically implicated genes.\n- Tools: `gwas_search_associations` (use `efo_id` for precision, not free-text `disease_trait`), `gwas_get_snps_for_gene`, ClinVar, OpenTargets associated targets\n- `gnomad_get_gene_constraints` — gene constraint metrics (pLI, oe_lof) to interpret whether LoF variants are tolerated vs. haploinsufficient\n- Get top 10-15 genes with genetic evidence scores; track Ensembl IDs for downstream phases\n\n### Phase 2: Transcriptomics Layer\nIdentify differentially expressed genes, tissue-specific expression, and expression-based biomarkers.\n- `GTEx_get_expression_summary` — baseline expression across 54 tissues (accepts `gene_symbol` directly)\n- Tools: Expression Atlas, HPA (tissue expression), EuropePMC scores\n- Check expression in disease-relevant tissues for top genes from Phase 1\n\n### Phase 3: Proteomics & Interaction Layer\nMap protein-protein interactions, identify hub genes, and characterize interaction networks.\n- `UniProt_get_function_by_accession` — protein function narrative (essential for mechanistic context)\n- Tools: `STRING_get_network` (param: `identifiers`, `species`=9606), `intact_get_interactions`, HumanBase\n- Build PPI network from top 15-20 genes; identify hub genes by degree centrality\n\n### Phase 4: Pathway & Network Layer\nIdentify enriched biological pathways and cross-pathway connections.\n- `ReactomeAnalysis_pathway_enrichment` — identifiers are **newline-separated** (`\\n`), NOT space-separated\n- `enrichr_gene_enrichment_analysis` — param: `gene_list` (array), `libs` (array). NOTE: `data` field is a JSON string that needs parsing\n- `kegg_search_pathway` — pathway keyword search\n\n### Phase 5: Gene Ontology & Functional Annotation\nCharacterize biological processes, molecular functions, and cellular components.\n- Tools: Enrichr (GO libraries), QuickGO, GO annotations, OpenTargets GO\n- Run GO enrichment for all 3 aspects (BP, MF, CC)\n\n### Phase 6: Therapeutic Landscape\nMap approved drugs, druggable targets, repurposing opportunities, and clinical trials.\n- `DGIdb_get_drug_gene_interactions` — drug interactions by gene (param: `genes` as array). Often more comprehensive than OpenTargets for drug-gene data.\n- OpenTargets drugs\u002Ftractability (use **EFO IDs** like `EFO_0000384` for Crohn's, not MONDO — MONDO IDs may return null for drug queries)\n- `search_clinical_trials` — `query_term` is REQUIRED\n\n### Phase 7: Multi-Omics Integration\nIntegrate findings across all layers. See `integration-scoring.md` for full details.\n- Cross-layer gene concordance: count layers per gene, score multi-layer hub genes\n- Direction concordance: genetics + expression agreement\n- Biomarker identification: diagnostic, prognostic, predictive\n- Mechanistic hypothesis generation\n\n### Phase 8: Report Finalization\nWrite executive summary, calculate confidence score, verify completeness.\n- See `integration-scoring.md` for quality checklist and scoring formula\n\n---\n\n## Key Tool Parameter Notes\n\nThese are the most common parameter pitfalls:\n- `OpenTargets` disease IDs: underscore format (`MONDO_0004975`), NOT colon\n- `STRING` `protein_ids`: must be **array** (`['APOE']`), not string\n- `enrichr` `libs`: must be **array** (`['KEGG_2021_Human']`)\n- `HPA_get_rna_expression_by_source`: ALL 3 params required (`gene_name`, `source_type`, `source_name`)\n- `humanbase_ppi_analysis`: ALL params required (`gene_list`, `tissue`, `max_node`, `interaction`, `string_mode`)\n- `expression_atlas_disease_target_score`: `pageSize` is REQUIRED\n- `search_clinical_trials`: `query_term` is REQUIRED even if `condition` is provided\n\nFor full tool parameters and per-phase workflows, see `tool-reference.md`.\n\n---\n\n## Reference Files\n\nAll detailed content is in reference files in this directory:\n\n| File | Contents |\n|------|----------|\n| `tool-reference.md` | Full tool parameters, inputs\u002Foutputs, per-phase workflows, quick reference table |\n| `report-template.md` | Complete report markdown template with all sections and checklists |\n| `integration-scoring.md` | Confidence score formula (0-100), evidence grading (T1-T4), integration procedures, quality checklist |\n| `response-formats.md` | Verified JSON response structures for key tools |\n| `use-patterns.md` | Common use patterns, edge case handling, fallback strategies |\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Flibrary\u002Fskills\u002Ftooluniverse-multiomic-disease-characterization","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":45,"prompt":55,"zipAvailable":56},[46,49,52],{"tool":47,"command":48},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-multiomic-disease-characterization",{"tool":50,"command":51},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-multiomic-disease-characterization",{"tool":53,"command":54},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-multiomic-disease-characterization","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-multiomic-disease-characterization\u002FSKILL.md",true,[58,64,68,72,76,82,86],{"path":59,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":62,"sourceHtmlUrl":63},"agents\u002Fopenai.yaml","REFERENCE","参考文档",82,"https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions\u002Fyuri-os\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fpilot-feedback\u002Fagents\u002Fopenai.yaml",{"path":65,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":66,"sourceHtmlUrl":67},"integration-scoring.md",4491,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-multiomic-disease-characterization\u002Fintegration-scoring.md",{"path":69,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":70,"sourceHtmlUrl":71},"report-template.md",7546,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-multiomic-disease-characterization\u002Freport-template.md",{"path":73,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":74,"sourceHtmlUrl":75},"response-formats.md",2059,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-multiomic-disease-characterization\u002Fresponse-formats.md",{"path":77,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":80,"sourceHtmlUrl":81},"test_multiomic_disease.py","SCRIPT","脚本",45094,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-multiomic-disease-characterization\u002Ftest_multiomic_disease.py",{"path":83,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":84,"sourceHtmlUrl":85},"tool-reference.md",15796,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-multiomic-disease-characterization\u002Ftool-reference.md",{"path":87,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":88,"sourceHtmlUrl":89},"use-patterns.md",3592,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-multiomic-disease-characterization\u002Fuse-patterns.md",[91,112,143,170,183,199],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":33},"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",[],[98,99,100,101,102,103,104,105,106,25,107,108,109,110,111],"clarify requirements","clarify","requirements","risk","options","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":33},"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",[124,125,126,127,128,129,130,131,132,133,134,135,136,137,25,138,139,140,141,142],"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":33},"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":33},"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",[],[172,177,20,178,179,180,181,182],"setup","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":33},"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":119,"categoryName":120,"taxonomyType":121,"taxonomyTypeDesc":122},[185,191,103,192,193,194,25,195,196,197,198],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":200,"name":177,"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":33},"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",[],[177,178,140,205,180,206],"files","interactive"]