[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DAXNAM7ECVA99754FT1FE2":3,"skill-same:01M6DAXNAM7ECVA99754FT1FE2":92},{"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":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":44,"commitSha":45,"skillDirectory":46,"forksCount":14,"repositoryHtmlUrl":47,"repositoryHomepageUrl":6,"ownerHtmlUrl":48,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":49,"install":50,"resources":63},"01M6DAXNAM7ECVA99754FT1FE2","tooluniverse-spatial-omics-analysis",null,"Computational analysis framework for spatial multi-omics data integration. Given spatially variable genes (SVGs), spatial domain annotations, tissue type, and disease context from spatial transcriptomics\u002Fproteomics experiments (10x Visium, MERFISH, DBiTplus, SLIDE-seq, etc.), performs comprehensive biological interpretation including pathway enrichment, cell-cell interaction inference, druggable target identification, immune microenvironment characterization, and multi-modal integration. Produces a detailed markdown report with Spatial Omics Integration Score (0-100), domain-by-domain characterization, and validation recommendations. Uses 70+ ToolUniverse tools across 9 analysis phases. Use when users ask about spatial transcriptomics analysis, spatial omics interpretation, tissue heterogeneity, spatial gene expression patterns, tumor microenvironment mapping, tissue zonation, or cell-cell communication from spatial data.","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-spatial-omics-analysis\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"tooluniverse spatial omics analysis","analysis","Spatial","Immune","type","recommendations","computational","gene expression","proteomics","across","domain","interpretation","use","ask","markdown","enrichment","integration","communication","data integration","report","2026-11-10 10:12:30",false,"---\nname: tooluniverse-spatial-omics-analysis\ndescription: Computational analysis framework for spatial multi-omics data integration. Given spatially variable genes (SVGs), spatial domain annotations, tissue type, and disease context from spatial transcriptomics\u002Fproteomics experiments (10x Visium, MERFISH, DBiTplus, SLIDE-seq, etc.), performs comprehensive biological interpretation including pathway enrichment, cell-cell interaction inference, druggable target identification, immune microenvironment characterization, and multi-modal integration. Produces a detailed markdown report with Spatial Omics Integration Score (0-100), domain-by-domain characterization, and validation recommendations. Uses 70+ ToolUniverse tools across 9 analysis phases. Use when users ask about spatial transcriptomics analysis, spatial omics interpretation, tissue heterogeneity, spatial gene expression patterns, tumor microenvironment mapping, tissue zonation, or cell-cell communication from spatial data.\n---\n\n# Spatial Multi-Omics Analysis Pipeline\n\nComprehensive biological interpretation of spatial omics data. Transforms spatially variable genes (SVGs), domain annotations, and tissue context into actionable biological insights.\n\n**KEY PRINCIPLES**:\n1. **Report-first approach** - Create report file FIRST, then populate progressively\n2. **Domain-by-domain analysis** - Characterize each spatial region independently before comparison\n3. **Gene-list-centric** - Analyze user-provided SVGs and marker genes with ToolUniverse databases\n4. **Biological interpretation** - Go beyond statistics to explain biological meaning of spatial patterns\n5. **Disease focus** - Emphasize disease mechanisms and therapeutic opportunities when disease context is provided\n6. **Evidence grading** - Grade all evidence as T1 (human\u002Fclinical) to T4 (computational)\n7. **Multi-modal thinking** - Integrate RNA, protein, and metabolite information when available\n8. **Validation guidance** - Suggest experimental validation approaches for key findings\n9. **Source references** - Every statement must cite tool\u002Fdatabase source\n10. **English-first queries** - Always use English terms in tool calls\n\n---\n\n## LOOK UP, DON'T GUESS\nWhen uncertain about any scientific fact, SEARCH databases first (PubMed, UniProt, ChEMBL, ClinVar, etc.) 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- Provide spatially variable genes from spatial transcriptomics experiments\n- Ask about biological interpretation of spatial domains\u002Fclusters\n- Need pathway enrichment of spatial gene expression data\n- Want to understand cell-cell interactions from spatial data\n- Ask about tumor microenvironment heterogeneity from spatial omics\n- Need druggable targets in specific spatial regions\n- Ask about tissue zonation patterns (liver, brain, kidney)\n- Want to integrate spatial transcriptomics + proteomics data\n\n**NOT for**: Single gene interpretation (use target-research), variant interpretation, drug safety, bulk RNA-seq, GWAS analysis.\n\n---\n\n## Input Parameters\n\n| Parameter | Required | Description | Example |\n|-----------|----------|-------------|---------|\n| **svgs** | Yes | Spatially variable genes | `['EGFR', 'CDH1', 'VIM', 'MYC', 'CD3E']` |\n| **tissue_type** | Yes | Tissue\u002Forgan type | `brain`, `liver`, `lung`, `breast` |\n| **technology** | No | Spatial omics platform | `10x Visium`, `MERFISH`, `DBiTplus` |\n| **disease_context** | No | Disease if applicable | `breast cancer`, `Alzheimer disease` |\n| **spatial_domains** | No | Domain -> marker genes dict | `{'Tumor core': ['MYC','EGFR']}` |\n| **cell_types** | No | Cell types from deconvolution | `['Epithelial', 'T cell']` |\n| **proteins** | No | Proteins detected (multi-modal) | `['CD3', 'PD-L1', 'Ki67']` |\n| **metabolites** | No | Metabolites (SpatialMETA) | `['glutamine', 'lactate']` |\n\n---\n\n## Spatial Omics Integration Score (0-100)\n\n**Data Completeness (0-30)**: SVGs (5), Disease context (5), Spatial domains (5), Cell types (5), Multi-modal (5), Literature (5)\n\n**Biological Insight (0-40)**: Pathway enrichment FDR\u003C0.05 (10), Cell-cell interactions (10), Disease mechanism (10), Druggable targets (10)\n\n**Evidence Quality (0-30)**: Cross-database validation 3+ DBs (10), Clinical validation (10), Literature support (10)\n\n| Score | Tier | Interpretation |\n|-------|------|----------------|\n| 80-100 | Excellent | Comprehensive characterization, strong insights, druggable targets |\n| 60-79 | Good | Good pathway\u002Finteraction analysis, some therapeutic context |\n| 40-59 | Moderate | Basic enrichment, limited domain comparison |\n| 0-39 | Limited | Minimal data, gene-level annotation only |\n\n### Evidence Grading\n\n| Tier | Criteria | Examples |\n|------|----------|----------|\n| [T1] | Direct human\u002Fclinical evidence | FDA-approved drug, validated biomarker |\n| [T2] | Experimental evidence | Validated spatial pattern, known L-R pair |\n| [T3] | Computational\u002Fdatabase evidence | PPI prediction, pathway enrichment |\n| [T4] | Annotation\u002Fprediction only | GO annotation, text-mined association |\n\n---\n\n## Analysis Phases Overview\n\n### Phase 0: Input Processing & Disambiguation (ALWAYS FIRST)\nResolve tissue\u002Fdisease identifiers, establish analysis context. Get MONDO\u002FEFO IDs for disease queries.\n- Tools: `OpenTargets_get_disease_id_description_by_name`, `OpenTargets_get_disease_description_by_efoId`, `HPA_search_genes_by_query`\n\n### Phase 1: Gene Characterization\nResolve gene IDs, annotate functions, tissue specificity, subcellular localization.\n- Tools: `MyGene_query_genes`, `UniProt_get_function_by_accession`, `HPA_get_subcellular_location`, `HPA_get_rna_expression_by_source`, `HPA_get_comprehensive_gene_details_by_ensembl_id`, `HPA_get_cancer_prognostics_by_gene`, `UniProtIDMap_gene_to_uniprot`\n\n### Phase 2: Pathway & Functional Enrichment\nIdentify enriched pathways globally and per-domain. Filter FDR \u003C 0.05.\n- Tools: `STRING_functional_enrichment` (PRIMARY), `ReactomeAnalysis_pathway_enrichment`, `GO_get_annotations_for_gene`, `kegg_search_pathway`, `WikiPathways_search`\n\n### Phase 3: Spatial Domain Characterization\nCharacterize each domain biologically, assign cell types from markers, compare domains.\n- Tools: Phase 2 tools + `HPA_get_biological_processes_by_gene`, `HPA_get_protein_interactions_by_gene`\n\n### Phase 4: Cell-Cell Interaction Inference\nPredict communication from spatial patterns. Check ligand-receptor pairs across domains.\n- Tools: `STRING_get_interaction_partners`, `STRING_get_protein_interactions`, `intact_search_interactions`, `Reactome_get_interactor`, `DGIdb_get_drug_gene_interactions`\n\n### Phase 5: Disease & Therapeutic Context\nConnect to disease mechanisms, identify druggable targets, find clinical trials.\n- Tools: `OpenTargets_get_associated_targets_by_disease_efoId`, `OpenTargets_get_target_tractability_by_ensemblID`, `OpenTargets_get_associated_drugs_by_target_ensemblID`, `search_clinical_trials`, `DGIdb_get_gene_druggability`, `civic_search_genes`\n\n### Phase 6: Multi-Modal Integration\nIntegrate protein\u002FRNA\u002Fmetabolite data. Compare spatial RNA with protein detection.\n- Tools: `HPA_get_subcellular_location`, `HPA_get_rna_expression_in_specific_tissues`, `Reactome_map_uniprot_to_pathways`, `kegg_get_pathway_info`\n\n### Phase 7: Immune Microenvironment (Cancer\u002FInflammation only)\nClassify immune cells, check checkpoint expression, assess Hot vs Cold vs Excluded patterns.\n- Tools: `STRING_functional_enrichment`, `OpenTargets_get_target_tractability_by_ensemblID`, `iedb_search_epitopes`\n\n### Phase 8: Literature & Validation Context\nSearch published evidence, suggest validation experiments (smFISH, IHC, PLA).\n- Tools: `PubMed_search_articles`, `openalex_literature_search`\n\n### Data Discovery: HuBMAP Spatial Atlas Tools\n\nUse HuBMAP tools to find published spatial biology reference datasets for comparison, validation, or cross-study analysis.\n\n| Tool | Purpose | Key Parameters |\n|------|---------|----------------|\n| `HuBMAP_search_datasets` | Search published spatial datasets by organ\u002Fassay\u002Fkeyword | `organ` (code: \"LK\"=Kidney, \"BR\"=Brain, \"LU\"=Lung, etc.), `dataset_type` (\"RNAseq\", \"CODEX\", \"MALDI\"), `query`, `limit` |\n| `HuBMAP_list_organs` | List all available organs with codes and UBERON IDs | (no required params) |\n| `HuBMAP_get_dataset` | Get detailed metadata for a specific HuBMAP dataset | `hubmap_id` (e.g. \"HBM626.FHJD.938\") |\n\n**When to use**: Phase 0 (find reference datasets for the tissue), Phase 8 (cross-reference findings with published HuBMAP atlas data).\n\nSee **phase-procedures.md** for detailed workflows, decision logic, and tool parameter specifications per phase.\n\n---\n\n## Report Structure\n\nCreate file: `{tissue}_{disease}_spatial_omics_report.md`\n\n```\n# Spatial Multi-Omics Analysis Report: {Tissue Type}\n**Report Generated**: {date} | **Technology**: {platform}\n**Tissue**: {tissue_type} | **Disease**: {disease or \"Normal tissue\"}\n**Total SVGs**: {count} | **Spatial Domains**: {count}\n**Spatial Omics Integration Score**: (calculated after analysis)\n\n## Executive Summary\n## 1. Tissue & Disease Context\n## 2. Spatially Variable Gene Characterization\n  - 2.1 Gene ID Resolution\n  - 2.2 Tissue Expression Patterns\n  - 2.3 Subcellular Localization\n  - 2.4 Disease Associations\n## 3. Pathway Enrichment Analysis\n  - 3.1 STRING, 3.2 Reactome, 3.3-3.5 GO (BP, MF, CC)\n## 4. Spatial Domain Characterization (per-domain + comparison)\n## 5. Cell-Cell Interaction Inference\n  - 5.1 PPI, 5.2 Ligand-Receptor, 5.3 Signaling Pathways\n## 6. Disease & Therapeutic Context\n  - 6.1 Disease Gene Overlap, 6.2 Druggable Targets, 6.3 Drug Mechanisms, 6.4 Trials\n## 7. Multi-Modal Integration (if data available)\n## 8. Immune Microenvironment (if relevant)\n## 9. Literature & Validation Context\n## Spatial Omics Integration Score (breakdown table)\n## Completeness Checklist\n## References (tools used, database versions)\n```\n\nSee **report-template.md** for full template with table structures.\n\n---\n\n## Completeness Checklist\n\n- [ ] Gene ID resolution complete\n- [ ] Tissue expression patterns analyzed (HPA)\n- [ ] Subcellular localization checked (HPA)\n- [ ] Pathway enrichment complete (STRING + Reactome)\n- [ ] GO enrichment complete (BP + MF + CC)\n- [ ] Spatial domains characterized individually\n- [ ] Domain comparison performed\n- [ ] PPI analyzed (STRING)\n- [ ] Ligand-receptor pairs identified\n- [ ] Disease associations checked (OpenTargets)\n- [ ] Druggable targets identified\n- [ ] Multi-modal integration performed (if data available)\n- [ ] Immune microenvironment characterized (if relevant)\n- [ ] Literature search completed\n- [ ] Validation recommendations provided\n- [ ] Integration Score calculated\n- [ ] Executive summary written\n- [ ] All sections have source citations\n\n---\n\n## Common Use Cases\n\n1. **Cancer Spatial Heterogeneity**: Visium with tumor\u002Fstroma\u002Fimmune domains -> pathways, immune infiltration, druggable targets, checkpoints\n2. **Brain Tissue Zonation**: MERFISH with neuronal subtypes -> synaptic signaling, receptors, hippocampal zonation\n3. **Liver Metabolic Zonation**: Periportal vs pericentral -> CYP450, Wnt gradient, drug metabolism enzymes\n4. **Tumor-Immune Interface**: DBiTplus RNA+protein -> checkpoint L-R pairs, immune exclusion, multi-modal concordance\n5. **Developmental Patterns**: Morphogen gradients (Wnt, BMP, FGF, SHH), TF patterns, cell fate genes\n6. **Disease Progression**: Disease gradient -> inflammatory response, neuronal loss, therapeutic windows\n\n---\n\n## Reference Files\n\n- **phase-procedures.md** - Detailed phase workflows, decision logic, tool usage per phase\n- **tool-reference.md** - Tool parameter names, response formats, fallback strategies, limitations\n- **reference-data.md** - Cell type markers, ligand-receptor pairs, immune checkpoint reference\n- **report-template.md** - Full report template with all table structures\n- **test_spatial_omics.py** - Test suite\n\n---\n\n## Summary\n\n**Spatial Multi-Omics Analysis** provides:\n1. Gene characterization (ID resolution, function, localization, tissue expression)\n2. Pathway & functional enrichment (STRING, Reactome, GO, KEGG)\n3. Spatial domain characterization (per-domain and cross-domain)\n4. Cell-cell interaction inference (PPI, ligand-receptor, signaling)\n5. Disease & therapeutic context (disease genes, druggable targets, trials)\n6. Multi-modal integration (RNA-protein concordance, metabolic pathways)\n7. Immune microenvironment (cell types, checkpoints, immunotherapy)\n8. Literature context & validation recommendations\n\n**Outputs**: Markdown report with Spatial Omics Integration Score (0-100)\n**Uses**: 70+ ToolUniverse tools across 9 analysis phases\n**Time**: ~10-20 minutes depending on gene list size\n","# Spatial Multi-Omics Analysis Pipeline\n\nComprehensive biological interpretation of spatial omics data. Transforms spatially variable genes (SVGs), domain annotations, and tissue context into actionable biological insights.\n\n**KEY PRINCIPLES**:\n1. **Report-first approach** - Create report file FIRST, then populate progressively\n2. **Domain-by-domain analysis** - Characterize each spatial region independently before comparison\n3. **Gene-list-centric** - Analyze user-provided SVGs and marker genes with ToolUniverse databases\n4. **Biological interpretation** - Go beyond statistics to explain biological meaning of spatial patterns\n5. **Disease focus** - Emphasize disease mechanisms and therapeutic opportunities when disease context is provided\n6. **Evidence grading** - Grade all evidence as T1 (human\u002Fclinical) to T4 (computational)\n7. **Multi-modal thinking** - Integrate RNA, protein, and metabolite information when available\n8. **Validation guidance** - Suggest experimental validation approaches for key findings\n9. **Source references** - Every statement must cite tool\u002Fdatabase source\n10. **English-first queries** - Always use English terms in tool calls\n\n---\n\n## LOOK UP, DON'T GUESS\nWhen uncertain about any scientific fact, SEARCH databases first (PubMed, UniProt, ChEMBL, ClinVar, etc.) 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- Provide spatially variable genes from spatial transcriptomics experiments\n- Ask about biological interpretation of spatial domains\u002Fclusters\n- Need pathway enrichment of spatial gene expression data\n- Want to understand cell-cell interactions from spatial data\n- Ask about tumor microenvironment heterogeneity from spatial omics\n- Need druggable targets in specific spatial regions\n- Ask about tissue zonation patterns (liver, brain, kidney)\n- Want to integrate spatial transcriptomics + proteomics data\n\n**NOT for**: Single gene interpretation (use target-research), variant interpretation, drug safety, bulk RNA-seq, GWAS analysis.\n\n---\n\n## Input Parameters\n\n| Parameter | Required | Description | Example |\n|-----------|----------|-------------|---------|\n| **svgs** | Yes | Spatially variable genes | `['EGFR', 'CDH1', 'VIM', 'MYC', 'CD3E']` |\n| **tissue_type** | Yes | Tissue\u002Forgan type | `brain`, `liver`, `lung`, `breast` |\n| **technology** | No | Spatial omics platform | `10x Visium`, `MERFISH`, `DBiTplus` |\n| **disease_context** | No | Disease if applicable | `breast cancer`, `Alzheimer disease` |\n| **spatial_domains** | No | Domain -> marker genes dict | `{'Tumor core': ['MYC','EGFR']}` |\n| **cell_types** | No | Cell types from deconvolution | `['Epithelial', 'T cell']` |\n| **proteins** | No | Proteins detected (multi-modal) | `['CD3', 'PD-L1', 'Ki67']` |\n| **metabolites** | No | Metabolites (SpatialMETA) | `['glutamine', 'lactate']` |\n\n---\n\n## Spatial Omics Integration Score (0-100)\n\n**Data Completeness (0-30)**: SVGs (5), Disease context (5), Spatial domains (5), Cell types (5), Multi-modal (5), Literature (5)\n\n**Biological Insight (0-40)**: Pathway enrichment FDR\u003C0.05 (10), Cell-cell interactions (10), Disease mechanism (10), Druggable targets (10)\n\n**Evidence Quality (0-30)**: Cross-database validation 3+ DBs (10), Clinical validation (10), Literature support (10)\n\n| Score | Tier | Interpretation |\n|-------|------|----------------|\n| 80-100 | Excellent | Comprehensive characterization, strong insights, druggable targets |\n| 60-79 | Good | Good pathway\u002Finteraction analysis, some therapeutic context |\n| 40-59 | Moderate | Basic enrichment, limited domain comparison |\n| 0-39 | Limited | Minimal data, gene-level annotation only |\n\n### Evidence Grading\n\n| Tier | Criteria | Examples |\n|------|----------|----------|\n| [T1] | Direct human\u002Fclinical evidence | FDA-approved drug, validated biomarker |\n| [T2] | Experimental evidence | Validated spatial pattern, known L-R pair |\n| [T3] | Computational\u002Fdatabase evidence | PPI prediction, pathway enrichment |\n| [T4] | Annotation\u002Fprediction only | GO annotation, text-mined association |\n\n---\n\n## Analysis Phases Overview\n\n### Phase 0: Input Processing & Disambiguation (ALWAYS FIRST)\nResolve tissue\u002Fdisease identifiers, establish analysis context. Get MONDO\u002FEFO IDs for disease queries.\n- Tools: `OpenTargets_get_disease_id_description_by_name`, `OpenTargets_get_disease_description_by_efoId`, `HPA_search_genes_by_query`\n\n### Phase 1: Gene Characterization\nResolve gene IDs, annotate functions, tissue specificity, subcellular localization.\n- Tools: `MyGene_query_genes`, `UniProt_get_function_by_accession`, `HPA_get_subcellular_location`, `HPA_get_rna_expression_by_source`, `HPA_get_comprehensive_gene_details_by_ensembl_id`, `HPA_get_cancer_prognostics_by_gene`, `UniProtIDMap_gene_to_uniprot`\n\n### Phase 2: Pathway & Functional Enrichment\nIdentify enriched pathways globally and per-domain. Filter FDR \u003C 0.05.\n- Tools: `STRING_functional_enrichment` (PRIMARY), `ReactomeAnalysis_pathway_enrichment`, `GO_get_annotations_for_gene`, `kegg_search_pathway`, `WikiPathways_search`\n\n### Phase 3: Spatial Domain Characterization\nCharacterize each domain biologically, assign cell types from markers, compare domains.\n- Tools: Phase 2 tools + `HPA_get_biological_processes_by_gene`, `HPA_get_protein_interactions_by_gene`\n\n### Phase 4: Cell-Cell Interaction Inference\nPredict communication from spatial patterns. Check ligand-receptor pairs across domains.\n- Tools: `STRING_get_interaction_partners`, `STRING_get_protein_interactions`, `intact_search_interactions`, `Reactome_get_interactor`, `DGIdb_get_drug_gene_interactions`\n\n### Phase 5: Disease & Therapeutic Context\nConnect to disease mechanisms, identify druggable targets, find clinical trials.\n- Tools: `OpenTargets_get_associated_targets_by_disease_efoId`, `OpenTargets_get_target_tractability_by_ensemblID`, `OpenTargets_get_associated_drugs_by_target_ensemblID`, `search_clinical_trials`, `DGIdb_get_gene_druggability`, `civic_search_genes`\n\n### Phase 6: Multi-Modal Integration\nIntegrate protein\u002FRNA\u002Fmetabolite data. Compare spatial RNA with protein detection.\n- Tools: `HPA_get_subcellular_location`, `HPA_get_rna_expression_in_specific_tissues`, `Reactome_map_uniprot_to_pathways`, `kegg_get_pathway_info`\n\n### Phase 7: Immune Microenvironment (Cancer\u002FInflammation only)\nClassify immune cells, check checkpoint expression, assess Hot vs Cold vs Excluded patterns.\n- Tools: `STRING_functional_enrichment`, `OpenTargets_get_target_tractability_by_ensemblID`, `iedb_search_epitopes`\n\n### Phase 8: Literature & Validation Context\nSearch published evidence, suggest validation experiments (smFISH, IHC, PLA).\n- Tools: `PubMed_search_articles`, `openalex_literature_search`\n\n### Data Discovery: HuBMAP Spatial Atlas Tools\n\nUse HuBMAP tools to find published spatial biology reference datasets for comparison, validation, or cross-study analysis.\n\n| Tool | Purpose | Key Parameters |\n|------|---------|----------------|\n| `HuBMAP_search_datasets` | Search published spatial datasets by organ\u002Fassay\u002Fkeyword | `organ` (code: \"LK\"=Kidney, \"BR\"=Brain, \"LU\"=Lung, etc.), `dataset_type` (\"RNAseq\", \"CODEX\", \"MALDI\"), `query`, `limit` |\n| `HuBMAP_list_organs` | List all available organs with codes and UBERON IDs | (no required params) |\n| `HuBMAP_get_dataset` | Get detailed metadata for a specific HuBMAP dataset | `hubmap_id` (e.g. \"HBM626.FHJD.938\") |\n\n**When to use**: Phase 0 (find reference datasets for the tissue), Phase 8 (cross-reference findings with published HuBMAP atlas data).\n\nSee **phase-procedures.md** for detailed workflows, decision logic, and tool parameter specifications per phase.\n\n---\n\n## Report Structure\n\nCreate file: `{tissue}_{disease}_spatial_omics_report.md`\n\n```\n# Spatial Multi-Omics Analysis Report: {Tissue Type}\n**Report Generated**: {date} | **Technology**: {platform}\n**Tissue**: {tissue_type} | **Disease**: {disease or \"Normal tissue\"}\n**Total SVGs**: {count} | **Spatial Domains**: {count}\n**Spatial Omics Integration Score**: (calculated after analysis)\n\n## Executive Summary\n## 1. Tissue & Disease Context\n## 2. Spatially Variable Gene Characterization\n  - 2.1 Gene ID Resolution\n  - 2.2 Tissue Expression Patterns\n  - 2.3 Subcellular Localization\n  - 2.4 Disease Associations\n## 3. Pathway Enrichment Analysis\n  - 3.1 STRING, 3.2 Reactome, 3.3-3.5 GO (BP, MF, CC)\n## 4. Spatial Domain Characterization (per-domain + comparison)\n## 5. Cell-Cell Interaction Inference\n  - 5.1 PPI, 5.2 Ligand-Receptor, 5.3 Signaling Pathways\n## 6. Disease & Therapeutic Context\n  - 6.1 Disease Gene Overlap, 6.2 Druggable Targets, 6.3 Drug Mechanisms, 6.4 Trials\n## 7. Multi-Modal Integration (if data available)\n## 8. Immune Microenvironment (if relevant)\n## 9. Literature & Validation Context\n## Spatial Omics Integration Score (breakdown table)\n## Completeness Checklist\n## References (tools used, database versions)\n```\n\nSee **report-template.md** for full template with table structures.\n\n---\n\n## Completeness Checklist\n\n- [ ] Gene ID resolution complete\n- [ ] Tissue expression patterns analyzed (HPA)\n- [ ] Subcellular localization checked (HPA)\n- [ ] Pathway enrichment complete (STRING + Reactome)\n- [ ] GO enrichment complete (BP + MF + CC)\n- [ ] Spatial domains characterized individually\n- [ ] Domain comparison performed\n- [ ] PPI analyzed (STRING)\n- [ ] Ligand-receptor pairs identified\n- [ ] Disease associations checked (OpenTargets)\n- [ ] Druggable targets identified\n- [ ] Multi-modal integration performed (if data available)\n- [ ] Immune microenvironment characterized (if relevant)\n- [ ] Literature search completed\n- [ ] Validation recommendations provided\n- [ ] Integration Score calculated\n- [ ] Executive summary written\n- [ ] All sections have source citations\n\n---\n\n## Common Use Cases\n\n1. **Cancer Spatial Heterogeneity**: Visium with tumor\u002Fstroma\u002Fimmune domains -> pathways, immune infiltration, druggable targets, checkpoints\n2. **Brain Tissue Zonation**: MERFISH with neuronal subtypes -> synaptic signaling, receptors, hippocampal zonation\n3. **Liver Metabolic Zonation**: Periportal vs pericentral -> CYP450, Wnt gradient, drug metabolism enzymes\n4. **Tumor-Immune Interface**: DBiTplus RNA+protein -> checkpoint L-R pairs, immune exclusion, multi-modal concordance\n5. **Developmental Patterns**: Morphogen gradients (Wnt, BMP, FGF, SHH), TF patterns, cell fate genes\n6. **Disease Progression**: Disease gradient -> inflammatory response, neuronal loss, therapeutic windows\n\n---\n\n## Reference Files\n\n- **phase-procedures.md** - Detailed phase workflows, decision logic, tool usage per phase\n- **tool-reference.md** - Tool parameter names, response formats, fallback strategies, limitations\n- **reference-data.md** - Cell type markers, ligand-receptor pairs, immune checkpoint reference\n- **report-template.md** - Full report template with all table structures\n- **test_spatial_omics.py** - Test suite\n\n---\n\n## Summary\n\n**Spatial Multi-Omics Analysis** provides:\n1. Gene characterization (ID resolution, function, localization, tissue expression)\n2. Pathway & functional enrichment (STRING, Reactome, GO, KEGG)\n3. Spatial domain characterization (per-domain and cross-domain)\n4. Cell-cell interaction inference (PPI, ligand-receptor, signaling)\n5. Disease & therapeutic context (disease genes, druggable targets, trials)\n6. Multi-modal integration (RNA-protein concordance, metabolic pathways)\n7. Immune microenvironment (cell types, checkpoints, immunotherapy)\n8. Literature context & validation recommendations\n\n**Outputs**: Markdown report with Spatial Omics Integration Score (0-100)\n**Uses**: 70+ ToolUniverse tools across 9 analysis phases\n**Time**: ~10-20 minutes depending on gene list size\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Flibrary\u002Fskills\u002Ftooluniverse-spatial-omics-analysis","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":51,"prompt":61,"zipAvailable":62},[52,55,58],{"tool":53,"command":54},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-spatial-omics-analysis",{"tool":56,"command":57},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-spatial-omics-analysis",{"tool":59,"command":60},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-spatial-omics-analysis","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-spatial-omics-analysis\u002FSKILL.md",true,[64,70,74,78,82,88],{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"agents\u002Fopenai.yaml","REFERENCE","参考文档",82,"https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions\u002Fyuri-os\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fsales-psychology\u002Fagents\u002Fopenai.yaml",{"path":71,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":72,"sourceHtmlUrl":73},"phase-procedures.md",10702,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-spatial-omics-analysis\u002Fphase-procedures.md",{"path":75,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":76,"sourceHtmlUrl":77},"reference-data.md",4371,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-spatial-omics-analysis\u002Freference-data.md",{"path":79,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":80,"sourceHtmlUrl":81},"report-template.md",8217,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-spatial-omics-analysis\u002Freport-template.md",{"path":83,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":86,"sourceHtmlUrl":87},"test_spatial_omics.py","SCRIPT","脚本",52643,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-spatial-omics-analysis\u002Ftest_spatial_omics.py",{"path":89,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":90,"sourceHtmlUrl":91},"tool-reference.md",5755,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-spatial-omics-analysis\u002Ftool-reference.md",[93,114,145,172,185,201],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":39},"01M6DF7D7478R55P46REYH4QAC","clarify-requirements","Resolve genuine pre-execution ambiguity by scanning repo context, generating 1-6 grounded options, and asking 1-3 focused questions via AskUserQuestion. NOT for mid-task use (injection risk); NOT when the goal is already unambiguous; use to disambiguate vague prompts before any file edits.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fworkspace-hooks\u002Fskills\u002Fclarify-requirements\u002FSKILL.md",[],[100,101,102,103,104,105,106,107,108,31,109,110,111,112,113],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","context","repo","injection","execution","file",{"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":125,"publishedAt":39},"01M6DF79CA4BHJS66J8EZDBPWJ","openmm-md","Run FREE, open-source, Windows-native GPU molecular dynamics via the openmm-md MCP (OpenMM + CUDA on the local NVIDIA GPU). Use for protein \u002F protein-ligand MD when you want a free stack or are on Windows without a Schrodinger license. Covers the full workflow (prepare, solvate, minimize, equilibrate, production, analyze, mmgbsa) AND an honest decision guide vs Schrodinger Desmond, including how to run Desmond legitimately on Linux or a cloud GPU with a real license. This is a deliberately LESSER free alternative and does NOT replace the schrodinger MCP tools. Do NOT use it to pick a free tool when a validated FEP+, WaterMap, IFD-MD, or Prime MM-GBSA result is actually required.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fmcp\u002Fopenmm-md-mcp\u002Fskill\u002Fopenmm-md\u002FSKILL.md",[120],{"categoryNo":121,"categoryName":122,"taxonomyType":123,"taxonomyTypeDesc":124},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[126,127,128,129,130,131,132,133,134,135,136,137,138,139,31,140,141,142,143,144],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":146,"name":147,"nameZh":6,"description":148,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":149,"categories":150,"keywords":157,"publishedAt":39},"01M6DF76C1MG85VEWP8VZCBNMN","visual-review","Take screenshots of web pages and UI using Playwright for visual review and iteration","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fvisual-review\u002FSKILL.md",[151,154],{"categoryNo":152,"categoryName":153,"taxonomyType":123,"taxonomyTypeDesc":124},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":155,"categoryName":156,"taxonomyType":123,"taxonomyTypeDesc":124},"01JBSEEDCAT000000000000008","测试与质量",[158,159,160,161,162,163,164,165,166,167,127,168,169,170,171],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":173,"name":174,"nameZh":6,"description":175,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":176,"categories":177,"keywords":178,"publishedAt":39},"01M6DF73AQVCBZKEN0YXEX9FXP","status","Diagnostic status report — shows metaswarm installation state, project setup, and potential issues","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstatus\u002FSKILL.md",[],[174,179,38,180,181,182,183,184],"setup","project","installation","project setup","issues","state",{"skillNo":186,"name":187,"nameZh":6,"description":188,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":189,"categories":190,"keywords":192,"publishedAt":39},"01M6DF6X6C2XB0P6GX76P7TTYV","start","Use when starting work on any task, when the user mentions metaswarm, or when the user wants to begin tracked development work","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstart\u002FSKILL.md",[191],{"categoryNo":121,"categoryName":122,"taxonomyType":123,"taxonomyTypeDesc":124},[187,193,105,194,195,196,31,197,198,199,200],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":202,"name":179,"nameZh":6,"description":203,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":204,"categories":205,"keywords":206,"publishedAt":39},"01M6DF6QMJ9AJKFKHHKRT005PQ","Interactive project setup — detects your project, configures metaswarm, writes project-local files","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fsetup\u002FSKILL.md",[],[179,180,142,207,182,208],"files","interactive"]