[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DARF4DE1PEJM9QH2ZGJFGC":3,"skill-same:01M6DARF4DE1PEJM9QH2ZGJFGC":83},{"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":30,"linkOnly":31,"markdownContent":32,"markdownBody":33,"frontMatter":34,"refName":35,"commitSha":36,"skillDirectory":37,"forksCount":14,"repositoryHtmlUrl":38,"repositoryHomepageUrl":6,"ownerHtmlUrl":39,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":40,"install":41,"resources":54},"01M6DARF4DE1PEJM9QH2ZGJFGC","tooluniverse-gwas-snp-interpretation",null,"Interpret genetic variants (SNPs) from GWAS studies by aggregating evidence from multiple databases (GWAS Catalog, Open Targets Genetics, ClinVar). Retrieves variant annotations, GWAS trait associations, fine-mapping evidence, locus-to-gene predictions, and clinical significance. Use when asked to interpret a SNP by rsID, find disease associations for a variant, assess clinical significance, or answer questions like \"What diseases is rs429358 associated with?\" or \"Interpret rs7903146\".","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-gwas-snp-interpretation\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29],"interpretation","tooluniverse gwas snp interpretation","open","annotations","find","catalog","use","evidence","databases","genetics","clinical","2026-11-10 10:12:30",false,"---\nname: tooluniverse-gwas-snp-interpretation\ndescription: Interpret genetic variants (SNPs) from GWAS studies by aggregating evidence from multiple databases (GWAS Catalog, Open Targets Genetics, ClinVar). Retrieves variant annotations, GWAS trait associations, fine-mapping evidence, locus-to-gene predictions, and clinical significance. Use when asked to interpret a SNP by rsID, find disease associations for a variant, assess clinical significance, or answer questions like \"What diseases is rs429358 associated with?\" or \"Interpret rs7903146\".\n---\n\n# GWAS SNP Interpretation Skill\n\n**SNP interpretation**: a GWAS hit is a REGION, not a single causal variant. The lead SNP may not be causal — it may be in LD with the causal variant. Always check LD structure and functional annotation before concluding a specific SNP is mechanistically responsible. Fine-mapping (SuSiE, FINEMAP credible sets) narrows the causal set but rarely identifies a single variant with certainty. L2G scores integrate eQTL, chromatin interaction, and distance data to predict the causal gene — a lead SNP mapping to gene A may actually regulate gene B 500 kb away via a distal enhancer.\n\n**LOOK UP DON'T GUESS**: never assume a SNP's functional consequence, mapped gene, or population frequency — always call `gwas_get_snp_by_id` and `OpenTargets_get_variant_info` to retrieve current annotations.\n\n## Overview\n\nInterpret genetic variants (SNPs) from GWAS studies by aggregating evidence from multiple sources to provide comprehensive clinical and biological context.\n\n**Use Cases:**\n- \"Interpret rs7903146\" (TCF7L2 diabetes variant)\n- \"What diseases is rs429358 associated with?\" (APOE Alzheimer's variant)\n- \"Clinical significance of rs1801133\" (MTHFR variant)\n- \"Is rs12913832 in any fine-mapped loci?\" (Eye color variant)\n\n## What It Does\n\nThe skill provides a comprehensive interpretation of SNPs by:\n\n1. **SNP Annotation**: Retrieves basic variant information including genomic coordinates, alleles, functional consequence, and mapped genes\n2. **Association Discovery**: Finds all GWAS trait\u002Fdisease associations with statistical significance\n3. **Fine-Mapping Evidence**: Identifies credible sets the variant belongs to (fine-mapped causal loci)\n4. **Gene Mapping**: Uses Locus-to-Gene (L2G) predictions to identify likely causal genes\n5. **Clinical Summary**: Aggregates evidence into actionable clinical significance\n\n## Workflow\n\n```\nUser Input: rs7903146\n    ↓\n[1] SNP Lookup\n    → Get location, consequence, MAF\n    → gwas_get_snp_by_id\n    ↓\n[2] Association Search\n    → Find all trait\u002Fdisease associations\n    → gwas_get_associations_for_snp\n    ↓\n[3] Fine-Mapping (Optional)\n    → Get credible set membership\n    → OpenTargets_get_variant_credible_sets\n    ↓\n[4] Gene Predictions\n    → Extract L2G scores for causal genes\n    → (embedded in credible sets)\n    ↓\n[5] Clinical Summary\n    → Aggregate evidence\n    → Identify key traits and genes\n    ↓\nOutput: Comprehensive Interpretation Report\n```\n\n## Data Sources\n\n### GWAS Catalog (EMBL-EBI)\n- **SNP annotations**: Functional consequences, mapped genes, population frequencies\n- **Associations**: P-values, effect sizes, study metadata\n- **Coverage**: 350,000+ publications, 670,000+ associations\n\n### Open Targets Genetics\n- **Fine-mapping**: Statistical credible sets from SuSiE, FINEMAP methods\n- **L2G predictions**: Machine learning-based gene prioritization\n- **Colocalization**: QTL evidence for causal genes\n- **Coverage**: UK Biobank, FinnGen, and other large cohorts\n\n## Input Parameters\n\n### Required\n- `rs_id` (str): dbSNP rs identifier\n  - Format: \"rs\" + number (e.g., \"rs7903146\")\n  - Must be valid rsID in GWAS Catalog\n\n### Optional\n- `include_credible_sets` (bool, default=True): Query fine-mapping data\n  - True: Complete interpretation (slower, ~10-30s)\n  - False: Fast associations only (~2-5s)\n- `p_threshold` (float, default=5e-8): Genome-wide significance threshold\n- `max_associations` (int, default=100): Maximum associations to retrieve\n\n## Output Format\n\nReturns `SNPInterpretationReport` containing:\n\n### 1. SNP Basic Info\n```python\n{\n    'rs_id': 'rs7903146',\n    'chromosome': '10',\n    'position': 112998590,\n    'ref_allele': 'C',\n    'alt_allele': 'T',\n    'consequence': 'intron_variant',\n    'mapped_genes': ['TCF7L2'],\n    'maf': 0.293\n}\n```\n\n### 2. Trait Associations\n```python\n[\n    {\n        'trait': 'Type 2 diabetes',\n        'p_value': 1.2e-128,\n        'beta': '0.28 unit increase',\n        'study_id': 'GCST010555',\n        'pubmed_id': '33536258',\n        'effect_allele': 'T'\n    },\n    ...\n]\n```\n\n### 3. Credible Sets (Fine-Mapping)\n```python\n[\n    {\n        'study_id': 'GCST90476118',\n        'trait': 'Renal failure',\n        'finemapping_method': 'SuSiE-inf',\n        'p_value': 3.5e-42,\n        'predicted_genes': [\n            {'gene': 'TCF7L2', 'score': 0.863}\n        ],\n        'region': '10:112950000-113050000'\n    },\n    ...\n]\n```\n\n### 4. Clinical Significance\n```\nGenome-wide significant associations with 100 traits\u002Fdiseases:\n  - Type 2 diabetes\n  - Diabetic retinopathy\n  - HbA1c levels\n  ...\n\nIdentified in 20 fine-mapped loci.\nPredicted causal genes: TCF7L2\n```\n\n## Example Usage\n\nSee `QUICK_START.md` for platform-specific examples.\n\n## Tools Used\n\n### GWAS Catalog Tools\n1. `gwas_get_snp_by_id`: Get SNP annotation\n2. `gwas_get_associations_for_snp`: Get all trait associations\n\n### Open Targets Tools\n3. `OpenTargets_get_variant_info`: Get variant details with population frequencies\n4. `OpenTargets_get_variant_credible_sets`: Get fine-mapping credible sets with L2G\n\n## Interpretation Guide\n\n### P-value Significance Levels\n- **p \u003C 5e-8**: Genome-wide significant (strong evidence)\n- **p \u003C 5e-6**: Suggestive (moderate evidence)\n- **p \u003C 0.05**: Nominal (weak evidence)\n\n### L2G Score Interpretation\n- **> 0.5**: High confidence causal gene\n- **0.1-0.5**: Moderate confidence\n- **\u003C 0.1**: Low confidence\n\n### Clinical Actionability\n1. **High**: Multiple genome-wide significant associations + in credible sets + high L2G scores\n2. **Moderate**: Genome-wide significant associations but limited fine-mapping\n3. **Low**: Suggestive associations or limited replication\n\n## Limitations\n\n1. **Variant ID Conversion**: OpenTargets requires chr_pos_ref_alt format, which may need allele lookup\n2. **Population Specificity**: Associations may vary by ancestry\n3. **Effect Sizes**: Beta values are study-dependent (different phenotype scales)\n4. **Causality**: Associations don't prove causation; fine-mapping improves confidence\n5. **Currency**: Data reflects published GWAS; latest studies may not be included\n\n## Best Practices\n\n1. **Use Full Interpretation**: Enable `include_credible_sets=True` for clinical decisions\n2. **Check Multiple Variants**: Look at other variants in the same locus\n3. **Validate Populations**: Consider ancestry-specific effect sizes\n4. **Review Publications**: Check original studies for context\n5. **Integrate Evidence**: Combine with functional data, eQTLs, pQTLs\n\n## Technical Notes\n\n### Performance\n- **Fast mode** (no credible sets): 2-5 seconds\n- **Full mode** (with credible sets): 10-30 seconds\n- **Bottleneck**: OpenTargets GraphQL API rate limits\n\n### Error Handling\n- Invalid rs_id: Returns error message\n- No associations: Returns empty list with note\n- API failures: Graceful degradation (returns partial results)\n\n## Related Skills\n\n- **Gene Function Analysis**: Interpret predicted causal genes\n- **Disease Ontology Lookup**: Understand trait classifications\n- **PubMed Literature Search**: Find original GWAS publications\n- **Variant Effect Prediction**: Functional consequence analysis\n\n## References\n\n1. GWAS Catalog: https:\u002F\u002Fwww.ebi.ac.uk\u002Fgwas\u002F\n2. Open Targets Genetics: https:\u002F\u002Fgenetics.opentargets.org\u002F\n3. GWAS Significance Thresholds: Fadista et al. 2016\n4. L2G Method: Mountjoy et al. 2021 (Nature Genetics)\n\n## Version\n\n- **Version**: 1.0.0\n- **Last Updated**: 2026-02-13\n- **ToolUniverse Version**: >= 1.0.0\n- **Tools Required**: gwas_get_snp_by_id, gwas_get_associations_for_snp, OpenTargets_get_variant_credible_sets\n","# GWAS SNP Interpretation Skill\n\n**SNP interpretation**: a GWAS hit is a REGION, not a single causal variant. The lead SNP may not be causal — it may be in LD with the causal variant. Always check LD structure and functional annotation before concluding a specific SNP is mechanistically responsible. Fine-mapping (SuSiE, FINEMAP credible sets) narrows the causal set but rarely identifies a single variant with certainty. L2G scores integrate eQTL, chromatin interaction, and distance data to predict the causal gene — a lead SNP mapping to gene A may actually regulate gene B 500 kb away via a distal enhancer.\n\n**LOOK UP DON'T GUESS**: never assume a SNP's functional consequence, mapped gene, or population frequency — always call `gwas_get_snp_by_id` and `OpenTargets_get_variant_info` to retrieve current annotations.\n\n## Overview\n\nInterpret genetic variants (SNPs) from GWAS studies by aggregating evidence from multiple sources to provide comprehensive clinical and biological context.\n\n**Use Cases:**\n- \"Interpret rs7903146\" (TCF7L2 diabetes variant)\n- \"What diseases is rs429358 associated with?\" (APOE Alzheimer's variant)\n- \"Clinical significance of rs1801133\" (MTHFR variant)\n- \"Is rs12913832 in any fine-mapped loci?\" (Eye color variant)\n\n## What It Does\n\nThe skill provides a comprehensive interpretation of SNPs by:\n\n1. **SNP Annotation**: Retrieves basic variant information including genomic coordinates, alleles, functional consequence, and mapped genes\n2. **Association Discovery**: Finds all GWAS trait\u002Fdisease associations with statistical significance\n3. **Fine-Mapping Evidence**: Identifies credible sets the variant belongs to (fine-mapped causal loci)\n4. **Gene Mapping**: Uses Locus-to-Gene (L2G) predictions to identify likely causal genes\n5. **Clinical Summary**: Aggregates evidence into actionable clinical significance\n\n## Workflow\n\n```\nUser Input: rs7903146\n    ↓\n[1] SNP Lookup\n    → Get location, consequence, MAF\n    → gwas_get_snp_by_id\n    ↓\n[2] Association Search\n    → Find all trait\u002Fdisease associations\n    → gwas_get_associations_for_snp\n    ↓\n[3] Fine-Mapping (Optional)\n    → Get credible set membership\n    → OpenTargets_get_variant_credible_sets\n    ↓\n[4] Gene Predictions\n    → Extract L2G scores for causal genes\n    → (embedded in credible sets)\n    ↓\n[5] Clinical Summary\n    → Aggregate evidence\n    → Identify key traits and genes\n    ↓\nOutput: Comprehensive Interpretation Report\n```\n\n## Data Sources\n\n### GWAS Catalog (EMBL-EBI)\n- **SNP annotations**: Functional consequences, mapped genes, population frequencies\n- **Associations**: P-values, effect sizes, study metadata\n- **Coverage**: 350,000+ publications, 670,000+ associations\n\n### Open Targets Genetics\n- **Fine-mapping**: Statistical credible sets from SuSiE, FINEMAP methods\n- **L2G predictions**: Machine learning-based gene prioritization\n- **Colocalization**: QTL evidence for causal genes\n- **Coverage**: UK Biobank, FinnGen, and other large cohorts\n\n## Input Parameters\n\n### Required\n- `rs_id` (str): dbSNP rs identifier\n  - Format: \"rs\" + number (e.g., \"rs7903146\")\n  - Must be valid rsID in GWAS Catalog\n\n### Optional\n- `include_credible_sets` (bool, default=True): Query fine-mapping data\n  - True: Complete interpretation (slower, ~10-30s)\n  - False: Fast associations only (~2-5s)\n- `p_threshold` (float, default=5e-8): Genome-wide significance threshold\n- `max_associations` (int, default=100): Maximum associations to retrieve\n\n## Output Format\n\nReturns `SNPInterpretationReport` containing:\n\n### 1. SNP Basic Info\n```python\n{\n    'rs_id': 'rs7903146',\n    'chromosome': '10',\n    'position': 112998590,\n    'ref_allele': 'C',\n    'alt_allele': 'T',\n    'consequence': 'intron_variant',\n    'mapped_genes': ['TCF7L2'],\n    'maf': 0.293\n}\n```\n\n### 2. Trait Associations\n```python\n[\n    {\n        'trait': 'Type 2 diabetes',\n        'p_value': 1.2e-128,\n        'beta': '0.28 unit increase',\n        'study_id': 'GCST010555',\n        'pubmed_id': '33536258',\n        'effect_allele': 'T'\n    },\n    ...\n]\n```\n\n### 3. Credible Sets (Fine-Mapping)\n```python\n[\n    {\n        'study_id': 'GCST90476118',\n        'trait': 'Renal failure',\n        'finemapping_method': 'SuSiE-inf',\n        'p_value': 3.5e-42,\n        'predicted_genes': [\n            {'gene': 'TCF7L2', 'score': 0.863}\n        ],\n        'region': '10:112950000-113050000'\n    },\n    ...\n]\n```\n\n### 4. Clinical Significance\n```\nGenome-wide significant associations with 100 traits\u002Fdiseases:\n  - Type 2 diabetes\n  - Diabetic retinopathy\n  - HbA1c levels\n  ...\n\nIdentified in 20 fine-mapped loci.\nPredicted causal genes: TCF7L2\n```\n\n## Example Usage\n\nSee `QUICK_START.md` for platform-specific examples.\n\n## Tools Used\n\n### GWAS Catalog Tools\n1. `gwas_get_snp_by_id`: Get SNP annotation\n2. `gwas_get_associations_for_snp`: Get all trait associations\n\n### Open Targets Tools\n3. `OpenTargets_get_variant_info`: Get variant details with population frequencies\n4. `OpenTargets_get_variant_credible_sets`: Get fine-mapping credible sets with L2G\n\n## Interpretation Guide\n\n### P-value Significance Levels\n- **p \u003C 5e-8**: Genome-wide significant (strong evidence)\n- **p \u003C 5e-6**: Suggestive (moderate evidence)\n- **p \u003C 0.05**: Nominal (weak evidence)\n\n### L2G Score Interpretation\n- **> 0.5**: High confidence causal gene\n- **0.1-0.5**: Moderate confidence\n- **\u003C 0.1**: Low confidence\n\n### Clinical Actionability\n1. **High**: Multiple genome-wide significant associations + in credible sets + high L2G scores\n2. **Moderate**: Genome-wide significant associations but limited fine-mapping\n3. **Low**: Suggestive associations or limited replication\n\n## Limitations\n\n1. **Variant ID Conversion**: OpenTargets requires chr_pos_ref_alt format, which may need allele lookup\n2. **Population Specificity**: Associations may vary by ancestry\n3. **Effect Sizes**: Beta values are study-dependent (different phenotype scales)\n4. **Causality**: Associations don't prove causation; fine-mapping improves confidence\n5. **Currency**: Data reflects published GWAS; latest studies may not be included\n\n## Best Practices\n\n1. **Use Full Interpretation**: Enable `include_credible_sets=True` for clinical decisions\n2. **Check Multiple Variants**: Look at other variants in the same locus\n3. **Validate Populations**: Consider ancestry-specific effect sizes\n4. **Review Publications**: Check original studies for context\n5. **Integrate Evidence**: Combine with functional data, eQTLs, pQTLs\n\n## Technical Notes\n\n### Performance\n- **Fast mode** (no credible sets): 2-5 seconds\n- **Full mode** (with credible sets): 10-30 seconds\n- **Bottleneck**: OpenTargets GraphQL API rate limits\n\n### Error Handling\n- Invalid rs_id: Returns error message\n- No associations: Returns empty list with note\n- API failures: Graceful degradation (returns partial results)\n\n## Related Skills\n\n- **Gene Function Analysis**: Interpret predicted causal genes\n- **Disease Ontology Lookup**: Understand trait classifications\n- **PubMed Literature Search**: Find original GWAS publications\n- **Variant Effect Prediction**: Functional consequence analysis\n\n## References\n\n1. GWAS Catalog: https:\u002F\u002Fwww.ebi.ac.uk\u002Fgwas\u002F\n2. Open Targets Genetics: https:\u002F\u002Fgenetics.opentargets.org\u002F\n3. GWAS Significance Thresholds: Fadista et al. 2016\n4. L2G Method: Mountjoy et al. 2021 (Nature Genetics)\n\n## Version\n\n- **Version**: 1.0.0\n- **Last Updated**: 2026-02-13\n- **ToolUniverse Version**: >= 1.0.0\n- **Tools Required**: gwas_get_snp_by_id, gwas_get_associations_for_snp, OpenTargets_get_variant_credible_sets\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Flibrary\u002Fskills\u002Ftooluniverse-gwas-snp-interpretation","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":42,"prompt":52,"zipAvailable":53},[43,46,49],{"tool":44,"command":45},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-gwas-snp-interpretation",{"tool":47,"command":48},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-gwas-snp-interpretation",{"tool":50,"command":51},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-gwas-snp-interpretation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-gwas-snp-interpretation\u002FSKILL.md",true,[55,61,67,71,75,79],{"path":56,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":59,"sourceHtmlUrl":60},"FINAL_VERIFICATION.txt","REFERENCE","参考文档",4872,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-gwas-snp-interpretation\u002FFINAL_VERIFICATION.txt",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"python_implementation.py","SCRIPT","脚本",11000,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-gwas-snp-interpretation\u002Fpython_implementation.py",{"path":68,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":69,"sourceHtmlUrl":70},"QUICK_START.md",3719,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-gwas-snp-interpretation\u002FQUICK_START.md",{"path":72,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":73,"sourceHtmlUrl":74},"test_gwas_snp_tools_simple.py",2733,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-gwas-snp-interpretation\u002Ftest_gwas_snp_tools_simple.py",{"path":76,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":77,"sourceHtmlUrl":78},"test_gwas_snp_tools.py",6519,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-gwas-snp-interpretation\u002Ftest_gwas_snp_tools.py",{"path":80,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":81,"sourceHtmlUrl":82},"test_skill_comprehensive.py",9823,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-gwas-snp-interpretation\u002Ftest_skill_comprehensive.py",[84,105,135,162,176,192],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":30},"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",[],[91,92,93,94,95,96,97,98,99,25,100,101,102,103,104],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","context","repo","injection","execution","file",{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":116,"publishedAt":30},"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",[111],{"categoryNo":112,"categoryName":113,"taxonomyType":114,"taxonomyTypeDesc":115},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[117,118,119,120,121,122,123,124,21,125,126,127,128,129,25,130,131,132,133,134],"openmm md","how","decision","pick","linux","analyze","tool","stack","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":136,"name":137,"nameZh":6,"description":138,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":139,"categories":140,"keywords":147,"publishedAt":30},"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",[141,144],{"categoryNo":142,"categoryName":143,"taxonomyType":114,"taxonomyTypeDesc":115},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":145,"categoryName":146,"taxonomyType":114,"taxonomyTypeDesc":115},"01JBSEEDCAT000000000000008","测试与质量",[148,149,150,151,152,153,154,155,156,157,118,158,159,160,161],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":163,"name":164,"nameZh":6,"description":165,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":166,"categories":167,"keywords":168,"publishedAt":30},"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",[],[164,169,170,171,172,173,174,175],"setup","report","project","installation","project setup","issues","state",{"skillNo":177,"name":178,"nameZh":6,"description":179,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":180,"categories":181,"keywords":183,"publishedAt":30},"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",[182],{"categoryNo":112,"categoryName":113,"taxonomyType":114,"taxonomyTypeDesc":115},[178,184,96,185,186,187,25,188,189,190,191],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":193,"name":169,"nameZh":6,"description":194,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":195,"categories":196,"keywords":197,"publishedAt":30},"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",[],[169,171,132,198,173,199],"files","interactive"]