[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DARJ70MKAP2EADXWJV30PH":3,"skill-same:01M6DARJ70MKAP2EADXWJV30PH":68},{"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},"01M6DARJ70MKAP2EADXWJV30PH","tooluniverse-gwas-study-explorer",null,"Compare GWAS studies, perform meta-analyses, and assess replication across cohorts. Integrates NHGRI-EBI GWAS Catalog and Open Targets Genetics to compare study designs, effect sizes, ancestry diversity, and heterogeneity statistics. Use when comparing GWAS studies for a trait, performing meta-analysis of genetic loci, assessing replication across cohorts, or exploring the genetic architecture of complex diseases.","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-study-explorer\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32],"explorer","study","tooluniverse gwas study explorer","architecture","Meta","analysis","open","effect","catalog","use","across","diversity","genetics","statistics","2026-11-10 10:12:30",false,"---\nname: tooluniverse-gwas-study-explorer\ndescription: Compare GWAS studies, perform meta-analyses, and assess replication across cohorts. Integrates NHGRI-EBI GWAS Catalog and Open Targets Genetics to compare study designs, effect sizes, ancestry diversity, and heterogeneity statistics. Use when comparing GWAS studies for a trait, performing meta-analysis of genetic loci, assessing replication across cohorts, or exploring the genetic architecture of complex diseases.\n---\n\n\n# GWAS Study Deep Dive & Meta-Analysis\n\n**Compare GWAS studies, perform meta-analyses, and assess replication across cohorts**\n\n---\n\n## Overview\n\nThe GWAS Study Deep Dive & Meta-Analysis skill enables comprehensive comparison of genome-wide association studies (GWAS) for the same trait, meta-analysis of genetic loci across studies, and systematic assessment of replication and study quality. It integrates data from the NHGRI-EBI GWAS Catalog and Open Targets Genetics to provide a complete picture of the genetic architecture of complex traits.\n\n### Key Capabilities\n\n1. **Study Comparison**: Compare all GWAS studies for a trait, assessing sample sizes, ancestries, and platforms\n2. **Meta-Analysis**: Aggregate effect sizes across studies and calculate heterogeneity statistics\n3. **Replication Assessment**: Identify replicated vs novel findings across discovery and replication cohorts\n4. **Quality Evaluation**: Assess statistical power, ancestry diversity, and data availability\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## Domain Reasoning: Comparing Studies for the Same Trait\n\nWhen comparing GWAS studies for the same trait, ask: do they replicate? The same lead SNPs appearing in independent studies is strong evidence of a true association. Different lead SNPs at the same locus may reflect LD differences between populations — they may tag the same causal variant. Different loci entirely may reflect different study designs, phenotype definitions, or population ancestry. Before concluding that a finding failed to replicate, check whether the SNP was even genotyped or imputed in the replication cohort.\n\nLOOK UP DON'T GUESS: effect sizes, p-values, allele frequencies, and LD structure for specific loci. Do not assume a SNP present in one study is present in another — use `gwas_get_associations_for_snp` to retrieve cross-study data. Do not infer LD blocks from genomic proximity; use credible sets from Open Targets for fine-mapping results.\n\n---\n\n## Use Cases\n\n### 1. Comprehensive Trait Analysis\n**Scenario**: \"I want to understand all available GWAS data for type 2 diabetes\"\n\n**Workflow**:\n- Search for all T2D studies in GWAS Catalog\n- Filter by sample size and ancestry\n- Extract top associations from each study\n- Identify consistently replicated loci\n- Assess ancestry-specific effects\n\n**Outcome**: Complete landscape of T2D genetics with replicated findings and population-specific signals\n\n### 2. Locus-Specific Meta-Analysis\n**Scenario**: \"Is the TCF7L2 association with T2D consistent across all studies?\"\n\n**Workflow**:\n- Retrieve all TCF7L2 (rs7903146) associations for T2D\n- Calculate combined effect size and p-value\n- Assess heterogeneity (I² statistic)\n- Generate forest plot data\n- Interpret heterogeneity level\n\n**Outcome**: Quantitative assessment of effect size consistency with heterogeneity interpretation\n\n### 3. Replication Analysis\n**Scenario**: \"Which findings from the discovery cohort replicated in the independent sample?\"\n\n**Workflow**:\n- Get top hits from discovery study\n- Check for presence and significance in replication study\n- Assess direction consistency\n- Calculate replication rate\n- Identify novel vs failed replication\n\n**Outcome**: Systematic replication report with success rates and failed findings\n\n### 4. Multi-Ancestry Comparison\n**Scenario**: \"Are T2D loci consistent across European and East Asian populations?\"\n\n**Workflow**:\n- Filter studies by ancestry\n- Compare top associations between populations\n- Identify shared vs population-specific loci\n- Assess allele frequency differences\n- Evaluate transferability of genetic risk scores\n\n**Outcome**: Ancestry-specific genetic architecture with transferability assessment\n\n---\n\n## Statistical Methods\n\n### Meta-Analysis Approach\n\nThis skill implements standard GWAS meta-analysis methods:\n\n**Fixed-Effects Model**:\n- Used when heterogeneity is low (I² \u003C 25%)\n- Weights studies by inverse variance\n- Assumes true effect size is the same across studies\n\n**Random-Effects Model** (recommended when I² > 50%):\n- Accounts for between-study variation\n- More conservative than fixed-effects\n- Better for diverse ancestries or methodologies\n\n**Heterogeneity Assessment**:\n\nThe **I² statistic** measures the percentage of variance due to between-study heterogeneity:\n\n```\nI² = [(Q - df) \u002F Q] × 100%\n\nwhere Q = Cochran's Q statistic\n      df = degrees of freedom (n_studies - 1)\n```\n\n**Interpretation Guidelines**:\n- **I² \u003C 25%**: Low heterogeneity → fixed-effects appropriate\n- **I² = 25-50%**: Moderate heterogeneity → investigate sources\n- **I² = 50-75%**: Substantial heterogeneity → random-effects preferred\n- **I² > 75%**: Considerable heterogeneity → meta-analysis may not be appropriate\n\n### Sources of Heterogeneity\n\nCommon reasons for high I²:\n\n1. **Ancestry differences**: Different allele frequencies and LD structure\n2. **Phenotype heterogeneity**: Trait definition varies across studies\n3. **Platform differences**: Imputation quality and coverage\n4. **Winner's curse**: Discovery studies overestimate effect sizes\n5. **Cohort characteristics**: Age, sex, environmental factors\n\n**Recommendations**:\n- Perform subgroup analysis by ancestry\n- Use meta-regression to investigate sources\n- Consider excluding outlier studies\n- Apply genomic control correction\n\n---\n\n## Study Quality Assessment\n\n### Quality Metrics\n\nThe skill evaluates studies based on:\n\n**1. Sample Size**:\n- Power to detect associations (80% power requires n > 10,000 for OR=1.2)\n- Precision of effect size estimates\n- Ability to detect modest effects\n\n**2. Ancestry Diversity**:\n- Single-ancestry vs multi-ancestry\n- Population stratification control\n- Transferability of findings\n\n**3. Data Availability**:\n- Summary statistics available for meta-analysis\n- Individual-level data vs summary-level\n- Imputation quality scores\n\n**4. Genotyping Quality**:\n- Platform density and coverage\n- Imputation reference panel\n- Quality control measures\n\n**5. Statistical Rigor**:\n- Genome-wide significance threshold (p \u003C 5×10⁻⁸)\n- Multiple testing correction\n- Replication in independent cohort\n\n### Quality Tiers\n\n**Tier 1 (High Quality)**:\n- n ≥ 50,000\n- Summary statistics available\n- Multi-ancestry or large single-ancestry\n- Imputed to high-quality reference\n- Independent replication\n\n**Tier 2 (Moderate Quality)**:\n- n ≥ 10,000\n- Standard GWAS platform\n- Adequate power for common variants\n- Some data availability\n\n**Tier 3 (Limited)**:\n- n \u003C 10,000\n- Limited power\n- May miss modest effects\n- Use with caution\n\n---\n\n## Best Practices\n\n### Before Meta-Analysis\n\n1. **Check phenotype consistency**: Ensure studies measure the same trait\n2. **Verify ancestry overlap**: High heterogeneity expected if ancestries differ\n3. **Harmonize alleles**: Align effect alleles across studies\n4. **Quality control**: Exclude low-quality studies or associations\n\n### Interpreting Results\n\n1. **Genome-wide significance**: p \u003C 5×10⁻⁸ (Bonferroni for ~1M independent tests)\n2. **Replication threshold**: p \u003C 0.05 in independent cohort\n3. **Direction consistency**: Effect should be same direction across studies\n4. **Heterogeneity**: I² > 50% suggests caution in interpretation\n\n### Common Pitfalls\n\n❌ **Don't**:\n- Meta-analyze without checking heterogeneity\n- Ignore ancestry differences\n- Over-interpret nominal p-values\n- Assume replication failure means false positive\n\n✅ **Do**:\n- Always report I² statistic\n- Perform sensitivity analyses\n- Consider ancestry-stratified analysis\n- Account for winner's curse in discovery studies\n\n---\n\n## Limitations & Caveats\n\n### Data Limitations\n\n1. **Incomplete Overlap**: Studies may analyze different SNPs\n2. **Cohort Overlap**: Some cohorts participate in multiple studies (inflates significance)\n3. **Publication Bias**: Significant findings more likely to be published\n4. **Winner's Curse**: Discovery studies overestimate effect sizes\n5. **Imputation Quality**: Varies across studies and populations\n\n### Statistical Limitations\n\n1. **Heterogeneity**: High I² may preclude meaningful meta-analysis\n2. **Sample Size Differences**: Large studies dominate fixed-effects models\n3. **Allele Frequency Differences**: Same variant has different effects across ancestries\n4. **Linkage Disequilibrium**: Fine-mapping needed to identify causal variants\n5. **Gene-Environment Interactions**: Not captured in standard meta-analysis\n\n### Interpretation Guidelines\n\n**When I² > 75%**:\n- Meta-analysis results should be interpreted with extreme caution\n- Investigate sources of heterogeneity systematically\n- Consider ancestry-specific or subgroup analyses\n- Descriptive comparison may be more appropriate than meta-analysis\n\n**When Studies Conflict**:\n- Check for methodological differences\n- Verify phenotype definitions match\n- Investigate population stratification\n- Consider conditional analysis\n\n---\n\n## Tools Used\n\n### GWAS Catalog API\n- `gwas_search_studies`: Find studies by trait\n- `gwas_get_study_by_id`: Get detailed study metadata\n- `gwas_get_associations_for_study`: Retrieve study associations\n- `gwas_get_associations_for_snp`: Get SNP associations across studies\n- `gwas_search_associations`: Search associations by trait\n\n### Open Targets Genetics GraphQL API\n- `OpenTargets_search_gwas_studies_by_disease`: Disease-based study search\n- `OpenTargets_get_gwas_study`: Detailed study information with LD populations\n- `OpenTargets_get_variant_credible_sets`: Fine-mapped loci for variant\n- `OpenTargets_get_study_credible_sets`: All credible sets for study\n- `OpenTargets_get_variant_info`: Variant annotation and allele frequencies\n\n## Glossary\n\n**Credible Set**: Set of variants likely to contain the causal variant (from fine-mapping)\n\n**L2G (Locus-to-Gene)**: Score predicting which gene is affected by a GWAS locus\n**License**: Open source (MIT)\n","# GWAS Study Deep Dive & Meta-Analysis\n\n**Compare GWAS studies, perform meta-analyses, and assess replication across cohorts**\n\n---\n\n## Overview\n\nThe GWAS Study Deep Dive & Meta-Analysis skill enables comprehensive comparison of genome-wide association studies (GWAS) for the same trait, meta-analysis of genetic loci across studies, and systematic assessment of replication and study quality. It integrates data from the NHGRI-EBI GWAS Catalog and Open Targets Genetics to provide a complete picture of the genetic architecture of complex traits.\n\n### Key Capabilities\n\n1. **Study Comparison**: Compare all GWAS studies for a trait, assessing sample sizes, ancestries, and platforms\n2. **Meta-Analysis**: Aggregate effect sizes across studies and calculate heterogeneity statistics\n3. **Replication Assessment**: Identify replicated vs novel findings across discovery and replication cohorts\n4. **Quality Evaluation**: Assess statistical power, ancestry diversity, and data availability\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## Domain Reasoning: Comparing Studies for the Same Trait\n\nWhen comparing GWAS studies for the same trait, ask: do they replicate? The same lead SNPs appearing in independent studies is strong evidence of a true association. Different lead SNPs at the same locus may reflect LD differences between populations — they may tag the same causal variant. Different loci entirely may reflect different study designs, phenotype definitions, or population ancestry. Before concluding that a finding failed to replicate, check whether the SNP was even genotyped or imputed in the replication cohort.\n\nLOOK UP DON'T GUESS: effect sizes, p-values, allele frequencies, and LD structure for specific loci. Do not assume a SNP present in one study is present in another — use `gwas_get_associations_for_snp` to retrieve cross-study data. Do not infer LD blocks from genomic proximity; use credible sets from Open Targets for fine-mapping results.\n\n---\n\n## Use Cases\n\n### 1. Comprehensive Trait Analysis\n**Scenario**: \"I want to understand all available GWAS data for type 2 diabetes\"\n\n**Workflow**:\n- Search for all T2D studies in GWAS Catalog\n- Filter by sample size and ancestry\n- Extract top associations from each study\n- Identify consistently replicated loci\n- Assess ancestry-specific effects\n\n**Outcome**: Complete landscape of T2D genetics with replicated findings and population-specific signals\n\n### 2. Locus-Specific Meta-Analysis\n**Scenario**: \"Is the TCF7L2 association with T2D consistent across all studies?\"\n\n**Workflow**:\n- Retrieve all TCF7L2 (rs7903146) associations for T2D\n- Calculate combined effect size and p-value\n- Assess heterogeneity (I² statistic)\n- Generate forest plot data\n- Interpret heterogeneity level\n\n**Outcome**: Quantitative assessment of effect size consistency with heterogeneity interpretation\n\n### 3. Replication Analysis\n**Scenario**: \"Which findings from the discovery cohort replicated in the independent sample?\"\n\n**Workflow**:\n- Get top hits from discovery study\n- Check for presence and significance in replication study\n- Assess direction consistency\n- Calculate replication rate\n- Identify novel vs failed replication\n\n**Outcome**: Systematic replication report with success rates and failed findings\n\n### 4. Multi-Ancestry Comparison\n**Scenario**: \"Are T2D loci consistent across European and East Asian populations?\"\n\n**Workflow**:\n- Filter studies by ancestry\n- Compare top associations between populations\n- Identify shared vs population-specific loci\n- Assess allele frequency differences\n- Evaluate transferability of genetic risk scores\n\n**Outcome**: Ancestry-specific genetic architecture with transferability assessment\n\n---\n\n## Statistical Methods\n\n### Meta-Analysis Approach\n\nThis skill implements standard GWAS meta-analysis methods:\n\n**Fixed-Effects Model**:\n- Used when heterogeneity is low (I² \u003C 25%)\n- Weights studies by inverse variance\n- Assumes true effect size is the same across studies\n\n**Random-Effects Model** (recommended when I² > 50%):\n- Accounts for between-study variation\n- More conservative than fixed-effects\n- Better for diverse ancestries or methodologies\n\n**Heterogeneity Assessment**:\n\nThe **I² statistic** measures the percentage of variance due to between-study heterogeneity:\n\n```\nI² = [(Q - df) \u002F Q] × 100%\n\nwhere Q = Cochran's Q statistic\n      df = degrees of freedom (n_studies - 1)\n```\n\n**Interpretation Guidelines**:\n- **I² \u003C 25%**: Low heterogeneity → fixed-effects appropriate\n- **I² = 25-50%**: Moderate heterogeneity → investigate sources\n- **I² = 50-75%**: Substantial heterogeneity → random-effects preferred\n- **I² > 75%**: Considerable heterogeneity → meta-analysis may not be appropriate\n\n### Sources of Heterogeneity\n\nCommon reasons for high I²:\n\n1. **Ancestry differences**: Different allele frequencies and LD structure\n2. **Phenotype heterogeneity**: Trait definition varies across studies\n3. **Platform differences**: Imputation quality and coverage\n4. **Winner's curse**: Discovery studies overestimate effect sizes\n5. **Cohort characteristics**: Age, sex, environmental factors\n\n**Recommendations**:\n- Perform subgroup analysis by ancestry\n- Use meta-regression to investigate sources\n- Consider excluding outlier studies\n- Apply genomic control correction\n\n---\n\n## Study Quality Assessment\n\n### Quality Metrics\n\nThe skill evaluates studies based on:\n\n**1. Sample Size**:\n- Power to detect associations (80% power requires n > 10,000 for OR=1.2)\n- Precision of effect size estimates\n- Ability to detect modest effects\n\n**2. Ancestry Diversity**:\n- Single-ancestry vs multi-ancestry\n- Population stratification control\n- Transferability of findings\n\n**3. Data Availability**:\n- Summary statistics available for meta-analysis\n- Individual-level data vs summary-level\n- Imputation quality scores\n\n**4. Genotyping Quality**:\n- Platform density and coverage\n- Imputation reference panel\n- Quality control measures\n\n**5. Statistical Rigor**:\n- Genome-wide significance threshold (p \u003C 5×10⁻⁸)\n- Multiple testing correction\n- Replication in independent cohort\n\n### Quality Tiers\n\n**Tier 1 (High Quality)**:\n- n ≥ 50,000\n- Summary statistics available\n- Multi-ancestry or large single-ancestry\n- Imputed to high-quality reference\n- Independent replication\n\n**Tier 2 (Moderate Quality)**:\n- n ≥ 10,000\n- Standard GWAS platform\n- Adequate power for common variants\n- Some data availability\n\n**Tier 3 (Limited)**:\n- n \u003C 10,000\n- Limited power\n- May miss modest effects\n- Use with caution\n\n---\n\n## Best Practices\n\n### Before Meta-Analysis\n\n1. **Check phenotype consistency**: Ensure studies measure the same trait\n2. **Verify ancestry overlap**: High heterogeneity expected if ancestries differ\n3. **Harmonize alleles**: Align effect alleles across studies\n4. **Quality control**: Exclude low-quality studies or associations\n\n### Interpreting Results\n\n1. **Genome-wide significance**: p \u003C 5×10⁻⁸ (Bonferroni for ~1M independent tests)\n2. **Replication threshold**: p \u003C 0.05 in independent cohort\n3. **Direction consistency**: Effect should be same direction across studies\n4. **Heterogeneity**: I² > 50% suggests caution in interpretation\n\n### Common Pitfalls\n\n❌ **Don't**:\n- Meta-analyze without checking heterogeneity\n- Ignore ancestry differences\n- Over-interpret nominal p-values\n- Assume replication failure means false positive\n\n✅ **Do**:\n- Always report I² statistic\n- Perform sensitivity analyses\n- Consider ancestry-stratified analysis\n- Account for winner's curse in discovery studies\n\n---\n\n## Limitations & Caveats\n\n### Data Limitations\n\n1. **Incomplete Overlap**: Studies may analyze different SNPs\n2. **Cohort Overlap**: Some cohorts participate in multiple studies (inflates significance)\n3. **Publication Bias**: Significant findings more likely to be published\n4. **Winner's Curse**: Discovery studies overestimate effect sizes\n5. **Imputation Quality**: Varies across studies and populations\n\n### Statistical Limitations\n\n1. **Heterogeneity**: High I² may preclude meaningful meta-analysis\n2. **Sample Size Differences**: Large studies dominate fixed-effects models\n3. **Allele Frequency Differences**: Same variant has different effects across ancestries\n4. **Linkage Disequilibrium**: Fine-mapping needed to identify causal variants\n5. **Gene-Environment Interactions**: Not captured in standard meta-analysis\n\n### Interpretation Guidelines\n\n**When I² > 75%**:\n- Meta-analysis results should be interpreted with extreme caution\n- Investigate sources of heterogeneity systematically\n- Consider ancestry-specific or subgroup analyses\n- Descriptive comparison may be more appropriate than meta-analysis\n\n**When Studies Conflict**:\n- Check for methodological differences\n- Verify phenotype definitions match\n- Investigate population stratification\n- Consider conditional analysis\n\n---\n\n## Tools Used\n\n### GWAS Catalog API\n- `gwas_search_studies`: Find studies by trait\n- `gwas_get_study_by_id`: Get detailed study metadata\n- `gwas_get_associations_for_study`: Retrieve study associations\n- `gwas_get_associations_for_snp`: Get SNP associations across studies\n- `gwas_search_associations`: Search associations by trait\n\n### Open Targets Genetics GraphQL API\n- `OpenTargets_search_gwas_studies_by_disease`: Disease-based study search\n- `OpenTargets_get_gwas_study`: Detailed study information with LD populations\n- `OpenTargets_get_variant_credible_sets`: Fine-mapped loci for variant\n- `OpenTargets_get_study_credible_sets`: All credible sets for study\n- `OpenTargets_get_variant_info`: Variant annotation and allele frequencies\n\n## Glossary\n\n**Credible Set**: Set of variants likely to contain the causal variant (from fine-mapping)\n\n**L2G (Locus-to-Gene)**: Score predicting which gene is affected by a GWAS locus\n**License**: Open source (MIT)\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Flibrary\u002Fskills\u002Ftooluniverse-gwas-study-explorer","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-gwas-study-explorer",{"tool":50,"command":51},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-gwas-study-explorer",{"tool":53,"command":54},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-gwas-study-explorer","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-gwas-study-explorer\u002FSKILL.md",true,[58,64],{"path":59,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":62,"sourceHtmlUrl":63},"python_implementation.py","SCRIPT","脚本",20637,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-gwas-study-explorer\u002Fpython_implementation.py",{"path":65,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":66,"sourceHtmlUrl":67},"test_skill_comprehensive.py",18875,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-gwas-study-explorer\u002Ftest_skill_comprehensive.py",[69,90,120,147,161,177],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"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",[],[76,77,78,79,80,81,82,83,84,28,85,86,87,88,89],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","context","repo","injection","execution","file",{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":101,"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",[96],{"categoryNo":97,"categoryName":98,"taxonomyType":99,"taxonomyTypeDesc":100},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[102,103,104,105,106,107,108,109,25,110,111,112,113,114,28,115,116,117,118,119],"openmm md","how","decision","pick","linux","analyze","tool","stack","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":121,"name":122,"nameZh":6,"description":123,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":124,"categories":125,"keywords":132,"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",[126,129],{"categoryNo":127,"categoryName":128,"taxonomyType":99,"taxonomyTypeDesc":100},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":130,"categoryName":131,"taxonomyType":99,"taxonomyTypeDesc":100},"01JBSEEDCAT000000000000008","测试与质量",[133,134,135,136,137,138,139,140,141,142,103,143,144,145,146],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":148,"name":149,"nameZh":6,"description":150,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":151,"categories":152,"keywords":153,"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",[],[149,154,155,156,157,158,159,160],"setup","report","project","installation","project setup","issues","state",{"skillNo":162,"name":163,"nameZh":6,"description":164,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":165,"categories":166,"keywords":168,"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",[167],{"categoryNo":97,"categoryName":98,"taxonomyType":99,"taxonomyTypeDesc":100},[163,169,81,170,171,172,28,173,174,175,176],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":178,"name":154,"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":182,"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",[],[154,156,117,183,158,184],"files","interactive"]