[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DARC800ZRVB3T4HJYKFDQ8":3,"skill-same:01M6DARC800ZRVB3T4HJYKFDQ8":61},{"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":26,"linkOnly":27,"markdownContent":28,"markdownBody":29,"frontMatter":30,"refName":31,"commitSha":32,"skillDirectory":33,"forksCount":14,"repositoryHtmlUrl":34,"repositoryHomepageUrl":6,"ownerHtmlUrl":35,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":36,"install":37,"resources":50},"01M6DARC800ZRVB3T4HJYKFDQ8","tooluniverse-gwas-finemapping",null,"Identify and prioritize causal variants at GWAS loci using statistical fine-mapping and locus-to-gene predictions. Computes posterior probabilities for causal variants, links variants to genes via L2G predictions, annotates functional consequences, and suggests validation strategies. Use when asked to fine-map GWAS loci, prioritize causal variants, identify credible sets, or link GWAS signals to causal genes.","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-finemapping\u002FSKILL.md",[],[19,20,21,22,23,24,25],"tooluniverse gwas finemapping","validation","prioritize","use","map","signals","strategies","2026-11-10 10:12:30",false,"---\nname: tooluniverse-gwas-finemapping\ndescription: Identify and prioritize causal variants at GWAS loci using statistical fine-mapping and locus-to-gene predictions. Computes posterior probabilities for causal variants, links variants to genes via L2G predictions, annotates functional consequences, and suggests validation strategies. Use when asked to fine-map GWAS loci, prioritize causal variants, identify credible sets, or link GWAS signals to causal genes.\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# GWAS Fine-Mapping & Causal Variant Prioritization\n\nIdentify and prioritize causal variants at GWAS loci using statistical fine-mapping and locus-to-gene predictions.\n\n## Overview\n\nGenome-wide association studies (GWAS) identify genomic regions associated with traits, but linkage disequilibrium (LD) makes it difficult to pinpoint the causal variant. **Fine-mapping** uses Bayesian statistical methods to compute the posterior probability that each variant is causal, given the GWAS summary statistics.\n\n**REASONING STRATEGY — Start Here**:\nFine-mapping asks: which variant at this locus is CAUSAL? Work through this chain:\n1. **LD structure first** — variants in high LD (r² > 0.8) cannot be statistically distinguished from each other. Look up the LD block via Open Targets or the GWAS Catalog before assuming any single variant is the cause.\n2. **Functional annotation breaks LD ties** — if two variants have similar posterior probabilities but one is coding (missense, stop-gain) or sits in an active regulatory element (promoter, enhancer), that variant is biologically prioritized. Functional evidence is the tiebreaker.\n3. **eQTL colocalization is the key bridge** — a variant that is also a significant eQTL for a nearby gene in the relevant tissue (e.g., a pancreatic islet eQTL for a T2D locus) has a mechanistic story. Look up eQTL evidence via Open Targets L2G scores; don't assume the nearest gene is the effector gene.\n\nThis skill provides tools to:\n- **Prioritize causal variants** using fine-mapping posterior probabilities\n- **Link variants to genes** using locus-to-gene (L2G) predictions\n- **Annotate variants** with functional consequences\n- **Suggest validation strategies** based on fine-mapping results\n\n## Key Concepts\n\n### Credible Sets\nA **credible set** is a minimal set of variants that contains the causal variant with high confidence (typically 95% or 99%). Each variant in the set has a **posterior probability** of being causal, computed using methods like:\n- **SuSiE** (Sum of Single Effects)\n- **FINEMAP** (Bayesian fine-mapping)\n- **PAINTOR** (Probabilistic Annotation INtegraTOR)\n\n### Posterior Probability\nThe probability that a specific variant is causal, given the GWAS data and LD structure. Higher posterior probability = more likely to be causal.\n\n### Locus-to-Gene (L2G) Predictions\nL2G scores integrate multiple data types to predict which gene is affected by a variant:\n- Distance to gene (closer = higher score)\n- eQTL evidence (expression changes)\n- Chromatin interactions (Hi-C, promoter capture)\n- Functional annotations (coding variants, regulatory regions)\n\nL2G scores range from 0 to 1, with higher scores indicating stronger gene-variant links.\n\n## Fine-Mapping Reasoning Framework (CRITICAL)\n\n**LOOK UP DON'T GUESS** -- never assume a lead SNP is the causal variant. Always check LD structure, credible sets, and functional annotations via the tools below.\n\n### Step 1: Lead SNP vs Causal Variant\n\nThe lead SNP (most significant p-value) is often NOT the causal variant. It is simply the best-tagged variant on the genotyping array. The causal variant may be:\n- In perfect LD (r2 > 0.95) with the lead SNP but with a functional consequence\n- A non-coding regulatory variant not on the array\n- One of several independent signals at the locus (conditional analysis reveals multiple)\n\n**Action**: Always call `OpenTargets_get_variant_credible_sets` for the lead SNP. If the posterior probability is \u003C 0.5, the lead SNP is likely NOT causal -- examine other variants in the credible set.\n\n### Step 2: LD Structure Interpretation\n\nLD blocks define the resolution limit of fine-mapping:\n- **Tight LD block (few variants, r2 > 0.9)**: Credible set will be small; functional annotation is the tiebreaker\n- **Broad LD block (many variants)**: Credible set is large; statistical fine-mapping alone is insufficient -- need functional data (eQTL, chromatin, CRISPR)\n- **Population matters**: LD patterns differ between European, African, East Asian populations. African populations have shorter LD blocks and better fine-mapping resolution. Check which population the GWAS was conducted in.\n\n### Step 3: Credible Set Analysis\n\nWhen interpreting a credible set:\n1. **Size matters**: A 95% credible set with 1-3 variants = high resolution. With 50+ variants = low resolution, need more data.\n2. **Posterior probability distribution**: If one variant has PP > 0.5, it is the strong favorite. If PP is spread evenly across many variants, no single causal variant can be identified statistically.\n3. **Multiple credible sets at one locus**: Indicates multiple independent causal signals (allelic heterogeneity). Each set represents a different causal mechanism.\n\n### Step 4: Colocalization Reasoning\n\nColocalization asks: do two association signals (e.g., GWAS + eQTL) share the SAME causal variant?\n- **High L2G score (> 0.7) + eQTL in relevant tissue**: Strong evidence the variant affects disease THROUGH gene expression changes\n- **High GWAS signal but no eQTL**: Variant may act through protein-coding change, splicing, or a tissue\u002Fcell-type not yet profiled\n- **eQTL for distant gene (not nearest)**: The effector gene is NOT the nearest gene. **LOOK UP** the L2G score -- do not default to nearest gene\n\n### Step 5: Prioritization Tiebreakers\n\nWhen multiple variants have similar posterior probabilities:\n1. Coding variant (missense, stop-gain) > regulatory > intronic > intergenic\n2. In active chromatin mark (H3K27ac, H3K4me1) in disease-relevant tissue\n3. Disrupts transcription factor binding motif\n4. Conserved across species (PhyloP, GERP)\n5. eQTL in disease-relevant tissue with consistent direction of effect\n\n## Common Queries\n\n- \"Which variant at the TCF7L2 locus is likely causal for type 2 diabetes?\" → Use `OpenTargets_get_variant_credible_sets` or `gwas_search_snps` with gene=TCF7L2\n- \"Fine-map rs429358 (APOE4)\" → Use `OpenTargets_get_variant_info` then `OpenTargets_get_variant_credible_sets`\n- \"All causal loci from GWAS study GCST90029024\" → Use `OpenTargets_get_study_credible_sets`\n- \"GWAS studies for Alzheimer's disease\" → Use `OpenTargets_search_gwas_studies_by_disease` or `gwas_search_studies`\n\n## Tools Used\n\n### Open Targets Genetics (GraphQL)\n- `OpenTargets_get_variant_info`: Variant details and allele frequencies\n- `OpenTargets_get_variant_credible_sets`: Credible sets containing a variant\n- `OpenTargets_get_credible_set_detail`: Detailed credible set information\n- `OpenTargets_get_study_credible_sets`: All loci from a GWAS study\n- `OpenTargets_search_gwas_studies_by_disease`: Find studies by disease\n\n### GWAS Catalog (REST API)\n- `gwas_search_snps`: Find SNPs by gene or rsID\n- `gwas_get_snp_by_id`: Detailed SNP information\n- `gwas_get_associations_for_snp`: All trait associations for a variant\n- `gwas_search_studies`: Find studies by disease\u002Ftrait\n\n## Understanding Fine-Mapping Output\n\n### Interpreting Posterior Probabilities\n- **> 0.5**: Very likely causal (strong candidate)\n- **0.1 - 0.5**: Plausible causal variant\n- **0.01 - 0.1**: Possible but uncertain\n- **\u003C 0.01**: Unlikely to be causal\n\n### Interpreting L2G Scores\n- **> 0.7**: High confidence gene-variant link\n- **0.5 - 0.7**: Moderate confidence\n- **0.3 - 0.5**: Weak but possible link\n- **\u003C 0.3**: Low confidence\n\n## Common Questions\n\n**Q: Why don't all variants have credible sets?**\nA: Fine-mapping requires:\n1. GWAS summary statistics (not just top hits)\n2. LD reference panel\n3. Sufficient signal strength (p \u003C 5e-8)\n4. Computational resources\n\n**Q: Can a variant be in multiple credible sets?**\nA: Yes! A variant can be causal for multiple traits (pleiotropy) or appear in different studies for the same trait.\n\n**Q: What if the top L2G gene is far from the variant?**\nA: This suggests regulatory effects (enhancers, promoters). Check:\n- eQTL evidence in relevant tissues\n- Chromatin interaction data (Hi-C)\n- Regulatory element annotations (Roadmap, ENCODE)\n\n**Q: How do I choose between variants in a credible set?**\nA: Prioritize by:\n1. Posterior probability (higher = better)\n2. Functional consequence (coding > regulatory > intergenic)\n3. eQTL evidence\n4. Evolutionary conservation\n5. Experimental feasibility\n\n## Limitations\n\n1. **LD-dependent**: Fine-mapping accuracy depends on LD structure matching the study population\n2. **Requires summary stats**: Not all studies provide full summary statistics\n3. **Computational intensive**: Fine-mapping large studies takes significant resources\n4. **Prior assumptions**: Bayesian methods depend on priors (number of causal variants, effect sizes)\n5. **Missing data**: Not all GWAS loci have been fine-mapped in Open Targets\n\n## Best Practices\n\n1. **Start with study-level queries** when exploring a new disease\n2. **Check multiple studies** for replication of signals\n3. **Combine with functional data** (eQTLs, chromatin, CRISPR screens)\n4. **Consider ancestry** - LD differs across populations\n5. **Validate experimentally** - fine-mapping provides candidates, not proof\n\n## References\n\n1. Wang et al. (2020) \"A simple new approach to variable selection in regression, with application to genetic fine mapping.\" *JRSS-B* (SuSiE)\n2. Benner et al. (2016) \"FINEMAP: efficient variable selection using summary data from genome-wide association studies.\" *Bioinformatics*\n3. Ghoussaini et al. (2021) \"Open Targets Genetics: systematic identification of trait-associated genes using large-scale genetics and functional genomics.\" *NAR*\n4. Mountjoy et al. (2021) \"An open approach to systematically prioritize causal variants and genes at all published human GWAS trait-associated loci.\" *Nat Genet*\n\n## Related Skills\n\n- **tooluniverse-gwas-explorer**: Broader GWAS analysis\n- **tooluniverse-eqtl-colocalization**: Link variants to gene expression\n- **tooluniverse-gene-prioritization**: Systematic gene ranking\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# GWAS Fine-Mapping & Causal Variant Prioritization\n\nIdentify and prioritize causal variants at GWAS loci using statistical fine-mapping and locus-to-gene predictions.\n\n## Overview\n\nGenome-wide association studies (GWAS) identify genomic regions associated with traits, but linkage disequilibrium (LD) makes it difficult to pinpoint the causal variant. **Fine-mapping** uses Bayesian statistical methods to compute the posterior probability that each variant is causal, given the GWAS summary statistics.\n\n**REASONING STRATEGY — Start Here**:\nFine-mapping asks: which variant at this locus is CAUSAL? Work through this chain:\n1. **LD structure first** — variants in high LD (r² > 0.8) cannot be statistically distinguished from each other. Look up the LD block via Open Targets or the GWAS Catalog before assuming any single variant is the cause.\n2. **Functional annotation breaks LD ties** — if two variants have similar posterior probabilities but one is coding (missense, stop-gain) or sits in an active regulatory element (promoter, enhancer), that variant is biologically prioritized. Functional evidence is the tiebreaker.\n3. **eQTL colocalization is the key bridge** — a variant that is also a significant eQTL for a nearby gene in the relevant tissue (e.g., a pancreatic islet eQTL for a T2D locus) has a mechanistic story. Look up eQTL evidence via Open Targets L2G scores; don't assume the nearest gene is the effector gene.\n\nThis skill provides tools to:\n- **Prioritize causal variants** using fine-mapping posterior probabilities\n- **Link variants to genes** using locus-to-gene (L2G) predictions\n- **Annotate variants** with functional consequences\n- **Suggest validation strategies** based on fine-mapping results\n\n## Key Concepts\n\n### Credible Sets\nA **credible set** is a minimal set of variants that contains the causal variant with high confidence (typically 95% or 99%). Each variant in the set has a **posterior probability** of being causal, computed using methods like:\n- **SuSiE** (Sum of Single Effects)\n- **FINEMAP** (Bayesian fine-mapping)\n- **PAINTOR** (Probabilistic Annotation INtegraTOR)\n\n### Posterior Probability\nThe probability that a specific variant is causal, given the GWAS data and LD structure. Higher posterior probability = more likely to be causal.\n\n### Locus-to-Gene (L2G) Predictions\nL2G scores integrate multiple data types to predict which gene is affected by a variant:\n- Distance to gene (closer = higher score)\n- eQTL evidence (expression changes)\n- Chromatin interactions (Hi-C, promoter capture)\n- Functional annotations (coding variants, regulatory regions)\n\nL2G scores range from 0 to 1, with higher scores indicating stronger gene-variant links.\n\n## Fine-Mapping Reasoning Framework (CRITICAL)\n\n**LOOK UP DON'T GUESS** -- never assume a lead SNP is the causal variant. Always check LD structure, credible sets, and functional annotations via the tools below.\n\n### Step 1: Lead SNP vs Causal Variant\n\nThe lead SNP (most significant p-value) is often NOT the causal variant. It is simply the best-tagged variant on the genotyping array. The causal variant may be:\n- In perfect LD (r2 > 0.95) with the lead SNP but with a functional consequence\n- A non-coding regulatory variant not on the array\n- One of several independent signals at the locus (conditional analysis reveals multiple)\n\n**Action**: Always call `OpenTargets_get_variant_credible_sets` for the lead SNP. If the posterior probability is \u003C 0.5, the lead SNP is likely NOT causal -- examine other variants in the credible set.\n\n### Step 2: LD Structure Interpretation\n\nLD blocks define the resolution limit of fine-mapping:\n- **Tight LD block (few variants, r2 > 0.9)**: Credible set will be small; functional annotation is the tiebreaker\n- **Broad LD block (many variants)**: Credible set is large; statistical fine-mapping alone is insufficient -- need functional data (eQTL, chromatin, CRISPR)\n- **Population matters**: LD patterns differ between European, African, East Asian populations. African populations have shorter LD blocks and better fine-mapping resolution. Check which population the GWAS was conducted in.\n\n### Step 3: Credible Set Analysis\n\nWhen interpreting a credible set:\n1. **Size matters**: A 95% credible set with 1-3 variants = high resolution. With 50+ variants = low resolution, need more data.\n2. **Posterior probability distribution**: If one variant has PP > 0.5, it is the strong favorite. If PP is spread evenly across many variants, no single causal variant can be identified statistically.\n3. **Multiple credible sets at one locus**: Indicates multiple independent causal signals (allelic heterogeneity). Each set represents a different causal mechanism.\n\n### Step 4: Colocalization Reasoning\n\nColocalization asks: do two association signals (e.g., GWAS + eQTL) share the SAME causal variant?\n- **High L2G score (> 0.7) + eQTL in relevant tissue**: Strong evidence the variant affects disease THROUGH gene expression changes\n- **High GWAS signal but no eQTL**: Variant may act through protein-coding change, splicing, or a tissue\u002Fcell-type not yet profiled\n- **eQTL for distant gene (not nearest)**: The effector gene is NOT the nearest gene. **LOOK UP** the L2G score -- do not default to nearest gene\n\n### Step 5: Prioritization Tiebreakers\n\nWhen multiple variants have similar posterior probabilities:\n1. Coding variant (missense, stop-gain) > regulatory > intronic > intergenic\n2. In active chromatin mark (H3K27ac, H3K4me1) in disease-relevant tissue\n3. Disrupts transcription factor binding motif\n4. Conserved across species (PhyloP, GERP)\n5. eQTL in disease-relevant tissue with consistent direction of effect\n\n## Common Queries\n\n- \"Which variant at the TCF7L2 locus is likely causal for type 2 diabetes?\" → Use `OpenTargets_get_variant_credible_sets` or `gwas_search_snps` with gene=TCF7L2\n- \"Fine-map rs429358 (APOE4)\" → Use `OpenTargets_get_variant_info` then `OpenTargets_get_variant_credible_sets`\n- \"All causal loci from GWAS study GCST90029024\" → Use `OpenTargets_get_study_credible_sets`\n- \"GWAS studies for Alzheimer's disease\" → Use `OpenTargets_search_gwas_studies_by_disease` or `gwas_search_studies`\n\n## Tools Used\n\n### Open Targets Genetics (GraphQL)\n- `OpenTargets_get_variant_info`: Variant details and allele frequencies\n- `OpenTargets_get_variant_credible_sets`: Credible sets containing a variant\n- `OpenTargets_get_credible_set_detail`: Detailed credible set information\n- `OpenTargets_get_study_credible_sets`: All loci from a GWAS study\n- `OpenTargets_search_gwas_studies_by_disease`: Find studies by disease\n\n### GWAS Catalog (REST API)\n- `gwas_search_snps`: Find SNPs by gene or rsID\n- `gwas_get_snp_by_id`: Detailed SNP information\n- `gwas_get_associations_for_snp`: All trait associations for a variant\n- `gwas_search_studies`: Find studies by disease\u002Ftrait\n\n## Understanding Fine-Mapping Output\n\n### Interpreting Posterior Probabilities\n- **> 0.5**: Very likely causal (strong candidate)\n- **0.1 - 0.5**: Plausible causal variant\n- **0.01 - 0.1**: Possible but uncertain\n- **\u003C 0.01**: Unlikely to be causal\n\n### Interpreting L2G Scores\n- **> 0.7**: High confidence gene-variant link\n- **0.5 - 0.7**: Moderate confidence\n- **0.3 - 0.5**: Weak but possible link\n- **\u003C 0.3**: Low confidence\n\n## Common Questions\n\n**Q: Why don't all variants have credible sets?**\nA: Fine-mapping requires:\n1. GWAS summary statistics (not just top hits)\n2. LD reference panel\n3. Sufficient signal strength (p \u003C 5e-8)\n4. Computational resources\n\n**Q: Can a variant be in multiple credible sets?**\nA: Yes! A variant can be causal for multiple traits (pleiotropy) or appear in different studies for the same trait.\n\n**Q: What if the top L2G gene is far from the variant?**\nA: This suggests regulatory effects (enhancers, promoters). Check:\n- eQTL evidence in relevant tissues\n- Chromatin interaction data (Hi-C)\n- Regulatory element annotations (Roadmap, ENCODE)\n\n**Q: How do I choose between variants in a credible set?**\nA: Prioritize by:\n1. Posterior probability (higher = better)\n2. Functional consequence (coding > regulatory > intergenic)\n3. eQTL evidence\n4. Evolutionary conservation\n5. Experimental feasibility\n\n## Limitations\n\n1. **LD-dependent**: Fine-mapping accuracy depends on LD structure matching the study population\n2. **Requires summary stats**: Not all studies provide full summary statistics\n3. **Computational intensive**: Fine-mapping large studies takes significant resources\n4. **Prior assumptions**: Bayesian methods depend on priors (number of causal variants, effect sizes)\n5. **Missing data**: Not all GWAS loci have been fine-mapped in Open Targets\n\n## Best Practices\n\n1. **Start with study-level queries** when exploring a new disease\n2. **Check multiple studies** for replication of signals\n3. **Combine with functional data** (eQTLs, chromatin, CRISPR screens)\n4. **Consider ancestry** - LD differs across populations\n5. **Validate experimentally** - fine-mapping provides candidates, not proof\n\n## References\n\n1. Wang et al. (2020) \"A simple new approach to variable selection in regression, with application to genetic fine mapping.\" *JRSS-B* (SuSiE)\n2. Benner et al. (2016) \"FINEMAP: efficient variable selection using summary data from genome-wide association studies.\" *Bioinformatics*\n3. Ghoussaini et al. (2021) \"Open Targets Genetics: systematic identification of trait-associated genes using large-scale genetics and functional genomics.\" *NAR*\n4. Mountjoy et al. (2021) \"An open approach to systematically prioritize causal variants and genes at all published human GWAS trait-associated loci.\" *Nat Genet*\n\n## Related Skills\n\n- **tooluniverse-gwas-explorer**: Broader GWAS analysis\n- **tooluniverse-eqtl-colocalization**: Link variants to gene expression\n- **tooluniverse-gene-prioritization**: Systematic gene ranking\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Flibrary\u002Fskills\u002Ftooluniverse-gwas-finemapping","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-gwas-finemapping",{"tool":43,"command":44},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-gwas-finemapping",{"tool":46,"command":47},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-gwas-finemapping","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-gwas-finemapping\u002FSKILL.md",true,[51,57],{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},"python_implementation.py","SCRIPT","脚本",20023,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-gwas-finemapping\u002Fpython_implementation.py",{"path":58,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":59,"sourceHtmlUrl":60},"test_skill_comprehensive.py",16433,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-gwas-finemapping\u002Ftest_skill_comprehensive.py",[62,83,114,141,155,171],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":26},"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",[],[69,70,71,72,73,74,75,76,77,22,78,79,80,81,82],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","context","repo","injection","execution","file",{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":94,"publishedAt":26},"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",[89],{"categoryNo":90,"categoryName":91,"taxonomyType":92,"taxonomyTypeDesc":93},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[95,96,97,98,99,100,101,102,103,104,105,106,107,108,22,109,110,111,112,113],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"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":126,"publishedAt":26},"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",[120,123],{"categoryNo":121,"categoryName":122,"taxonomyType":92,"taxonomyTypeDesc":93},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":124,"categoryName":125,"taxonomyType":92,"taxonomyTypeDesc":93},"01JBSEEDCAT000000000000008","测试与质量",[127,128,129,130,131,132,133,134,135,136,96,137,138,139,140],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":142,"name":143,"nameZh":6,"description":144,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":145,"categories":146,"keywords":147,"publishedAt":26},"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",[],[143,148,149,150,151,152,153,154],"setup","report","project","installation","project setup","issues","state",{"skillNo":156,"name":157,"nameZh":6,"description":158,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":159,"categories":160,"keywords":162,"publishedAt":26},"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",[161],{"categoryNo":90,"categoryName":91,"taxonomyType":92,"taxonomyTypeDesc":93},[157,163,74,164,165,166,22,167,168,169,170],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":172,"name":148,"nameZh":6,"description":173,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":174,"categories":175,"keywords":176,"publishedAt":26},"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",[],[148,150,111,177,152,178],"files","interactive"]