[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DAY803MH6SB9Y40F9ASH61":3,"skill-same:01M6DAY803MH6SB9Y40F9ASH61":79},{"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":23,"publishedAt":36,"linkOnly":37,"markdownContent":38,"markdownBody":39,"frontMatter":40,"refName":41,"commitSha":42,"skillDirectory":43,"forksCount":14,"repositoryHtmlUrl":44,"repositoryHomepageUrl":6,"ownerHtmlUrl":45,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":46,"install":47,"resources":60},"01M6DAY803MH6SB9Y40F9ASH61","tooluniverse-structural-variant-analysis",null,"Comprehensive structural variant (SV) analysis skill for clinical genomics. Classifies SVs (deletions, duplications, inversions, translocations), assesses pathogenicity using ACMG-adapted criteria, evaluates gene disruption and dosage sensitivity, and provides clinical interpretation with evidence grading. Use when analyzing CNVs, large deletions\u002Fduplications, chromosomal rearrangements, or any structural variants requiring clinical interpretation.","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-structural-variant-analysis\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35],"analysis","variant analysis","structural","tooluniverse structural variant analysis","interpretation","analyzing","use","evidence","grading","sensitivity","genomics","clinical","2026-11-10 10:12:30",false,"---\nname: tooluniverse-structural-variant-analysis\ndescription: Comprehensive structural variant (SV) analysis skill for clinical genomics. Classifies SVs (deletions, duplications, inversions, translocations), assesses pathogenicity using ACMG-adapted criteria, evaluates gene disruption and dosage sensitivity, and provides clinical interpretation with evidence grading. Use when analyzing CNVs, large deletions\u002Fduplications, chromosomal rearrangements, or any structural variants requiring clinical interpretation.\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# Structural Variant Analysis Workflow\n\nSystematic analysis of structural variants (deletions, duplications, inversions, translocations, complex rearrangements) for clinical genomics interpretation using ACMG-adapted criteria.\n\n**LOOK UP DON'T GUESS** - Always retrieve ClinGen HI\u002FTS scores, gnomAD frequencies, and ClinVar evidence from tools. Do not infer dosage sensitivity from gene function alone.\n\n**KEY PRINCIPLES**:\n1. **Report-first approach** - Create SV_analysis_report.md FIRST, then populate progressively\n2. **ACMG-style classification** - Pathogenic\u002FLikely Pathogenic\u002FVUS\u002FLikely Benign\u002FBenign with explicit evidence\n3. **Evidence grading** - Grade all findings by confidence level (High\u002FModerate\u002FLimited)\n4. **Dosage sensitivity critical** - Gene dosage effects drive SV pathogenicity\n5. **Breakpoint precision matters** - Exact gene disruption vs dosage-only effects\n6. **Population context essential** - gnomAD SVs for frequency assessment\n7. **English-first queries** - Always use English terms in tool calls. Respond in the user's language\n\n---\n\n## Triggers\n\nUse this skill when users:\n- Ask about structural variant interpretation\n- Have CNV data from array or sequencing\n- Ask \"is this deletion\u002Fduplication pathogenic?\"\n- Need ACMG classification for SVs\n- Want to assess gene dosage effects\n- Ask about chromosomal rearrangements\n- Have large-scale genomic alterations requiring interpretation\n\n---\n\n## SV Pathogenicity Reasoning (Start Here)\n\nBefore any tool call, apply this reasoning to frame the analysis:\n\n**SV pathogenicity depends on what the SV disrupts. A deletion removing an entire gene is likely pathogenic if the gene is haploinsufficient. A duplication is pathogenic if the gene is dosage-sensitive. An inversion is pathogenic only if it disrupts a coding region or regulatory element at the breakpoint.**\n\nWork through these questions in order:\n\n**1. What type is the SV, and what disruption mechanism does it cause?**\n- **Deletion**: loss of one copy. Pathogenic if any contained gene is haploinsufficient (ClinGen HI score 3, pLI >= 0.9). A deletion of a dosage-insensitive gene in a gene-dense region may be benign even if large.\n- **Duplication**: gain of one copy. Pathogenic if any contained gene is dosage-sensitive (ClinGen TS score 3). Duplications can also disrupt gene regulation if tandem (disrupts reading frame at junction) or if they separate a gene from its enhancer.\n- **Inversion**: no copy number change. Pathogenic only at the breakpoints: if one breakpoint falls within an exon (truncation) or separates a gene from its regulatory element. Inversions entirely within gene-poor, regulatory-poor regions are often benign.\n- **Translocation**: pathogenic if a breakpoint disrupts a coding region or creates a pathogenic fusion gene. Balanced translocations in parents of affected children warrant special scrutiny.\n- **Complex rearrangements**: assess each segment and each breakpoint independently.\n\n**2. Is the disrupted gene dosage-sensitive?**\n- ClinGen HI score 3 = definitive haploinsufficiency (deletion of this gene is pathogenic)\n- ClinGen HI score 2 = likely haploinsufficient\n- pLI >= 0.9 = strong LoF intolerance (supporting haploinsufficiency)\n- ClinGen TS score 3 = definitive triplosensitivity (duplication is pathogenic)\n- If no ClinGen data: use OMIM inheritance (autosomal dominant = often dosage-sensitive) as weaker evidence\n\n**3. Does the population frequency contextualize the SV?**\n- >=1% frequency in gnomAD SV = BA1 (likely benign unless phenotype is extreme)\n- \u003C0.01% = supports pathogenicity (PM2)\n- Present in unaffected parents = weak evidence against pathogenicity, but not conclusive\n\n**4. Is there clinical precedent?**\n- Identical SV in ClinVar as Pathogenic\u002FLikely Pathogenic = strong evidence (PS1)\n- De novo occurrence = strong evidence for pathogenicity (PS2)\n- Phenotype match to known gene-disease association = supporting evidence (PP4)\n\nDocument this reasoning before computing the final score.\n\n---\n\n## Workflow Overview\n\n```\nPhase 1: SV IDENTITY & CLASSIFICATION\n  Normalize coordinates (hg19\u002Fhg38), determine type (DEL\u002FDUP\u002FINV\u002FTRA\u002FCPX),\n  calculate size, assess breakpoint precision\n\nPhase 2: GENE CONTENT ANALYSIS\n  Identify fully contained genes, partially disrupted genes (breakpoint within),\n  flanking genes (within 1 Mb), annotate function and disease associations\n\nPhase 3: DOSAGE SENSITIVITY ASSESSMENT\n  ClinGen HI\u002FTS scores, pLI scores, OMIM inheritance patterns,\n  gene-disease validity levels\n\nPhase 4: POPULATION FREQUENCY CONTEXT\n  gnomAD SV database, ClinVar known SVs, DECIPHER patient cases,\n  reciprocal overlap calculation (>=70% = same SV)\n\nPhase 5: PATHOGENICITY SCORING\n  Quantitative 0-10 scale: gene content (40%), dosage sensitivity (30%),\n  population frequency (20%), clinical evidence (10%)\n\nPhase 6: LITERATURE & CLINICAL EVIDENCE\n  PubMed searches, DECIPHER cohort analysis, functional evidence\n\nPhase 7: ACMG-ADAPTED CLASSIFICATION\n  Apply SV-specific evidence codes, calculate final classification,\n  generate clinical recommendations\n```\n\n---\n\n## Phase 1: SV Identity & Classification\n\n**Goal**: Standardize SV notation and classify type.\n\nCapture: chromosome(s), coordinates (start\u002Fend in hg19\u002Fhg38), SV size, SV type (DEL\u002FDUP\u002FINV\u002FTRA\u002FCPX), breakpoint precision, inheritance pattern (de novo\u002Finherited\u002Funknown).\n\nFor SV type definitions, scoring tables, and ACMG code details, see `CLASSIFICATION_GUIDE.md`.\n\n---\n\n## Phase 2: Gene Content Analysis\n\n**Goal**: Annotate all genes affected by the SV.\n\nTools:\n- `ensembl_lookup_gene` - gene structure, coordinates, exons\n- `NCBIGene_search` - official symbol, aliases, description\n- `Gene_Ontology_get_term_info` - biological process, molecular function\n- `OMIM_search`, `OMIM_get_entry` - disease associations, inheritance\n- `DisGeNET_search_gene` - gene-disease association scores\n\nClassify genes as: **fully contained** (entire gene in SV), **partially disrupted** (breakpoint within gene), or **flanking** (within 1 Mb of breakpoints).\n\nFor implementation pseudocode, see `ANALYSIS_PROCEDURES.md` Phase 2.\n\n---\n\n## Phase 3: Dosage Sensitivity Assessment\n\n**Goal**: Determine if affected genes are dosage-sensitive.\n\nTools:\n- `ClinGen_search_dosage_sensitivity` - HI\u002FTS scores (0-3, gold standard)\n- `ClinGen_search_gene_validity` - gene-disease validity level\n- `gnomad_search_variants` - pLI scores for LoF intolerance\n- `OMIM_get_entry` - inheritance pattern (AD suggests dosage sensitivity)\n\nInterpret scores using the reasoning above. ClinGen HI\u002FTS score 3 = definitive; score 2 = likely; score 1 = little evidence; score 0 = no evidence. Do not equate AD inheritance with haploinsufficiency without ClinGen support.\n\n---\n\n## Phase 4: Population Frequency Context\n\n**Goal**: Determine if SV is common (likely benign) or rare (supports pathogenicity).\n\nTools:\n- `gnomad_search_variants` - population SV frequencies\n- `ClinVar_search_variants` - known pathogenic\u002Fbenign SVs\n- `ClinGen_search_dosage_sensitivity` - patient SVs with phenotypes\n\nUse >=70% reciprocal overlap to define \"same\" SV for comparison. A frequency >=1% triggers BA1 unless there is very strong clinical evidence to override.\n\n---\n\n## Phase 5: Pathogenicity Scoring\n\n**Goal**: Quantitative pathogenicity assessment on 0-10 scale.\n\nFour components weighted: gene content (40%), dosage sensitivity (30%), population frequency (20%), clinical evidence (10%).\n\nScore mapping: 9-10 = Pathogenic, 7-8 = Likely Pathogenic, 4-6 = VUS, 2-3 = Likely Benign, 0-1 = Benign.\n\nFor detailed scoring breakdowns and implementation, see `CLASSIFICATION_GUIDE.md` and `ANALYSIS_PROCEDURES.md` Phase 5.\n\n---\n\n## Phase 6: Literature & Clinical Evidence\n\n**Goal**: Find case reports, functional studies, and clinical validation.\n\nTools:\n- `PubMed_search_articles` - peer-reviewed literature\n- `EuropePMC_search_articles` - additional coverage\n- `ClinGen_search_dosage_sensitivity` - patient case database\n\nSearch strategies: gene-specific dosage sensitivity papers, SV-specific case reports, phenotype-gene associations. See `ANALYSIS_PROCEDURES.md` Phase 6.\n\n---\n\n## Phase 7: ACMG-Adapted Classification\n\n**Goal**: Apply ACMG\u002FClinGen criteria adapted for SVs and generate a final classification with explicit evidence summary.\n\nThe LLM knows the ACMG criteria codes and combination rules. Apply them to the evidence gathered in Phases 1-6. Key points to verify with tool data:\n- PVS1 applies to deletions of genes with ClinGen HI score >= 2 or pLI >= 0.9\n- PS2 requires confirmed de novo status (check parental genotypes if available)\n- PM2 requires absence from population databases at >=70% reciprocal overlap\n\nFor complete evidence code tables and classification algorithm, see `CLASSIFICATION_GUIDE.md`.\n\n---\n\n## Output\n\nCreate report using the template in `REPORT_TEMPLATE.md`. Name files as:\n```\nSV_analysis_[TYPE]_chr[CHR]_[START]_[END]_[GENES].md\n```\n\n---\n\n## Required Tools Reference\n\n- `ClinGen_search_dosage_sensitivity` - HI\u002FTS scores (required for all deletions\u002Fduplications)\n- `ClinGen_search_gene_validity` - gene-disease validity (required)\n- `ClinVar_search_variants` - known pathogenic\u002Fbenign SVs (required)\n- `ensembl_lookup_gene` - gene coordinates, structure (required)\n- `OMIM_search`, `OMIM_get_entry` - gene-disease associations (required)\n- `gnomad_search_variants` - population frequency and pLI (required)\n- `DisGeNET_search_gene` - additional disease associations (recommended)\n- `PubMed_search_articles` - literature evidence (recommended)\n- `Gene_Ontology_get_term_info` - gene function (supporting)\n\n---\n\n## When NOT to Use This Skill\n\n- **Single nucleotide variants (SNVs)** - Use `tooluniverse-variant-interpretation`\n- **Small indels (\u003C50 bp)** - Use variant interpretation skill\n- **Somatic variants in cancer** - Different framework needed\n- **Mitochondrial variants** - Specialized interpretation required\n- **Repeat expansions** - Different mechanism\n\nUse this skill for **structural variants >=50 bp** requiring dosage sensitivity assessment and ACMG-adapted classification.\n\n---\n\n## Reference Files\n\n- `EXAMPLES.md` - Sample SV interpretations with worked examples\n- `CLASSIFICATION_GUIDE.md` - ACMG criteria, scoring system, evidence codes, special scenarios, clinical recommendations\n- `REPORT_TEMPLATE.md` - Full report template with section structure and file naming\n- `ANALYSIS_PROCEDURES.md` - Detailed implementation pseudocode for each phase\n\n## External References\n\n- ClinGen Dosage Sensitivity Map: https:\u002F\u002Fwww.ncbi.nlm.nih.gov\u002Fprojects\u002Fdbvar\u002Fclingen\u002F\n- ACMG SV Guidelines: Riggs et al., Genet Med 2020 (PMID: 31690835)\n- `tooluniverse-variant-interpretation` - For SNVs and small indels\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# Structural Variant Analysis Workflow\n\nSystematic analysis of structural variants (deletions, duplications, inversions, translocations, complex rearrangements) for clinical genomics interpretation using ACMG-adapted criteria.\n\n**LOOK UP DON'T GUESS** - Always retrieve ClinGen HI\u002FTS scores, gnomAD frequencies, and ClinVar evidence from tools. Do not infer dosage sensitivity from gene function alone.\n\n**KEY PRINCIPLES**:\n1. **Report-first approach** - Create SV_analysis_report.md FIRST, then populate progressively\n2. **ACMG-style classification** - Pathogenic\u002FLikely Pathogenic\u002FVUS\u002FLikely Benign\u002FBenign with explicit evidence\n3. **Evidence grading** - Grade all findings by confidence level (High\u002FModerate\u002FLimited)\n4. **Dosage sensitivity critical** - Gene dosage effects drive SV pathogenicity\n5. **Breakpoint precision matters** - Exact gene disruption vs dosage-only effects\n6. **Population context essential** - gnomAD SVs for frequency assessment\n7. **English-first queries** - Always use English terms in tool calls. Respond in the user's language\n\n---\n\n## Triggers\n\nUse this skill when users:\n- Ask about structural variant interpretation\n- Have CNV data from array or sequencing\n- Ask \"is this deletion\u002Fduplication pathogenic?\"\n- Need ACMG classification for SVs\n- Want to assess gene dosage effects\n- Ask about chromosomal rearrangements\n- Have large-scale genomic alterations requiring interpretation\n\n---\n\n## SV Pathogenicity Reasoning (Start Here)\n\nBefore any tool call, apply this reasoning to frame the analysis:\n\n**SV pathogenicity depends on what the SV disrupts. A deletion removing an entire gene is likely pathogenic if the gene is haploinsufficient. A duplication is pathogenic if the gene is dosage-sensitive. An inversion is pathogenic only if it disrupts a coding region or regulatory element at the breakpoint.**\n\nWork through these questions in order:\n\n**1. What type is the SV, and what disruption mechanism does it cause?**\n- **Deletion**: loss of one copy. Pathogenic if any contained gene is haploinsufficient (ClinGen HI score 3, pLI >= 0.9). A deletion of a dosage-insensitive gene in a gene-dense region may be benign even if large.\n- **Duplication**: gain of one copy. Pathogenic if any contained gene is dosage-sensitive (ClinGen TS score 3). Duplications can also disrupt gene regulation if tandem (disrupts reading frame at junction) or if they separate a gene from its enhancer.\n- **Inversion**: no copy number change. Pathogenic only at the breakpoints: if one breakpoint falls within an exon (truncation) or separates a gene from its regulatory element. Inversions entirely within gene-poor, regulatory-poor regions are often benign.\n- **Translocation**: pathogenic if a breakpoint disrupts a coding region or creates a pathogenic fusion gene. Balanced translocations in parents of affected children warrant special scrutiny.\n- **Complex rearrangements**: assess each segment and each breakpoint independently.\n\n**2. Is the disrupted gene dosage-sensitive?**\n- ClinGen HI score 3 = definitive haploinsufficiency (deletion of this gene is pathogenic)\n- ClinGen HI score 2 = likely haploinsufficient\n- pLI >= 0.9 = strong LoF intolerance (supporting haploinsufficiency)\n- ClinGen TS score 3 = definitive triplosensitivity (duplication is pathogenic)\n- If no ClinGen data: use OMIM inheritance (autosomal dominant = often dosage-sensitive) as weaker evidence\n\n**3. Does the population frequency contextualize the SV?**\n- >=1% frequency in gnomAD SV = BA1 (likely benign unless phenotype is extreme)\n- \u003C0.01% = supports pathogenicity (PM2)\n- Present in unaffected parents = weak evidence against pathogenicity, but not conclusive\n\n**4. Is there clinical precedent?**\n- Identical SV in ClinVar as Pathogenic\u002FLikely Pathogenic = strong evidence (PS1)\n- De novo occurrence = strong evidence for pathogenicity (PS2)\n- Phenotype match to known gene-disease association = supporting evidence (PP4)\n\nDocument this reasoning before computing the final score.\n\n---\n\n## Workflow Overview\n\n```\nPhase 1: SV IDENTITY & CLASSIFICATION\n  Normalize coordinates (hg19\u002Fhg38), determine type (DEL\u002FDUP\u002FINV\u002FTRA\u002FCPX),\n  calculate size, assess breakpoint precision\n\nPhase 2: GENE CONTENT ANALYSIS\n  Identify fully contained genes, partially disrupted genes (breakpoint within),\n  flanking genes (within 1 Mb), annotate function and disease associations\n\nPhase 3: DOSAGE SENSITIVITY ASSESSMENT\n  ClinGen HI\u002FTS scores, pLI scores, OMIM inheritance patterns,\n  gene-disease validity levels\n\nPhase 4: POPULATION FREQUENCY CONTEXT\n  gnomAD SV database, ClinVar known SVs, DECIPHER patient cases,\n  reciprocal overlap calculation (>=70% = same SV)\n\nPhase 5: PATHOGENICITY SCORING\n  Quantitative 0-10 scale: gene content (40%), dosage sensitivity (30%),\n  population frequency (20%), clinical evidence (10%)\n\nPhase 6: LITERATURE & CLINICAL EVIDENCE\n  PubMed searches, DECIPHER cohort analysis, functional evidence\n\nPhase 7: ACMG-ADAPTED CLASSIFICATION\n  Apply SV-specific evidence codes, calculate final classification,\n  generate clinical recommendations\n```\n\n---\n\n## Phase 1: SV Identity & Classification\n\n**Goal**: Standardize SV notation and classify type.\n\nCapture: chromosome(s), coordinates (start\u002Fend in hg19\u002Fhg38), SV size, SV type (DEL\u002FDUP\u002FINV\u002FTRA\u002FCPX), breakpoint precision, inheritance pattern (de novo\u002Finherited\u002Funknown).\n\nFor SV type definitions, scoring tables, and ACMG code details, see `CLASSIFICATION_GUIDE.md`.\n\n---\n\n## Phase 2: Gene Content Analysis\n\n**Goal**: Annotate all genes affected by the SV.\n\nTools:\n- `ensembl_lookup_gene` - gene structure, coordinates, exons\n- `NCBIGene_search` - official symbol, aliases, description\n- `Gene_Ontology_get_term_info` - biological process, molecular function\n- `OMIM_search`, `OMIM_get_entry` - disease associations, inheritance\n- `DisGeNET_search_gene` - gene-disease association scores\n\nClassify genes as: **fully contained** (entire gene in SV), **partially disrupted** (breakpoint within gene), or **flanking** (within 1 Mb of breakpoints).\n\nFor implementation pseudocode, see `ANALYSIS_PROCEDURES.md` Phase 2.\n\n---\n\n## Phase 3: Dosage Sensitivity Assessment\n\n**Goal**: Determine if affected genes are dosage-sensitive.\n\nTools:\n- `ClinGen_search_dosage_sensitivity` - HI\u002FTS scores (0-3, gold standard)\n- `ClinGen_search_gene_validity` - gene-disease validity level\n- `gnomad_search_variants` - pLI scores for LoF intolerance\n- `OMIM_get_entry` - inheritance pattern (AD suggests dosage sensitivity)\n\nInterpret scores using the reasoning above. ClinGen HI\u002FTS score 3 = definitive; score 2 = likely; score 1 = little evidence; score 0 = no evidence. Do not equate AD inheritance with haploinsufficiency without ClinGen support.\n\n---\n\n## Phase 4: Population Frequency Context\n\n**Goal**: Determine if SV is common (likely benign) or rare (supports pathogenicity).\n\nTools:\n- `gnomad_search_variants` - population SV frequencies\n- `ClinVar_search_variants` - known pathogenic\u002Fbenign SVs\n- `ClinGen_search_dosage_sensitivity` - patient SVs with phenotypes\n\nUse >=70% reciprocal overlap to define \"same\" SV for comparison. A frequency >=1% triggers BA1 unless there is very strong clinical evidence to override.\n\n---\n\n## Phase 5: Pathogenicity Scoring\n\n**Goal**: Quantitative pathogenicity assessment on 0-10 scale.\n\nFour components weighted: gene content (40%), dosage sensitivity (30%), population frequency (20%), clinical evidence (10%).\n\nScore mapping: 9-10 = Pathogenic, 7-8 = Likely Pathogenic, 4-6 = VUS, 2-3 = Likely Benign, 0-1 = Benign.\n\nFor detailed scoring breakdowns and implementation, see `CLASSIFICATION_GUIDE.md` and `ANALYSIS_PROCEDURES.md` Phase 5.\n\n---\n\n## Phase 6: Literature & Clinical Evidence\n\n**Goal**: Find case reports, functional studies, and clinical validation.\n\nTools:\n- `PubMed_search_articles` - peer-reviewed literature\n- `EuropePMC_search_articles` - additional coverage\n- `ClinGen_search_dosage_sensitivity` - patient case database\n\nSearch strategies: gene-specific dosage sensitivity papers, SV-specific case reports, phenotype-gene associations. See `ANALYSIS_PROCEDURES.md` Phase 6.\n\n---\n\n## Phase 7: ACMG-Adapted Classification\n\n**Goal**: Apply ACMG\u002FClinGen criteria adapted for SVs and generate a final classification with explicit evidence summary.\n\nThe LLM knows the ACMG criteria codes and combination rules. Apply them to the evidence gathered in Phases 1-6. Key points to verify with tool data:\n- PVS1 applies to deletions of genes with ClinGen HI score >= 2 or pLI >= 0.9\n- PS2 requires confirmed de novo status (check parental genotypes if available)\n- PM2 requires absence from population databases at >=70% reciprocal overlap\n\nFor complete evidence code tables and classification algorithm, see `CLASSIFICATION_GUIDE.md`.\n\n---\n\n## Output\n\nCreate report using the template in `REPORT_TEMPLATE.md`. Name files as:\n```\nSV_analysis_[TYPE]_chr[CHR]_[START]_[END]_[GENES].md\n```\n\n---\n\n## Required Tools Reference\n\n- `ClinGen_search_dosage_sensitivity` - HI\u002FTS scores (required for all deletions\u002Fduplications)\n- `ClinGen_search_gene_validity` - gene-disease validity (required)\n- `ClinVar_search_variants` - known pathogenic\u002Fbenign SVs (required)\n- `ensembl_lookup_gene` - gene coordinates, structure (required)\n- `OMIM_search`, `OMIM_get_entry` - gene-disease associations (required)\n- `gnomad_search_variants` - population frequency and pLI (required)\n- `DisGeNET_search_gene` - additional disease associations (recommended)\n- `PubMed_search_articles` - literature evidence (recommended)\n- `Gene_Ontology_get_term_info` - gene function (supporting)\n\n---\n\n## When NOT to Use This Skill\n\n- **Single nucleotide variants (SNVs)** - Use `tooluniverse-variant-interpretation`\n- **Small indels (\u003C50 bp)** - Use variant interpretation skill\n- **Somatic variants in cancer** - Different framework needed\n- **Mitochondrial variants** - Specialized interpretation required\n- **Repeat expansions** - Different mechanism\n\nUse this skill for **structural variants >=50 bp** requiring dosage sensitivity assessment and ACMG-adapted classification.\n\n---\n\n## Reference Files\n\n- `EXAMPLES.md` - Sample SV interpretations with worked examples\n- `CLASSIFICATION_GUIDE.md` - ACMG criteria, scoring system, evidence codes, special scenarios, clinical recommendations\n- `REPORT_TEMPLATE.md` - Full report template with section structure and file naming\n- `ANALYSIS_PROCEDURES.md` - Detailed implementation pseudocode for each phase\n\n## External References\n\n- ClinGen Dosage Sensitivity Map: https:\u002F\u002Fwww.ncbi.nlm.nih.gov\u002Fprojects\u002Fdbvar\u002Fclingen\u002F\n- ACMG SV Guidelines: Riggs et al., Genet Med 2020 (PMID: 31690835)\n- `tooluniverse-variant-interpretation` - For SNVs and small indels\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Flibrary\u002Fskills\u002Ftooluniverse-structural-variant-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":48,"prompt":58,"zipAvailable":59},[49,52,55],{"tool":50,"command":51},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-structural-variant-analysis",{"tool":53,"command":54},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-structural-variant-analysis",{"tool":56,"command":57},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-structural-variant-analysis","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-structural-variant-analysis\u002FSKILL.md",true,[61,67,71,75],{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"ANALYSIS_PROCEDURES.md","REFERENCE","参考文档",11026,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-structural-variant-analysis\u002FANALYSIS_PROCEDURES.md",{"path":68,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":69,"sourceHtmlUrl":70},"CLASSIFICATION_GUIDE.md",8818,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-structural-variant-analysis\u002FCLASSIFICATION_GUIDE.md",{"path":72,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":73,"sourceHtmlUrl":74},"EXAMPLES.md",45028,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-structural-variant-analysis\u002FEXAMPLES.md",{"path":76,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":77,"sourceHtmlUrl":78},"REPORT_TEMPLATE.md",4912,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-structural-variant-analysis\u002FREPORT_TEMPLATE.md",[80,101,128,155,169,185],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":36},"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",[],[87,88,89,90,91,92,93,94,95,30,96,97,98,99,100],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","context","repo","injection","execution","file",{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":108,"publishedAt":36},"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",[107],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[109,110,111,112,113,114,115,116,117,118,119,120,121,122,30,123,124,125,126,127],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":129,"name":130,"nameZh":6,"description":131,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":132,"categories":133,"keywords":140,"publishedAt":36},"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",[134,137],{"categoryNo":135,"categoryName":136,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":138,"categoryName":139,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[141,142,143,144,145,146,147,148,149,150,110,151,152,153,154],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"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":161,"publishedAt":36},"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",[],[157,162,163,164,165,166,167,168],"setup","report","project","installation","project setup","issues","state",{"skillNo":170,"name":171,"nameZh":6,"description":172,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":173,"categories":174,"keywords":176,"publishedAt":36},"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",[175],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[171,177,92,178,179,180,30,181,182,183,184],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":186,"name":162,"nameZh":6,"description":187,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":188,"categories":189,"keywords":190,"publishedAt":36},"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",[],[162,164,125,191,166,192],"files","interactive"]