[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75422RHKA6HCS0NHP0DEKPT":3,"skill-same:01M75422RHKA6HCS0NHP0DEKPT":54},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":32,"commitSha":33,"skillDirectory":34,"forksCount":35,"repositoryHtmlUrl":36,"repositoryHomepageUrl":37,"ownerHtmlUrl":38,"ownerBlogUrl":6,"ownerDescription":39,"updatedAt":40,"install":41,"resources":53},"01M75422RHKA6HCS0NHP0DEKPT","clinvar",null,"Build and inspect ClinVar exact-match evidence and candidate inventories.\nUse for clinical labels, VUS\u002Fconflict, carrier context, and drug-response rows.","exon-research\u002Fgenomi","exon-research","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F287072540?v=4","01M754130SK0JVWXNQKF8XANKV","Exon Research","01M754131W4AFK5CDRWT1KHP8X",492,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fexon-research\u002Fgenomi\u002Fblob\u002Fmaster\u002Fskills\u002Fclinvar\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: clinvar\ndescription: |\n  Build and inspect ClinVar exact-match evidence and candidate inventories.\n  Use for clinical labels, VUS\u002Fconflict, carrier context, and drug-response rows.\ntools:\n  - genomi.check_libraries\n  - clinvar.match_variants\n  - clinvar.scan_candidates\n  - variant.gather_allele_context\n  - variant.gather_gene_context\nmutating: true\n---\n\n# ClinVar Evidence\n\nUse this skill when the user asks about clinical labels, carrier findings,\npathogenic\u002Flikely pathogenic entries, VUS, conflicting classifications, drug\nresponse, risk-factor labels, or ClinVar-derived discovery.\n\n## Goal\n\nBuild a candidate landscape from exact ClinVar matches. Use\n`candidate_inventory` as variant-level provenance evidence and\n`candidate_review_groups` as the carrier\u002Fcondition review inventory.\n\n> **Convention:** See `skills\u002Fconventions\u002Fevidence-quality.md`.\n\n## Contract\n\n- ClinVar matches provide exact\u002Fstatic evidence for source-backed\n  interpretation.\n- Exact matching requires the optional build-specific library\n  `clinvar-grch38` or `clinvar-grch37`.\n- Candidate inventories are variant-level evidence, not interpretation.\n- Candidate review groups are review targets. A heterozygous P\u002FLP group can be\n  carrier-relevance evidence; it is not a carrier-status conclusion.\n- `clinvar.scan_candidates` returns an evidence view, grouped support,\n  warnings, and coverage; use those fields rather than inferring priority from\n  prose.\n- By default, `clinvar.scan_candidates` includes P\u002FLP, conflicting, VUS,\n  risk\u002Fassociation\u002Fprotective, drug-response, and benign ClinVar groups.\n- If ClinVar matches are missing, `clinvar.scan_candidates` materializes them\n  from the Active Genome Index before building the candidate inventory.\n- VUS, conflicts, and low-review assertions are downgraded unless reviewed\n  source evidence supports a stronger claim.\n- Drug-response rows use pharmacogenomic source context before actionability is\n  implied.\n\n## Cross-Capability Synthesis\n\nA scope-limited result from this capability is not a final user-facing answer\nwhen other Genomi capabilities can contribute orthogonal evidence to the same\nquestion. Returning \"cannot answer\" while applicable capabilities remain\nunexamined is a host-agent failure mode.\n\n## Tools\n\n### clinvar.match_variants\n\nMaterialize exact ClinVar matches for comparable Active Genome Index variants using the installed build-specific ClinVar library.\n\n**Use when**: After an Active Genome Index and the matching build-specific ClinVar library are available to materialize exact ClinVar\u002Fsample matches.\n\n**Why necessary**: ClinVar matching is library-scoped materialization; it turns installed public ClinVar rows into exact matches for an Active Genome Index without forcing every genome-artifact task to run ClinVar.\n\n### clinvar.scan_candidates\n\nBuild a deterministic candidate inventory and candidate review groups from exact ClinVar matches, materializing those matches from the Active Genome Index when needed.\n\n**Use when**: Broad Active Genome Index disease or risk triage when exact ClinVar candidate inventory is needed.\n\n**Why necessary**: Broad disease triage needs bounded ClinVar variant provenance plus review groups instead of ad hoc spot checks over a large genome file. It performs missing match materialization internally before candidate scanning.\n\n## Interpretation Rules\n\n- Pathogenic\u002Flikely pathogenic labels need zygosity, inheritance, population\n  frequency, gene-disease context, and source quality.\n- Carrier language belongs in `phenotype.plan_risk_investigation` with\n  `investigation_type:\"carrier_review\"` after reviewing the group gates.\n- VUS and conflicting labels use uncertainty\u002Fconflict wording.\n- Drug-response labels require pharmacogenomic guideline context before clinical\n  actionability is implied.\n- Common association\u002Frisk\u002Fprotective labels usually provide limited context for\n  personal common-disease risk.\n\n## Routing Checks\n\n- Prioritize ClinVar matches by actionability, review status, uncertainty,\n  population context, inheritance, and zygosity.\n- If a ClinVar operation returns `status=\"requires_library_install\"`, explain how\n  the named library helps this request and ask before installing it.\n- Treat ClinVar condition strings as database labels that need interpretation.\n- Keep the whole candidate inventory local; send selected public targets to\n  Journal source-review memory.\n","# ClinVar Evidence\n\nUse this skill when the user asks about clinical labels, carrier findings,\npathogenic\u002Flikely pathogenic entries, VUS, conflicting classifications, drug\nresponse, risk-factor labels, or ClinVar-derived discovery.\n\n## Goal\n\nBuild a candidate landscape from exact ClinVar matches. Use\n`candidate_inventory` as variant-level provenance evidence and\n`candidate_review_groups` as the carrier\u002Fcondition review inventory.\n\n> **Convention:** See `skills\u002Fconventions\u002Fevidence-quality.md`.\n\n## Contract\n\n- ClinVar matches provide exact\u002Fstatic evidence for source-backed\n  interpretation.\n- Exact matching requires the optional build-specific library\n  `clinvar-grch38` or `clinvar-grch37`.\n- Candidate inventories are variant-level evidence, not interpretation.\n- Candidate review groups are review targets. A heterozygous P\u002FLP group can be\n  carrier-relevance evidence; it is not a carrier-status conclusion.\n- `clinvar.scan_candidates` returns an evidence view, grouped support,\n  warnings, and coverage; use those fields rather than inferring priority from\n  prose.\n- By default, `clinvar.scan_candidates` includes P\u002FLP, conflicting, VUS,\n  risk\u002Fassociation\u002Fprotective, drug-response, and benign ClinVar groups.\n- If ClinVar matches are missing, `clinvar.scan_candidates` materializes them\n  from the Active Genome Index before building the candidate inventory.\n- VUS, conflicts, and low-review assertions are downgraded unless reviewed\n  source evidence supports a stronger claim.\n- Drug-response rows use pharmacogenomic source context before actionability is\n  implied.\n\n## Cross-Capability Synthesis\n\nA scope-limited result from this capability is not a final user-facing answer\nwhen other Genomi capabilities can contribute orthogonal evidence to the same\nquestion. Returning \"cannot answer\" while applicable capabilities remain\nunexamined is a host-agent failure mode.\n\n## Tools\n\n### clinvar.match_variants\n\nMaterialize exact ClinVar matches for comparable Active Genome Index variants using the installed build-specific ClinVar library.\n\n**Use when**: After an Active Genome Index and the matching build-specific ClinVar library are available to materialize exact ClinVar\u002Fsample matches.\n\n**Why necessary**: ClinVar matching is library-scoped materialization; it turns installed public ClinVar rows into exact matches for an Active Genome Index without forcing every genome-artifact task to run ClinVar.\n\n### clinvar.scan_candidates\n\nBuild a deterministic candidate inventory and candidate review groups from exact ClinVar matches, materializing those matches from the Active Genome Index when needed.\n\n**Use when**: Broad Active Genome Index disease or risk triage when exact ClinVar candidate inventory is needed.\n\n**Why necessary**: Broad disease triage needs bounded ClinVar variant provenance plus review groups instead of ad hoc spot checks over a large genome file. It performs missing match materialization internally before candidate scanning.\n\n## Interpretation Rules\n\n- Pathogenic\u002Flikely pathogenic labels need zygosity, inheritance, population\n  frequency, gene-disease context, and source quality.\n- Carrier language belongs in `phenotype.plan_risk_investigation` with\n  `investigation_type:\"carrier_review\"` after reviewing the group gates.\n- VUS and conflicting labels use uncertainty\u002Fconflict wording.\n- Drug-response labels require pharmacogenomic guideline context before clinical\n  actionability is implied.\n- Common association\u002Frisk\u002Fprotective labels usually provide limited context for\n  personal common-disease risk.\n\n## Routing Checks\n\n- Prioritize ClinVar matches by actionability, review status, uncertainty,\n  population context, inheritance, and zygosity.\n- If a ClinVar operation returns `status=\"requires_library_install\"`, explain how\n  the named library helps this request and ask before installing it.\n- Treat ClinVar condition strings as database labels that need interpretation.\n- Keep the whole candidate inventory local; send selected public targets to\n  Journal source-review memory.\n",{"name":5,"tools":24,"mutating":30,"description":31},[25,26,27,28,29],"genomi.check_libraries","clinvar.match_variants","clinvar.scan_candidates","variant.gather_allele_context","variant.gather_gene_context",true,"Build and inspect ClinVar exact-match evidence and candidate inventories.\nUse for clinical labels, VUS\u002Fconflict, carrier context, and drug-response rows.\n","master","1df4f5bfb635e2d08f93a1102b70b840fbe80d86","skills\u002Fclinvar",61,"https:\u002F\u002Fgithub.com\u002Fexon-research\u002Fgenomi","https:\u002F\u002Fwww.genomiagent.com\u002F","https:\u002F\u002Fgithub.com\u002Fexon-research","Building local-first AI co-scientist for genomic research","2026-09-01 03:30:56",{"source":8,"skillName":5,"commands":42,"prompt":52,"zipAvailable":30},[43,46,49],{"tool":44,"command":45},"npx","npx skills add exon-research\u002Fgenomi --skill clinvar",{"tool":47,"command":48},"bunx","bunx skills add exon-research\u002Fgenomi --skill clinvar",{"tool":50,"command":51},"pnpm","pnpm dlx skills add exon-research\u002Fgenomi --skill clinvar","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fexon-research\u002Fgenomi\u002Fblob\u002Fmaster\u002Fskills\u002Fclinvar\u002FSKILL.md",[],[55,62,69,76,83,90],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M75442YT3ZG6MG47E5MJ3HG2","variant-evidence","Answer specific rsID, allele, gene, region, genotype, and absence\u002Fcallability\nquestions using explicit session context or public evidence.","https:\u002F\u002Fgithub.com\u002Fexon-research\u002Fgenomi\u002Fblob\u002Fmaster\u002Fskills\u002Fvariant-evidence\u002FSKILL.md",[],[],{"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":19},"01M754400MW6S0MEN19S4CM9DE","journal-source-research","Journal sub-skill for focused public\u002Fsource evidence review and reviewed\nfinding write-back before interpretation or answer synthesis.","https:\u002F\u002Fgithub.com\u002Fexon-research\u002Fgenomi\u002Fblob\u002Fmaster\u002Fskills\u002Fsource-research\u002FSKILL.md",[],[],{"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":19},"01M7543X67TA0MBK3YGC0NJAX9","sequence","Deterministic sequence utilities for translation, ORFs, restriction sites,\nKozak context, primer checks, and local FASTA record matching.","https:\u002F\u002Fgithub.com\u002Fexon-research\u002Fgenomi\u002Fblob\u002Fmaster\u002Fskills\u002Fsequence\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M7543RHCHF4WJ69P0K0QTTFB","rare-disease-cancer","Plan rare disease, hereditary disease, cancer risk, carrier-relevance, and\nobserved-condition source investigation from public targets or selected\nactive genome evidence.","https:\u002F\u002Fgithub.com\u002Fexon-research\u002Fgenomi\u002Fblob\u002Fmaster\u002Fskills\u002Frare-disease-cancer\u002FSKILL.md",[],[],{"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":89,"publishedAt":19},"01M7543NDTVZB8T3RQBD0RK3MC","prs","Apply published polygenic scores from PGS Catalog to approved local personal DNA and return raw weighted score plus overlap QC.","https:\u002F\u002Fgithub.com\u002Fexon-research\u002Fgenomi\u002Fblob\u002Fmaster\u002Fskills\u002Fprs\u002FSKILL.md",[],[],{"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":96,"publishedAt":19},"01M7543FDFTWSYVVTEGHQSPHQK","pharmacogenomics","Answer drug-response, medication, PharmGKB-style, PGxDB, ATC, DrugBank,\ngene-drug, and variant-drug questions using public PGx evidence plus local\nsample genotype support when an Active Genome Index is selected.","https:\u002F\u002Fgithub.com\u002Fexon-research\u002Fgenomi\u002Fblob\u002Fmaster\u002Fskills\u002Fpharmacogenomics\u002FSKILL.md",[],[]]