[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7541ZCT8Q3KWEWNJM8Z5FZP":3,"skill-same:01M7541ZCT8Q3KWEWNJM8Z5FZP":58},{"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":36,"commitSha":37,"skillDirectory":38,"forksCount":39,"repositoryHtmlUrl":40,"repositoryHomepageUrl":41,"ownerHtmlUrl":42,"ownerBlogUrl":6,"ownerDescription":43,"updatedAt":44,"install":45,"resources":57},"01M7541ZCT8Q3KWEWNJM8Z5FZP","ancestry",null,"Use local ancestry reference-panel tools for 1000 Genomes GRCh37\u002FGRCh38 PCA\nprojection, marker overlap QC, and qualitative reference-neighbor context.","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\u002Fancestry\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: ancestry\ndescription: |\n  Use local ancestry reference-panel tools for 1000 Genomes GRCh37\u002FGRCh38 PCA\n  projection, marker overlap QC, and qualitative reference-neighbor context.\ntools:\n  - genomi.check_libraries\n  - genomi.describe_context\n  - ancestry.list_reference_panels\n  - ancestry.build_source_context\n  - ancestry.check_sample_overlap\n  - ancestry.project_pca\n  - ancestry.estimate_population_context\n  - active_genome_index.approve_access\n  - genomi.parse_source\nmutating: true\n---\n\n# Ancestry Reference-Panel Context\n\nUse this skill when the user asks about ancestry, population context, PCA\nprojection, reference-panel similarity, or which public reference samples their\ngenome is closest to.\n\n## Contract\n\n- This capability is a local reference-panel workflow, not an ethnicity or race\n  predictor.\n- Private tools require current-session Active Genome Index access approval or a genome source\n  path supplied in the current chat.\n- Public metadata tools do not read an Active Genome Index.\n- Private genotype data stays local. Do not upload sample genotypes to external\n  APIs or URLs.\n- The MVP supports GRCh38 and GRCh37. If `genome_build` is omitted, the tool\n  default is GRCh38 unless an approved Active Genome Index provides another\n  build; the returned `defaults_applied` records that default.\n- Labels are 1000 Genomes reference-panel labels, not ethnicity, nationality,\n  race, tribe, caste, religion, or personal identity.\n- Output is qualitative reference-panel similarity in PCA space. Do not produce\n  component percentages, admixture proportions, haplogroups, local ancestry,\n  ancestry dates, or relative matching.\n\n> **Convention:** See `skills\u002Fconventions\u002Fcontext-routing.md`.\n> **Convention:** See `skills\u002Fconventions\u002Fevidence-quality.md`.\n> **Convention:** See `skills\u002F_output-rules.md`.\n\n## First Actions\n\n1. Use `ancestry.list_reference_panels` to check whether the matching-build\n   1000 Genomes 30x panel is installed and to inspect source URLs and label\n   definitions.\n2. Use `ancestry.build_source_context` when the user asks what the panel means\n   or when you need explicit label and method boundaries before answering.\n3. For sample-specific questions, use `genomi.describe_context` only\n   when the chat asks about current Active Genome Index context or already mentioned a\n   genome source. If the user supplied a genome source path, that is approval to read\n   it for this session.\n4. Use `ancestry.estimate_population_context` as the default sample-specific\n   entry point. It runs overlap QC and PCA projection when enough markers are\n   usable.\n5. Use `ancestry.check_sample_overlap` when you only need QC readiness, and\n   `ancestry.project_pca` when the host agent needs raw PCA coordinates and\n   nearest reference-neighbor distances.\n\n## Library Handling\n\nThe required optional library is build-specific:\n`ancestry-1000g-30x-grch38` for GRCh38 samples and\n`ancestry-1000g-30x-grch37` for GRCh37 samples. If a private ancestry tool\nreturns `requires_library_install`, explain that the compact local panel is\nneeded for marker overlap and PCA projection, then ask before installing with\nthe returned `ask_user.install_command` or `missing_library.install_command`.\nFor example:\n\n```bash\ngenomi install --libraries ancestry-1000g-30x-grch38\ngenomi install --libraries ancestry-1000g-30x-grch38,liftover-chains,ancestry-1000g-30x-grch37\n```\n\nDo not treat a missing panel as evidence about the sample.\n\n## Interpretation Rules\n\n- Report marker overlap, projection readiness, marker-overlap quality, nearest reference\n  group labels, and the method boundary.\n- Marker-overlap quality is graded by the fraction of the loaded panel covered\n  by usable sample dosages. There is no absolute marker-count floor.\n- If less than 20% of the loaded panel is usable, do not project.\n- If 20%-49% of the loaded panel is usable, projection is allowed with low\n  marker-overlap quality and reference-neighbor context only.\n- If 50%-79% of the loaded panel is usable, projection is allowed with moderate\n  marker-overlap quality.\n- If at least 80% of the loaded panel is usable, projection is allowed with\n  high marker-overlap quality.\n- Use wording like: \"The sample projects closest to the EUR reference cluster\n  in this panel.\"\n- Do not say \"predict ethnicity\", \"determine origin\", or imply personal\n  identity from a reference-panel label.\n\n## User-Facing Answer Shape\n\nIf an Active Genome Index was projected, give the qualitative reference-panel\nsimilarity, marker-overlap quality, and limitations. If the tool only returned public\nmetadata, answer directly without an Active Genome Index status disclaimer.\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### ancestry.build_source_context\n\nExplain 1000 Genomes ancestry panel provenance, label meanings, sampling limits, and method boundaries.\n\n**Use when**: The user asks what the ancestry panel means, where labels come from, or why output is reference similarity rather than identity.\n\n**Why necessary**: Ancestry language is easy to overstate; source context gives agents explicit label and method boundaries before answering.\n\n**Not for**: Reading or projecting a user's genome; use ancestry.estimate_population_context after approval.\n\n**Example prompts**: Explain the source and limitations of the ancestry panel.\n\n**Result semantics**: Public metadata only; no Active Genome Index is read.\n\n### ancestry.check_sample_overlap\n\nCheck how many installed 1000 Genomes ancestry panel markers are usable in an approved Active Genome Index.\n\n**Use when**: The agent needs to know if a selected sample has enough overlap with the installed ancestry reference panel before projection.\n\n**Why necessary**: Projection is not interpretable below the overlap thresholds; this tool separates QC from interpretation.\n\n**Not for**: Public panel metadata; use ancestry.list_reference_panels. Ethnicity or origin prediction; ancestry tools provide reference-panel similarity only.\n\n**Example prompts**: Does my Active Genome Index have enough overlap with the ancestry panel?\n\n**Result semantics**: Reports usable marker count and projection readiness. It must not be interpreted as ethnicity, nationality, race, tribe, caste, religion, or identity.\n\n### ancestry.estimate_population_context\n\nEstimate qualitative reference-panel similarity for an approved GRCh37 or GRCh38 sample using local 1000 Genomes PCA projection.\n\n**Use when**: The user asks for ancestry or population context from their genome and has approved Active Genome Index use in this session.\n\n**Why necessary**: Provides a bounded default entry that combines overlap QC and PCA projection while preserving reference-similarity language.\n\n**Not for**: Ethnicity prediction, determining origin, component percentages, haplogroups, local ancestry, or relative matching.\n\n**Example prompts**: What 1000 Genomes reference cluster is my Active Genome Index closest to?\n\n**Result semantics**: The interpretation is qualitative reference-panel similarity only and must never be phrased as ethnicity, nationality, race, tribe, caste, religion, or personal identity.\n\n### ancestry.list_reference_panels\n\nList local ancestry reference panels, installation state, public source URLs, label definitions, and method boundaries.\n\n**Use when**: The user asks what ancestry reference panels are available, whether the 1000 Genomes panel is installed, or what source data and labels are used.\n\n**Why necessary**: Public panel metadata can be inspected without Active Genome Index access approval and tells agents whether private projection tools are answerable.\n\n**Not for**: Projecting or interpreting a user's genome; use ancestry.estimate_population_context after Active Genome Index access approval.\n\n**Example prompts**: What ancestry reference panel does Genomi have installed?\n\n**Result semantics**: Returns public reference-panel metadata and install status only; it does not read Active Genome Index.\n\n### ancestry.project_pca\n\nProject an approved sample into the installed 1000 Genomes ancestry PCA space and return nearest reference neighbors.\n\n**Use when**: The user or host agent needs PCA coordinates and nearest reference neighbors after scoped Active Genome Index access is approved.\n\n**Why necessary**: This is the focused computational step behind ancestry.estimate_population_context and avoids component\u002Fadmixture proportion claims.\n\n**Not for**: Haplogroups, local ancestry, relative matching, component proportions, or identity\u002Forigin prediction.\n\n**Example prompts**: Project my genome into the matching-build 1000 Genomes PCA panel.\n\n**Result semantics**: Returns PCA coordinates and reference-neighbor distances only; labels are reference-panel labels, not personal identity labels.\n","# Ancestry Reference-Panel Context\n\nUse this skill when the user asks about ancestry, population context, PCA\nprojection, reference-panel similarity, or which public reference samples their\ngenome is closest to.\n\n## Contract\n\n- This capability is a local reference-panel workflow, not an ethnicity or race\n  predictor.\n- Private tools require current-session Active Genome Index access approval or a genome source\n  path supplied in the current chat.\n- Public metadata tools do not read an Active Genome Index.\n- Private genotype data stays local. Do not upload sample genotypes to external\n  APIs or URLs.\n- The MVP supports GRCh38 and GRCh37. If `genome_build` is omitted, the tool\n  default is GRCh38 unless an approved Active Genome Index provides another\n  build; the returned `defaults_applied` records that default.\n- Labels are 1000 Genomes reference-panel labels, not ethnicity, nationality,\n  race, tribe, caste, religion, or personal identity.\n- Output is qualitative reference-panel similarity in PCA space. Do not produce\n  component percentages, admixture proportions, haplogroups, local ancestry,\n  ancestry dates, or relative matching.\n\n> **Convention:** See `skills\u002Fconventions\u002Fcontext-routing.md`.\n> **Convention:** See `skills\u002Fconventions\u002Fevidence-quality.md`.\n> **Convention:** See `skills\u002F_output-rules.md`.\n\n## First Actions\n\n1. Use `ancestry.list_reference_panels` to check whether the matching-build\n   1000 Genomes 30x panel is installed and to inspect source URLs and label\n   definitions.\n2. Use `ancestry.build_source_context` when the user asks what the panel means\n   or when you need explicit label and method boundaries before answering.\n3. For sample-specific questions, use `genomi.describe_context` only\n   when the chat asks about current Active Genome Index context or already mentioned a\n   genome source. If the user supplied a genome source path, that is approval to read\n   it for this session.\n4. Use `ancestry.estimate_population_context` as the default sample-specific\n   entry point. It runs overlap QC and PCA projection when enough markers are\n   usable.\n5. Use `ancestry.check_sample_overlap` when you only need QC readiness, and\n   `ancestry.project_pca` when the host agent needs raw PCA coordinates and\n   nearest reference-neighbor distances.\n\n## Library Handling\n\nThe required optional library is build-specific:\n`ancestry-1000g-30x-grch38` for GRCh38 samples and\n`ancestry-1000g-30x-grch37` for GRCh37 samples. If a private ancestry tool\nreturns `requires_library_install`, explain that the compact local panel is\nneeded for marker overlap and PCA projection, then ask before installing with\nthe returned `ask_user.install_command` or `missing_library.install_command`.\nFor example:\n\n```bash\ngenomi install --libraries ancestry-1000g-30x-grch38\ngenomi install --libraries ancestry-1000g-30x-grch38,liftover-chains,ancestry-1000g-30x-grch37\n```\n\nDo not treat a missing panel as evidence about the sample.\n\n## Interpretation Rules\n\n- Report marker overlap, projection readiness, marker-overlap quality, nearest reference\n  group labels, and the method boundary.\n- Marker-overlap quality is graded by the fraction of the loaded panel covered\n  by usable sample dosages. There is no absolute marker-count floor.\n- If less than 20% of the loaded panel is usable, do not project.\n- If 20%-49% of the loaded panel is usable, projection is allowed with low\n  marker-overlap quality and reference-neighbor context only.\n- If 50%-79% of the loaded panel is usable, projection is allowed with moderate\n  marker-overlap quality.\n- If at least 80% of the loaded panel is usable, projection is allowed with\n  high marker-overlap quality.\n- Use wording like: \"The sample projects closest to the EUR reference cluster\n  in this panel.\"\n- Do not say \"predict ethnicity\", \"determine origin\", or imply personal\n  identity from a reference-panel label.\n\n## User-Facing Answer Shape\n\nIf an Active Genome Index was projected, give the qualitative reference-panel\nsimilarity, marker-overlap quality, and limitations. If the tool only returned public\nmetadata, answer directly without an Active Genome Index status disclaimer.\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### ancestry.build_source_context\n\nExplain 1000 Genomes ancestry panel provenance, label meanings, sampling limits, and method boundaries.\n\n**Use when**: The user asks what the ancestry panel means, where labels come from, or why output is reference similarity rather than identity.\n\n**Why necessary**: Ancestry language is easy to overstate; source context gives agents explicit label and method boundaries before answering.\n\n**Not for**: Reading or projecting a user's genome; use ancestry.estimate_population_context after approval.\n\n**Example prompts**: Explain the source and limitations of the ancestry panel.\n\n**Result semantics**: Public metadata only; no Active Genome Index is read.\n\n### ancestry.check_sample_overlap\n\nCheck how many installed 1000 Genomes ancestry panel markers are usable in an approved Active Genome Index.\n\n**Use when**: The agent needs to know if a selected sample has enough overlap with the installed ancestry reference panel before projection.\n\n**Why necessary**: Projection is not interpretable below the overlap thresholds; this tool separates QC from interpretation.\n\n**Not for**: Public panel metadata; use ancestry.list_reference_panels. Ethnicity or origin prediction; ancestry tools provide reference-panel similarity only.\n\n**Example prompts**: Does my Active Genome Index have enough overlap with the ancestry panel?\n\n**Result semantics**: Reports usable marker count and projection readiness. It must not be interpreted as ethnicity, nationality, race, tribe, caste, religion, or identity.\n\n### ancestry.estimate_population_context\n\nEstimate qualitative reference-panel similarity for an approved GRCh37 or GRCh38 sample using local 1000 Genomes PCA projection.\n\n**Use when**: The user asks for ancestry or population context from their genome and has approved Active Genome Index use in this session.\n\n**Why necessary**: Provides a bounded default entry that combines overlap QC and PCA projection while preserving reference-similarity language.\n\n**Not for**: Ethnicity prediction, determining origin, component percentages, haplogroups, local ancestry, or relative matching.\n\n**Example prompts**: What 1000 Genomes reference cluster is my Active Genome Index closest to?\n\n**Result semantics**: The interpretation is qualitative reference-panel similarity only and must never be phrased as ethnicity, nationality, race, tribe, caste, religion, or personal identity.\n\n### ancestry.list_reference_panels\n\nList local ancestry reference panels, installation state, public source URLs, label definitions, and method boundaries.\n\n**Use when**: The user asks what ancestry reference panels are available, whether the 1000 Genomes panel is installed, or what source data and labels are used.\n\n**Why necessary**: Public panel metadata can be inspected without Active Genome Index access approval and tells agents whether private projection tools are answerable.\n\n**Not for**: Projecting or interpreting a user's genome; use ancestry.estimate_population_context after Active Genome Index access approval.\n\n**Example prompts**: What ancestry reference panel does Genomi have installed?\n\n**Result semantics**: Returns public reference-panel metadata and install status only; it does not read Active Genome Index.\n\n### ancestry.project_pca\n\nProject an approved sample into the installed 1000 Genomes ancestry PCA space and return nearest reference neighbors.\n\n**Use when**: The user or host agent needs PCA coordinates and nearest reference neighbors after scoped Active Genome Index access is approved.\n\n**Why necessary**: This is the focused computational step behind ancestry.estimate_population_context and avoids component\u002Fadmixture proportion claims.\n\n**Not for**: Haplogroups, local ancestry, relative matching, component proportions, or identity\u002Forigin prediction.\n\n**Example prompts**: Project my genome into the matching-build 1000 Genomes PCA panel.\n\n**Result semantics**: Returns PCA coordinates and reference-neighbor distances only; labels are reference-panel labels, not personal identity labels.\n",{"name":5,"tools":24,"mutating":34,"description":35},[25,26,27,28,29,30,31,32,33],"genomi.check_libraries","genomi.describe_context","ancestry.list_reference_panels","ancestry.build_source_context","ancestry.check_sample_overlap","ancestry.project_pca","ancestry.estimate_population_context","active_genome_index.approve_access","genomi.parse_source",true,"Use local ancestry reference-panel tools for 1000 Genomes GRCh37\u002FGRCh38 PCA\nprojection, marker overlap QC, and qualitative reference-neighbor context.\n","master","1df4f5bfb635e2d08f93a1102b70b840fbe80d86","skills\u002Fancestry",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":46,"prompt":56,"zipAvailable":34},[47,50,53],{"tool":48,"command":49},"npx","npx skills add exon-research\u002Fgenomi --skill ancestry",{"tool":51,"command":52},"bunx","bunx skills add exon-research\u002Fgenomi --skill ancestry",{"tool":54,"command":55},"pnpm","pnpm dlx skills add exon-research\u002Fgenomi --skill ancestry","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fexon-research\u002Fgenomi\u002Fblob\u002Fmaster\u002Fskills\u002Fancestry\u002FSKILL.md",[],[59,66,73,80,87,94],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"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":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"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":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"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":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":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":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"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":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"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",[],[]]