[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75PYBE8FEC36C75CS6TZZTM":3,"skill-same:01M75PYBE8FEC36C75CS6TZZTM":53},{"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":14,"repositoryHtmlUrl":35,"repositoryHomepageUrl":6,"ownerHtmlUrl":36,"ownerBlogUrl":6,"ownerDescription":37,"updatedAt":38,"install":39,"resources":52},"01M75PYBE8FEC36C75CS6TZZTM","prs",null,"Apply published polygenic scores from PGS Catalog to approved local personal DNA and return raw weighted score plus overlap QC.","yo-steven\u002Fgenomi-exploration-20260613","yo-steven","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F262067909?v=4","01M75PWHCKN2Q8VHD38R3834KJ","Steven Li","01M75PWHD790RCCRFRJ8G5KTSR",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fyo-steven\u002Fgenomi-exploration-20260613\u002Fblob\u002Fmain\u002Fskills\u002Fprs\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: prs\ndescription: >\n  Apply published polygenic scores from PGS Catalog to approved local personal\n  DNA and return raw weighted score plus overlap QC.\ntools:\n  - prs.search_scores\n  - prs.fetch_score_metadata\n  - prs.list_imported_scores\n  - prs.check_score_overlap\n  - prs.calculate_score\n  - prs.build_source_context\n---\n\n# Polygenic Scores\n\nUse this skill when the user asks about polygenic risk scores, PRS, PGS\nCatalog scores, common disease or trait risk from many variants, or applying a\npublished scoring file to their genome.\n\n## Boundaries\n\n- PRS\u002FPGS here means applying published variant weights from a scoring file.\n  Genomi does not train new PRS models from GWAS summary statistics.\n- Default genome build is `GRCh38` when omitted; use `GRCh37` only when the\n  Active Genome Index is GRCh37\u002Fhg19.\n- Active Genome Index artifacts stay local. Public score metadata may use PGS\n  Catalog, but private genotypes are not uploaded to external services.\n- A raw PRS is common-risk or trait context, not a diagnosis, absolute disease\n  risk, treatment recommendation, or clinical category.\n- Only state standardized score context when valid `score_mean` and `score_sd`\n  are supplied for the same score, build, cohort\u002Freference distribution, and\n  scoring convention.\n- Do not use PRS output for ethnicity, identity, monogenic diagnosis,\n  medication response, or rare-disease causality.\n\n## Workflow\n\n1. Use `prs.search_scores` for public trait or score discovery. If the user\n   already supplies a PGS ID, use that ID directly.\n2. Use `prs.fetch_score_metadata` when the source publication, build, variant\n   count, scoring-file URLs, licensing, or cohort\u002Fevaluation context matters.\n3. Use `prs.calculate_score` with the chosen `pgs_id` and the user's genome\n   source to get the raw weighted score plus overlap QC.\n4. Use `prs.check_score_overlap` when you only need readiness and QC without a\n   calculated score.\n5. Use `prs.list_imported_scores` when the user asks what scores are already\n   available locally.\n6. Use `prs.build_source_context` when the user asks what PRS can or cannot\n   tell them.\n\n## When published calibration is missing\n\nPGS Catalog rarely publishes a reference cohort mean\u002FSD, so a raw weighted\nscore has units on an arbitrary scale. Deliver a defensible directional or\nquantitative answer for this specific question by combining capabilities\nthat contribute orthogonal evidence — population allele frequencies feeding\na closed-form z, direct effect-allele dosages at well-replicated lead loci,\nadditional published scores derived by different methods, treatment-response\ncontext when the outcome is treatable, mechanism context from functional or\npathway evidence, or whatever else Genomi currently exposes that fits.\nDisclose the assumptions of any closed-form estimate (HWE, variant\nindependence, ancestry of the allele-frequency source).\n\n## Answering\n\nWhen an Active Genome Index is scored or its overlap changes the result, report\nthe score ID\u002Fsource, genome build, overlap status, matched\u002Fmissing\u002Fexcluded\nvariant counts, and whether the result is raw or calibrated. Do not add a\nroutine Active Genome Index status line for public score metadata lookups.\n\nUse careful language:\n\n- \"The raw weighted score was calculated from N matched score variants.\"\n- \"This is source-bound PRS context, not an absolute risk estimate.\"\n- \"Performance may not transfer across ancestry\u002Fevaluation cohorts.\"\n- When grounded in an analytic z from gnomAD or a multi-score consensus:\n  \"Your analytic z relative to \u003Cpopulation> under HWE is +X.X, ~Yth\n  percentile. This is a closed-form estimate, not an empirical\n  reference-cohort percentile.\"\n\nDirectional language (\"leans above population average\", \"in the upper\ntertile of the analytic z distribution\") is appropriate when grounded in\nthe orthogonal evidence the synthesis combined.\n\nAvoid:\n\n- Clinical-risk category labels (high\u002Felevated\u002Flow risk) unless a\n  validated calibration and category threshold from the same source\n  context is explicitly supplied.\n- Absolute outcome probabilities (\"X% chance of disease by age N\") —\n  these require an empirical risk-calibration model.\n- \"This diagnoses\", \"rules out\", \"predicts disease\", or \"determines origin\".\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### prs.build_source_context\n\nExplain PGS Catalog provenance, local scoring workflow, genome-build defaults, calibration limits, and PRS risk boundaries.\n\n**Use when**: The user asks what PRS can and cannot tell them, whether PRS means common risk analysis, or how Genomi applies published scores.\n\n**Why necessary**: PRS answers require explicit boundaries around calibration, cohort portability, missing variants, and clinical non-diagnosis.\n\n**Not for**: Calculating a personal score; use prs.calculate_score after Active Genome Index access approval.\n\n**Example prompts**: Explain how Genomi implements PRS. Does PRS give common disease risk?\n\n**Result semantics**: Returns public method context only; it does not read Active Genome Index.\n\n### prs.calculate_score\n\nApply a published polygenic score to an approved Active Genome Index and return raw weighted score plus QC.\n\n**Use when**: The user asks to calculate or apply a published PRS\u002FPGS score to their genome.\n\n**Why necessary**: This keeps Active Genome Index local, applies only selected published weights, reports overlap and build defaults, and avoids unsupported risk-category claims.\n\n**Not for**: Training a new PRS model. Diagnosis, monogenic disease interpretation, medication response, or absolute-risk prediction without a validated calibration model. Ancestry or identity inference.\n\n**Example prompts**: Calculate PGS000001 for my Active Genome Index. Apply this local scoring file to my GRCh38 genome.\n\n**Result semantics**: Output is a raw weighted score and QC unless explicit calibration parameters are supplied. Do not phrase it as diagnosis, absolute disease risk, ethnicity, or clinical actionability.\n\n### prs.check_score_overlap\n\nCheck how many variants from a polygenic score are usable in an approved Active Genome Index.\n\n**Use when**: The agent needs PRS overlap\u002Freadiness before calculating or interpreting a published polygenic score.\n\n**Why necessary**: A PRS score can be misleading with low variant overlap, build mismatch, unharmonized palindromic alleles, or missing genotype records.\n\n**Not for**: Public score search; use prs.search_scores. Diagnosis or absolute risk classification.\n\n**Example prompts**: Does my genome have enough overlap with PGS000001?\n\n**Result semantics**: Reports overlap and calculation readiness only; missing score variants are not negative evidence for disease risk.\n\n### prs.fetch_score_metadata\n\nFetch detailed public PGS Catalog metadata for one score ID, including scoring-file URLs and source publication context.\n\n**Use when**: The agent needs the exact PGS Catalog record context — trait, build, variant count, source publication, cohort, ancestry\u002Fevaluation, licensing — before explaining or applying a score.\n\n**Why necessary**: The score metadata carries build, trait, source publication, cohort, ancestry\u002Fevaluation, and licensing context that determines whether applying a score is appropriate.\n\n**Not for**: Calculating a personal score; use prs.calculate_score with the chosen pgs_id.\n\n**Example prompts**: Fetch metadata for PGS000001.\n\n**Result semantics**: Returns public PGS Catalog metadata only and may report source_unavailable if the external source cannot be reached.\n\n### prs.import_scoring_file\n\nImport a PGS Catalog or local scoring file into Genomi's local PRS score cache for a declared genome build.\n\n**Use when**: A score has been selected and needs to be materialized locally before overlap checking or scoring.\n\n**Why necessary**: Private genotype scoring must run against local score artifacts rather than uploading genotypes to external services.\n\n**Not for**: Reading Active Genome Index; import is public\u002Flocal score materialization only. Interpreting the score as risk; use prs.calculate_score and preserve its limitations.\n\n**Example prompts**: Import PGS000001 for GRCh38. Import this local scoring file for GRCh37.\n\n**Result semantics**: Creates a local cache of variant weights and manifest metadata. The default genome_build is GRCh38 when omitted and is disclosed in defaults_applied.\n\n### prs.list_imported_scores\n\nList polygenic scores available locally for use without reading Active Genome Index.\n\n**Use when**: The user asks which polygenic scores are available locally.\n\n**Why necessary**: Knowing which scores are already available locally helps the agent pick a matching genome build and avoid re-fetching.\n\n**Not for**: Calculating personal PRS values; use prs.calculate_score after approval.\n\n**Example prompts**: Which PRS scores are imported locally?\n\n**Result semantics**: Lists local score-cache metadata only; it does not read Active Genome Index.\n\n### prs.search_scores\n\nSearch public PGS Catalog score metadata by trait, score ID, EFO term, or free-text query without reading Active Genome Index.\n\n**Use when**: The user asks which published PGS\u002FPRS scores exist for a trait or provides a PGS Catalog score ID.\n\n**Why necessary**: Score selection is source-specific and must expose trait, build, variant count, publication, evaluation, and licensing context before using a score on Active Genome Index.\n\n**Not for**: Reading or scoring a user's genome; pass the chosen pgs_id to prs.calculate_score after Active Genome Index access approval. Training a new PRS from GWAS summary statistics.\n\n**Example prompts**: Find PGS Catalog scores for coronary artery disease. What is PGS000001?\n\n**Result semantics**: Returns public score candidates and source metadata only; it does not read Active Genome Index.\n","# Polygenic Scores\n\nUse this skill when the user asks about polygenic risk scores, PRS, PGS\nCatalog scores, common disease or trait risk from many variants, or applying a\npublished scoring file to their genome.\n\n## Boundaries\n\n- PRS\u002FPGS here means applying published variant weights from a scoring file.\n  Genomi does not train new PRS models from GWAS summary statistics.\n- Default genome build is `GRCh38` when omitted; use `GRCh37` only when the\n  Active Genome Index is GRCh37\u002Fhg19.\n- Active Genome Index artifacts stay local. Public score metadata may use PGS\n  Catalog, but private genotypes are not uploaded to external services.\n- A raw PRS is common-risk or trait context, not a diagnosis, absolute disease\n  risk, treatment recommendation, or clinical category.\n- Only state standardized score context when valid `score_mean` and `score_sd`\n  are supplied for the same score, build, cohort\u002Freference distribution, and\n  scoring convention.\n- Do not use PRS output for ethnicity, identity, monogenic diagnosis,\n  medication response, or rare-disease causality.\n\n## Workflow\n\n1. Use `prs.search_scores` for public trait or score discovery. If the user\n   already supplies a PGS ID, use that ID directly.\n2. Use `prs.fetch_score_metadata` when the source publication, build, variant\n   count, scoring-file URLs, licensing, or cohort\u002Fevaluation context matters.\n3. Use `prs.calculate_score` with the chosen `pgs_id` and the user's genome\n   source to get the raw weighted score plus overlap QC.\n4. Use `prs.check_score_overlap` when you only need readiness and QC without a\n   calculated score.\n5. Use `prs.list_imported_scores` when the user asks what scores are already\n   available locally.\n6. Use `prs.build_source_context` when the user asks what PRS can or cannot\n   tell them.\n\n## When published calibration is missing\n\nPGS Catalog rarely publishes a reference cohort mean\u002FSD, so a raw weighted\nscore has units on an arbitrary scale. Deliver a defensible directional or\nquantitative answer for this specific question by combining capabilities\nthat contribute orthogonal evidence — population allele frequencies feeding\na closed-form z, direct effect-allele dosages at well-replicated lead loci,\nadditional published scores derived by different methods, treatment-response\ncontext when the outcome is treatable, mechanism context from functional or\npathway evidence, or whatever else Genomi currently exposes that fits.\nDisclose the assumptions of any closed-form estimate (HWE, variant\nindependence, ancestry of the allele-frequency source).\n\n## Answering\n\nWhen an Active Genome Index is scored or its overlap changes the result, report\nthe score ID\u002Fsource, genome build, overlap status, matched\u002Fmissing\u002Fexcluded\nvariant counts, and whether the result is raw or calibrated. Do not add a\nroutine Active Genome Index status line for public score metadata lookups.\n\nUse careful language:\n\n- \"The raw weighted score was calculated from N matched score variants.\"\n- \"This is source-bound PRS context, not an absolute risk estimate.\"\n- \"Performance may not transfer across ancestry\u002Fevaluation cohorts.\"\n- When grounded in an analytic z from gnomAD or a multi-score consensus:\n  \"Your analytic z relative to \u003Cpopulation> under HWE is +X.X, ~Yth\n  percentile. This is a closed-form estimate, not an empirical\n  reference-cohort percentile.\"\n\nDirectional language (\"leans above population average\", \"in the upper\ntertile of the analytic z distribution\") is appropriate when grounded in\nthe orthogonal evidence the synthesis combined.\n\nAvoid:\n\n- Clinical-risk category labels (high\u002Felevated\u002Flow risk) unless a\n  validated calibration and category threshold from the same source\n  context is explicitly supplied.\n- Absolute outcome probabilities (\"X% chance of disease by age N\") —\n  these require an empirical risk-calibration model.\n- \"This diagnoses\", \"rules out\", \"predicts disease\", or \"determines origin\".\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### prs.build_source_context\n\nExplain PGS Catalog provenance, local scoring workflow, genome-build defaults, calibration limits, and PRS risk boundaries.\n\n**Use when**: The user asks what PRS can and cannot tell them, whether PRS means common risk analysis, or how Genomi applies published scores.\n\n**Why necessary**: PRS answers require explicit boundaries around calibration, cohort portability, missing variants, and clinical non-diagnosis.\n\n**Not for**: Calculating a personal score; use prs.calculate_score after Active Genome Index access approval.\n\n**Example prompts**: Explain how Genomi implements PRS. Does PRS give common disease risk?\n\n**Result semantics**: Returns public method context only; it does not read Active Genome Index.\n\n### prs.calculate_score\n\nApply a published polygenic score to an approved Active Genome Index and return raw weighted score plus QC.\n\n**Use when**: The user asks to calculate or apply a published PRS\u002FPGS score to their genome.\n\n**Why necessary**: This keeps Active Genome Index local, applies only selected published weights, reports overlap and build defaults, and avoids unsupported risk-category claims.\n\n**Not for**: Training a new PRS model. Diagnosis, monogenic disease interpretation, medication response, or absolute-risk prediction without a validated calibration model. Ancestry or identity inference.\n\n**Example prompts**: Calculate PGS000001 for my Active Genome Index. Apply this local scoring file to my GRCh38 genome.\n\n**Result semantics**: Output is a raw weighted score and QC unless explicit calibration parameters are supplied. Do not phrase it as diagnosis, absolute disease risk, ethnicity, or clinical actionability.\n\n### prs.check_score_overlap\n\nCheck how many variants from a polygenic score are usable in an approved Active Genome Index.\n\n**Use when**: The agent needs PRS overlap\u002Freadiness before calculating or interpreting a published polygenic score.\n\n**Why necessary**: A PRS score can be misleading with low variant overlap, build mismatch, unharmonized palindromic alleles, or missing genotype records.\n\n**Not for**: Public score search; use prs.search_scores. Diagnosis or absolute risk classification.\n\n**Example prompts**: Does my genome have enough overlap with PGS000001?\n\n**Result semantics**: Reports overlap and calculation readiness only; missing score variants are not negative evidence for disease risk.\n\n### prs.fetch_score_metadata\n\nFetch detailed public PGS Catalog metadata for one score ID, including scoring-file URLs and source publication context.\n\n**Use when**: The agent needs the exact PGS Catalog record context — trait, build, variant count, source publication, cohort, ancestry\u002Fevaluation, licensing — before explaining or applying a score.\n\n**Why necessary**: The score metadata carries build, trait, source publication, cohort, ancestry\u002Fevaluation, and licensing context that determines whether applying a score is appropriate.\n\n**Not for**: Calculating a personal score; use prs.calculate_score with the chosen pgs_id.\n\n**Example prompts**: Fetch metadata for PGS000001.\n\n**Result semantics**: Returns public PGS Catalog metadata only and may report source_unavailable if the external source cannot be reached.\n\n### prs.import_scoring_file\n\nImport a PGS Catalog or local scoring file into Genomi's local PRS score cache for a declared genome build.\n\n**Use when**: A score has been selected and needs to be materialized locally before overlap checking or scoring.\n\n**Why necessary**: Private genotype scoring must run against local score artifacts rather than uploading genotypes to external services.\n\n**Not for**: Reading Active Genome Index; import is public\u002Flocal score materialization only. Interpreting the score as risk; use prs.calculate_score and preserve its limitations.\n\n**Example prompts**: Import PGS000001 for GRCh38. Import this local scoring file for GRCh37.\n\n**Result semantics**: Creates a local cache of variant weights and manifest metadata. The default genome_build is GRCh38 when omitted and is disclosed in defaults_applied.\n\n### prs.list_imported_scores\n\nList polygenic scores available locally for use without reading Active Genome Index.\n\n**Use when**: The user asks which polygenic scores are available locally.\n\n**Why necessary**: Knowing which scores are already available locally helps the agent pick a matching genome build and avoid re-fetching.\n\n**Not for**: Calculating personal PRS values; use prs.calculate_score after approval.\n\n**Example prompts**: Which PRS scores are imported locally?\n\n**Result semantics**: Lists local score-cache metadata only; it does not read Active Genome Index.\n\n### prs.search_scores\n\nSearch public PGS Catalog score metadata by trait, score ID, EFO term, or free-text query without reading Active Genome Index.\n\n**Use when**: The user asks which published PGS\u002FPRS scores exist for a trait or provides a PGS Catalog score ID.\n\n**Why necessary**: Score selection is source-specific and must expose trait, build, variant count, publication, evaluation, and licensing context before using a score on Active Genome Index.\n\n**Not for**: Reading or scoring a user's genome; pass the chosen pgs_id to prs.calculate_score after Active Genome Index access approval. Training a new PRS from GWAS summary statistics.\n\n**Example prompts**: Find PGS Catalog scores for coronary artery disease. What is PGS000001?\n\n**Result semantics**: Returns public score candidates and source metadata only; it does not read Active Genome Index.\n",{"name":5,"tools":24,"description":31},[25,26,27,28,29,30],"prs.search_scores","prs.fetch_score_metadata","prs.list_imported_scores","prs.check_score_overlap","prs.calculate_score","prs.build_source_context","Apply published polygenic scores from PGS Catalog to approved local personal DNA and return raw weighted score plus overlap QC.\n","main","baf95108bc0bb0453d4d64ab342ce9edc513985c","skills\u002Fprs","https:\u002F\u002Fgithub.com\u002Fyo-steven\u002Fgenomi-exploration-20260613","https:\u002F\u002Fgithub.com\u002Fyo-steven","2nd biggest fan of Garry Tan","2026-06-14 07:28:34",{"source":8,"skillName":5,"commands":40,"prompt":50,"zipAvailable":51},[41,44,47],{"tool":42,"command":43},"npx","npx skills add yo-steven\u002Fgenomi-exploration-20260613 --skill prs",{"tool":45,"command":46},"bunx","bunx skills add yo-steven\u002Fgenomi-exploration-20260613 --skill prs",{"tool":48,"command":49},"pnpm","pnpm dlx skills add yo-steven\u002Fgenomi-exploration-20260613 --skill prs","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fyo-steven\u002Fgenomi-exploration-20260613\u002Fblob\u002Fmain\u002Fskills\u002Fprs\u002FSKILL.md",true,[],[54,61,68,75,82,89],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M75PYQ79GDHFYVWT6XR7Y4JW","variant-evidence","Answer specific rsID, allele, gene, region, genotype, and absence\u002Fcallability\nquestions using explicit session context or public evidence.","https:\u002F\u002Fgithub.com\u002Fyo-steven\u002Fgenomi-exploration-20260613\u002Fblob\u002Fmain\u002Fskills\u002Fvariant-evidence\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M75PYMQWNAHAPQS5NP90RSQG","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\u002Fyo-steven\u002Fgenomi-exploration-20260613\u002Fblob\u002Fmain\u002Fskills\u002Fsource-research\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M75PYJGYQ3A9Q2TN02BJ1AKA","sequence","Deterministic sequence utilities for translation, ORFs, restriction sites,\nKozak context, primer checks, and local FASTA record matching.","https:\u002F\u002Fgithub.com\u002Fyo-steven\u002Fgenomi-exploration-20260613\u002Fblob\u002Fmain\u002Fskills\u002Fsequence\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M75PYFD88KZA7NZ8WZ8TWRX4","rare-disease-cancer","Plan rare disease, hereditary disease, and cancer risk source investigation\nfrom public targets or selected active genome evidence.","https:\u002F\u002Fgithub.com\u002Fyo-steven\u002Fgenomi-exploration-20260613\u002Fblob\u002Fmain\u002Fskills\u002Frare-disease-cancer\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M75PY79TYD7AGMF5AGNJV57J","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\u002Fyo-steven\u002Fgenomi-exploration-20260613\u002Fblob\u002Fmain\u002Fskills\u002Fpharmacogenomics\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":19},"01M75PY2X45ZQWRTM530J0B7JM","nutrigenomics","Curated single-marker evidence for declared nutrient-metabolism,\nfood-tolerance, and taste-perception domains. Refuses diet prescriptions,\nsupplement dosing, weight-loss prediction, methylation-cycle prescriptions,\nmicrobiome-mediated effects, and other out-of-scope nutrigenomic claims.","https:\u002F\u002Fgithub.com\u002Fyo-steven\u002Fgenomi-exploration-20260613\u002Fblob\u002Fmain\u002Fskills\u002Fnutrigenomics\u002FSKILL.md",[],[]]