[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7543FDFTWSYVVTEGHQSPHQK":3,"skill-same:01M7543FDFTWSYVVTEGHQSPHQK":66},{"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":44,"commitSha":45,"skillDirectory":46,"forksCount":47,"repositoryHtmlUrl":48,"repositoryHomepageUrl":49,"ownerHtmlUrl":50,"ownerBlogUrl":6,"ownerDescription":51,"updatedAt":52,"install":53,"resources":65},"01M7543FDFTWSYVVTEGHQSPHQK","pharmacogenomics",null,"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.","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\u002Fpharmacogenomics\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: pharmacogenomics\ndescription: |\n  Answer drug-response, medication, PharmGKB-style, PGxDB, ATC, DrugBank,\n  gene-drug, and variant-drug questions using public PGx evidence plus local\n  sample genotype support when an Active Genome Index is selected.\ntools:\n  - genomi.describe_context\n  - pharmacogenomics.review_medication\n  - pharmacogenomics.describe_gene_requirements\n  - pharmacogenomics.preflight_pharmcat\n  - pharmacogenomics.prepare_outside_call_tsv\n  - pharmacogenomics.validate_outside_call_tsv\n  - pharmacogenomics.import_pharmcat_artifacts\n  - pharmacogenomics.check_pharmcat\n  - pharmacogenomics.run_pharmcat\n  - pharmacogenomics.fetch_clinpgx\n  - pharmacogenomics.fetch_fda_labels\n  - pharmacogenomics.fetch_pgxdb\n  - variant.resolve\n  - active_genome_index.classify_genotype_support\n  - research.list_sources\n  - research.record\n  - research.query\nmutating: true\n---\n\n# Pharmacogenomics\n\nUse this skill when the user asks about medication response, PGx guidelines,\ndrug-gene or variant-drug evidence, PGxDB, ATC codes, DrugBank IDs, PharmCAT,\nor pharmacogene sample evidence.\n\n## Contract\n\n- Drug-response claims use public PGx source evidence.\n- Personal drug-response statements cite separate local genotype or PGx caller\n  support.\n- External PGx lookups receive selected public targets only.\n- Source-backed PGx findings can be stored as shared reviewed research.\n- User-specific sample interpretations can be stored as private reviewed\n  research.\n\n> **Convention:** See `skills\u002Fconventions\u002Fevidence-quality.md`.\n> **Convention:** See `skills\u002F_output-rules.md`.\n\n## Primary Flow\n\n1. Use `pharmacogenomics.review_medication` for ordinary medication questions.\n   It combines ClinPGx, FDA PGx tables, PGxDB, stored reviewed research, and\n   optional selected sample evidence in one bounded review.\n2. Inspect `evidence_envelope`, `medication_review_matrix`,\n   `evidence_matrix`, `target_inventory`, `answer_support`, and\n   `unanswered_answer_components` before answering. Treat each\n   `medication_review_matrix.rows[]` entry as the review unit.\n3. If the answer needs source review beyond returned public records, use\n   `research.list_sources`, review the selected public target, then store the\n   finding with `research.record`.\n4. If the answer needs personal sample evidence, use the Active Genome Index\n   only when selected or supplied in this chat. Confirm relevant alleles with\n   `variant.resolve` or `active_genome_index.classify_genotype_support`.\n\n## Tool Choices\n\n- `pharmacogenomics.review_medication`: bounded medication evidence review;\n  public-only by default, with Active Genome Index evidence when selected.\n- `pharmacogenomics.fetch_clinpgx`, `pharmacogenomics.fetch_fda_labels`, and\n  `pharmacogenomics.fetch_pgxdb`: focused public PGx source retrieval when the\n  medication review needs a source-specific follow-up.\n- `pharmacogenomics.describe_gene_requirements`: gene-specific sample evidence\n  requirements for named allele matching, outside calls, HLA, MT-RNR1, G6PD,\n  and SV\u002FCNV-sensitive genes.\n- `pharmacogenomics.check_pharmcat`: check local PharmCAT availability.\n- `pharmacogenomics.preflight_pharmcat`: inspect whether the selected Active\n  Genome Index can provide a suitable PharmCAT input before running it.\n- `pharmacogenomics.prepare_outside_call_tsv` and\n  `pharmacogenomics.validate_outside_call_tsv`: prepare or validate specialized\n  outside-call evidence for PharmCAT.\n- `pharmacogenomics.run_pharmcat`: run broad PharmCAT calling from the selected\n  Active Genome Index and return provenance plus `sample_pgx_matrix` rows\n  projected from report, phenotype, calls-only, and matcher artifacts.\n- `pharmacogenomics.import_pharmcat_artifacts`: import existing PharmCAT JSON,\n  TSV, matcher, phenotype, missing-position, or output-directory artifacts and\n  return `sample_pgx_matrix`.\n\nPGx capability metadata is exposed through `genomi.list_resources`; there is\nno separate PGx capability-listing tool.\n\n## Answering\n\n- Mention Active Genome Index evidence only when it changes the medication\n  interpretation, limitation, blocker, or next action.\n- Keep PGx language informational and recommend clinical confirmation for\n  medication decisions.\n- Do not infer medication actionability from a genotype alone; connect sample\n  evidence to public drug-response evidence.\n- Treat user-provided diplotypes, phenotypes, activity scores, and outside\n  calls as supplied sample evidence that may need independent confirmation.\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### pharmacogenomics.check_pharmcat\n\nCheck local PharmCAT availability and version provenance for broad PGx calling from an AGI-derived PharmCAT input.\n\n**Use when**: The agent needs to know whether broad PharmCAT PGx calling is available before running pharmacogenomics.run_pharmcat.\n\n**Why necessary**: External PGx calls need availability and version provenance before they are trusted.\n\n**Result semantics**: Reports local PharmCAT executable\u002Fjar availability and version probe output for auditability before broad PGx calling.\n\n### pharmacogenomics.describe_gene_requirements\n\nReturn pharmacogene-specific sample evidence requirements for PharmCAT named allele matching, outside calls, CYP2D6 SV\u002FCNV handling, HLA typing, MT-RNR1, and G6PD chrX representation.\n\n**Use when**: The selected medication or source evidence names a pharmacogene and the agent needs to choose sample evidence, PharmCAT, outside-call, or targeted lookup handling.\n\n**Why necessary**: Complex pharmacogenes require special evidence handling that a simple rsID lookup cannot provide.\n\n**Result semantics**: Returns packaged source-backed pharmacogene sample-evidence requirements, candidate tools, and source references for the selected gene.\n\n### pharmacogenomics.fetch_clinpgx\n\nFetch traceable ClinPGx pharmacogenomic guideline, clinical annotation, and FDA label evidence for a selected drug, gene, or rsID; compact normalized records are returned by default.\n\n**Use when**: The question involves medication response, adverse effects, CPIC\u002FDPWG guidance, FDA drug-label PGx context, PharmGKB\u002FClinPGx annotations, or drug plus gene\u002FrsID interpretation.\n\n**Why necessary**: Guideline, clinical annotation, and label rows are separate public PGx evidence from sample genotype calls.\n\n**Result semantics**: Fetches public guideline, annotation, and label rows; raw API records are opt-in with include_raw_records; personal interpretation requires separate local genotype or diplotype evidence.\n\n### pharmacogenomics.fetch_fda_labels\n\nFetch targeted FDA pharmacogenomic biomarker-labeling and pharmacogenetic-association table rows from official FDA pages.\n\n**Use when**: The question needs FDA biomarker-labeling table context or FDA pharmacogenetic association table context for a selected drug or gene.\n\n**Why necessary**: FDA biomarker and pharmacogenetic-association tables are official label evidence with their own boundaries.\n\n**Result semantics**: Fetches official FDA table rows; keep biomarker-labeling rows separate from pharmacogenetic-association rows and combine with separate sample evidence for personal interpretation.\n\n### pharmacogenomics.fetch_pgxdb\n\nFetch targeted PGxDB pharmacogenomic evidence for a selected drug, ATC code, DrugBank ID, rsID, variant marker, or gene.\n\n**Use when**: The question involves medication response, adverse effects, pharmacogenomics, PharmGKB-style evidence, a drug plus rsID, or a drug plus gene.\n\n**Why necessary**: PGxDB association records provide targeted drug-variant evidence distinct from guideline recommendations.\n\n**Result semantics**: Fetches public PGxDB rows; sample interpretation requires separate local genotype evidence.\n\n### pharmacogenomics.import_pharmcat_artifacts\n\nImport existing PharmCAT report JSON, calls-only TSV, matcher JSON, phenotype JSON, missing-position VCF, or output directory without executing PharmCAT.\n\n**Use when**: The agent has existing PharmCAT artifacts and needs sample-side PGx evidence without running local PharmCAT.\n\n**Why necessary**: Existing PharmCAT outputs should be reused rather than rerun when sample-side PGx evidence already exists.\n\n**Result semantics**: Parses existing PharmCAT artifacts into `sample_pgx_matrix`, evidence summaries, and record_research_payloads used by pharmacogenomics.run_pharmcat, including interpretation readiness and missing-position review facts.\n\n### pharmacogenomics.preflight_pharmcat\n\nInspect selected Active Genome Index structure for broad PharmCAT PGx calling without running PharmCAT or writing artifacts.\n\n**Use when**: The agent needs read-only Active Genome Index structure, sample-column, genotype-field, or header evidence before broad PharmCAT PGx calling.\n\n**Why necessary**: Broad PharmCAT runs need input suitability checks before execution or artifact interpretation.\n\n**Result semantics**: Returns local AGI-derived preflight facts without exposing the raw AGI path; PharmCAT coverage sufficiency is judged from execution artifacts, especially missing PGx position review.\n\n### pharmacogenomics.prepare_outside_call_tsv\n\nPrepare a PharmCAT outside-call TSV from supported specialized caller output such as OptiType HLA calls, StellarPGx CYP2D6 summaries, or generic gene\u002Fdiplotype tables.\n\n**Use when**: The agent has specialized caller output for HLA-A, HLA-B, CYP2D6, MT-RNR1, or another pharmacogene and needs a PharmCAT outside-call TSV.\n\n**Why necessary**: Specialized callers for HLA, CYP2D6, and related genes need conversion before PharmCAT can consume them.\n\n**Result semantics**: Writes a canonical outside-call TSV under Genomi output storage or the requested output_file, validates it, and returns output.path for pharmacogenomics.run_pharmcat with parsed rows, invalid rows, warnings, caller format, and sample identity facts.\n\n### pharmacogenomics.review_medication\n\nReview medication pharmacogenomic evidence as medication-first rows combining ClinPGx guideline\u002Flabel context, FDA PGx table rows, PGxDB association evidence, Active Genome Index rsID lookup when selected, implemented marker-definition evidence when selected, evidence components, and target inventory.\n\n**Use when**: Combines public PGx evidence with selected active-genome-index or marker evidence for one medication.\n\n**Why necessary**: Medication-response questions need drug-specific PGx sources plus optional personal genotype evidence in one bounded review.\n\n**Not for**: diagnosing disease risk; it is medication-response evidence.\n\n**Example prompts**: Does my DNA say anything about clopidogrel?\n\n**Result semantics**: Returns `medication_review_matrix` where each row carries drug, gene, variant\u002Fdiplotype\u002Fphenotype, recommendation\u002Fsource text, evidence IDs, sample relevance, row readiness, and clinical boundary. Public-only by default unless active-genome-index context is selected.\n\n### pharmacogenomics.run_pharmcat\n\nRun a local PharmCAT installation from an approved Active Genome Index for broad PGx diplotype, phenotype, recommendation artifacts, and `sample_pgx_matrix` rows.\n\n**Use when**: Runs local PharmCAT from the selected Active Genome Index to generate broad PGx diplotype, phenotype, and recommendation artifacts.\n\n**Why necessary**: Broad PGx diplotype and recommendation artifacts require a specialized external caller.\n\n**Result semantics**: Runs local PharmCAT as sample-side PGx evidence generation; returns input preflight, runtime provenance, outside-call validation, `sample_pgx_matrix`, artifacts, warnings, interpretation readiness, and record_research_payloads for synthesis.\n\n### pharmacogenomics.validate_outside_call_tsv\n\nValidate PharmCAT outside-call TSV structure and summarize selected diplotype, phenotype, or activity-score evidence.\n\n**Use when**: The PGx sample evidence path already has a PharmCAT outside-call TSV for CYP2D6, HLA-A, HLA-B, MT-RNR1, or another specialized caller result before PharmCAT execution.\n\n**Why necessary**: Outside calls can override complex gene evidence, so their structure must be validated before use.\n\n**Result semantics**: Validates outside-call TSV shape, hides the local path, returns parsed rows, invalid rows, warnings, and explains that outside calls override PharmCAT VCF-derived calls for the same gene.\n","# Pharmacogenomics\n\nUse this skill when the user asks about medication response, PGx guidelines,\ndrug-gene or variant-drug evidence, PGxDB, ATC codes, DrugBank IDs, PharmCAT,\nor pharmacogene sample evidence.\n\n## Contract\n\n- Drug-response claims use public PGx source evidence.\n- Personal drug-response statements cite separate local genotype or PGx caller\n  support.\n- External PGx lookups receive selected public targets only.\n- Source-backed PGx findings can be stored as shared reviewed research.\n- User-specific sample interpretations can be stored as private reviewed\n  research.\n\n> **Convention:** See `skills\u002Fconventions\u002Fevidence-quality.md`.\n> **Convention:** See `skills\u002F_output-rules.md`.\n\n## Primary Flow\n\n1. Use `pharmacogenomics.review_medication` for ordinary medication questions.\n   It combines ClinPGx, FDA PGx tables, PGxDB, stored reviewed research, and\n   optional selected sample evidence in one bounded review.\n2. Inspect `evidence_envelope`, `medication_review_matrix`,\n   `evidence_matrix`, `target_inventory`, `answer_support`, and\n   `unanswered_answer_components` before answering. Treat each\n   `medication_review_matrix.rows[]` entry as the review unit.\n3. If the answer needs source review beyond returned public records, use\n   `research.list_sources`, review the selected public target, then store the\n   finding with `research.record`.\n4. If the answer needs personal sample evidence, use the Active Genome Index\n   only when selected or supplied in this chat. Confirm relevant alleles with\n   `variant.resolve` or `active_genome_index.classify_genotype_support`.\n\n## Tool Choices\n\n- `pharmacogenomics.review_medication`: bounded medication evidence review;\n  public-only by default, with Active Genome Index evidence when selected.\n- `pharmacogenomics.fetch_clinpgx`, `pharmacogenomics.fetch_fda_labels`, and\n  `pharmacogenomics.fetch_pgxdb`: focused public PGx source retrieval when the\n  medication review needs a source-specific follow-up.\n- `pharmacogenomics.describe_gene_requirements`: gene-specific sample evidence\n  requirements for named allele matching, outside calls, HLA, MT-RNR1, G6PD,\n  and SV\u002FCNV-sensitive genes.\n- `pharmacogenomics.check_pharmcat`: check local PharmCAT availability.\n- `pharmacogenomics.preflight_pharmcat`: inspect whether the selected Active\n  Genome Index can provide a suitable PharmCAT input before running it.\n- `pharmacogenomics.prepare_outside_call_tsv` and\n  `pharmacogenomics.validate_outside_call_tsv`: prepare or validate specialized\n  outside-call evidence for PharmCAT.\n- `pharmacogenomics.run_pharmcat`: run broad PharmCAT calling from the selected\n  Active Genome Index and return provenance plus `sample_pgx_matrix` rows\n  projected from report, phenotype, calls-only, and matcher artifacts.\n- `pharmacogenomics.import_pharmcat_artifacts`: import existing PharmCAT JSON,\n  TSV, matcher, phenotype, missing-position, or output-directory artifacts and\n  return `sample_pgx_matrix`.\n\nPGx capability metadata is exposed through `genomi.list_resources`; there is\nno separate PGx capability-listing tool.\n\n## Answering\n\n- Mention Active Genome Index evidence only when it changes the medication\n  interpretation, limitation, blocker, or next action.\n- Keep PGx language informational and recommend clinical confirmation for\n  medication decisions.\n- Do not infer medication actionability from a genotype alone; connect sample\n  evidence to public drug-response evidence.\n- Treat user-provided diplotypes, phenotypes, activity scores, and outside\n  calls as supplied sample evidence that may need independent confirmation.\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### pharmacogenomics.check_pharmcat\n\nCheck local PharmCAT availability and version provenance for broad PGx calling from an AGI-derived PharmCAT input.\n\n**Use when**: The agent needs to know whether broad PharmCAT PGx calling is available before running pharmacogenomics.run_pharmcat.\n\n**Why necessary**: External PGx calls need availability and version provenance before they are trusted.\n\n**Result semantics**: Reports local PharmCAT executable\u002Fjar availability and version probe output for auditability before broad PGx calling.\n\n### pharmacogenomics.describe_gene_requirements\n\nReturn pharmacogene-specific sample evidence requirements for PharmCAT named allele matching, outside calls, CYP2D6 SV\u002FCNV handling, HLA typing, MT-RNR1, and G6PD chrX representation.\n\n**Use when**: The selected medication or source evidence names a pharmacogene and the agent needs to choose sample evidence, PharmCAT, outside-call, or targeted lookup handling.\n\n**Why necessary**: Complex pharmacogenes require special evidence handling that a simple rsID lookup cannot provide.\n\n**Result semantics**: Returns packaged source-backed pharmacogene sample-evidence requirements, candidate tools, and source references for the selected gene.\n\n### pharmacogenomics.fetch_clinpgx\n\nFetch traceable ClinPGx pharmacogenomic guideline, clinical annotation, and FDA label evidence for a selected drug, gene, or rsID; compact normalized records are returned by default.\n\n**Use when**: The question involves medication response, adverse effects, CPIC\u002FDPWG guidance, FDA drug-label PGx context, PharmGKB\u002FClinPGx annotations, or drug plus gene\u002FrsID interpretation.\n\n**Why necessary**: Guideline, clinical annotation, and label rows are separate public PGx evidence from sample genotype calls.\n\n**Result semantics**: Fetches public guideline, annotation, and label rows; raw API records are opt-in with include_raw_records; personal interpretation requires separate local genotype or diplotype evidence.\n\n### pharmacogenomics.fetch_fda_labels\n\nFetch targeted FDA pharmacogenomic biomarker-labeling and pharmacogenetic-association table rows from official FDA pages.\n\n**Use when**: The question needs FDA biomarker-labeling table context or FDA pharmacogenetic association table context for a selected drug or gene.\n\n**Why necessary**: FDA biomarker and pharmacogenetic-association tables are official label evidence with their own boundaries.\n\n**Result semantics**: Fetches official FDA table rows; keep biomarker-labeling rows separate from pharmacogenetic-association rows and combine with separate sample evidence for personal interpretation.\n\n### pharmacogenomics.fetch_pgxdb\n\nFetch targeted PGxDB pharmacogenomic evidence for a selected drug, ATC code, DrugBank ID, rsID, variant marker, or gene.\n\n**Use when**: The question involves medication response, adverse effects, pharmacogenomics, PharmGKB-style evidence, a drug plus rsID, or a drug plus gene.\n\n**Why necessary**: PGxDB association records provide targeted drug-variant evidence distinct from guideline recommendations.\n\n**Result semantics**: Fetches public PGxDB rows; sample interpretation requires separate local genotype evidence.\n\n### pharmacogenomics.import_pharmcat_artifacts\n\nImport existing PharmCAT report JSON, calls-only TSV, matcher JSON, phenotype JSON, missing-position VCF, or output directory without executing PharmCAT.\n\n**Use when**: The agent has existing PharmCAT artifacts and needs sample-side PGx evidence without running local PharmCAT.\n\n**Why necessary**: Existing PharmCAT outputs should be reused rather than rerun when sample-side PGx evidence already exists.\n\n**Result semantics**: Parses existing PharmCAT artifacts into `sample_pgx_matrix`, evidence summaries, and record_research_payloads used by pharmacogenomics.run_pharmcat, including interpretation readiness and missing-position review facts.\n\n### pharmacogenomics.preflight_pharmcat\n\nInspect selected Active Genome Index structure for broad PharmCAT PGx calling without running PharmCAT or writing artifacts.\n\n**Use when**: The agent needs read-only Active Genome Index structure, sample-column, genotype-field, or header evidence before broad PharmCAT PGx calling.\n\n**Why necessary**: Broad PharmCAT runs need input suitability checks before execution or artifact interpretation.\n\n**Result semantics**: Returns local AGI-derived preflight facts without exposing the raw AGI path; PharmCAT coverage sufficiency is judged from execution artifacts, especially missing PGx position review.\n\n### pharmacogenomics.prepare_outside_call_tsv\n\nPrepare a PharmCAT outside-call TSV from supported specialized caller output such as OptiType HLA calls, StellarPGx CYP2D6 summaries, or generic gene\u002Fdiplotype tables.\n\n**Use when**: The agent has specialized caller output for HLA-A, HLA-B, CYP2D6, MT-RNR1, or another pharmacogene and needs a PharmCAT outside-call TSV.\n\n**Why necessary**: Specialized callers for HLA, CYP2D6, and related genes need conversion before PharmCAT can consume them.\n\n**Result semantics**: Writes a canonical outside-call TSV under Genomi output storage or the requested output_file, validates it, and returns output.path for pharmacogenomics.run_pharmcat with parsed rows, invalid rows, warnings, caller format, and sample identity facts.\n\n### pharmacogenomics.review_medication\n\nReview medication pharmacogenomic evidence as medication-first rows combining ClinPGx guideline\u002Flabel context, FDA PGx table rows, PGxDB association evidence, Active Genome Index rsID lookup when selected, implemented marker-definition evidence when selected, evidence components, and target inventory.\n\n**Use when**: Combines public PGx evidence with selected active-genome-index or marker evidence for one medication.\n\n**Why necessary**: Medication-response questions need drug-specific PGx sources plus optional personal genotype evidence in one bounded review.\n\n**Not for**: diagnosing disease risk; it is medication-response evidence.\n\n**Example prompts**: Does my DNA say anything about clopidogrel?\n\n**Result semantics**: Returns `medication_review_matrix` where each row carries drug, gene, variant\u002Fdiplotype\u002Fphenotype, recommendation\u002Fsource text, evidence IDs, sample relevance, row readiness, and clinical boundary. Public-only by default unless active-genome-index context is selected.\n\n### pharmacogenomics.run_pharmcat\n\nRun a local PharmCAT installation from an approved Active Genome Index for broad PGx diplotype, phenotype, recommendation artifacts, and `sample_pgx_matrix` rows.\n\n**Use when**: Runs local PharmCAT from the selected Active Genome Index to generate broad PGx diplotype, phenotype, and recommendation artifacts.\n\n**Why necessary**: Broad PGx diplotype and recommendation artifacts require a specialized external caller.\n\n**Result semantics**: Runs local PharmCAT as sample-side PGx evidence generation; returns input preflight, runtime provenance, outside-call validation, `sample_pgx_matrix`, artifacts, warnings, interpretation readiness, and record_research_payloads for synthesis.\n\n### pharmacogenomics.validate_outside_call_tsv\n\nValidate PharmCAT outside-call TSV structure and summarize selected diplotype, phenotype, or activity-score evidence.\n\n**Use when**: The PGx sample evidence path already has a PharmCAT outside-call TSV for CYP2D6, HLA-A, HLA-B, MT-RNR1, or another specialized caller result before PharmCAT execution.\n\n**Why necessary**: Outside calls can override complex gene evidence, so their structure must be validated before use.\n\n**Result semantics**: Validates outside-call TSV shape, hides the local path, returns parsed rows, invalid rows, warnings, and explains that outside calls override PharmCAT VCF-derived calls for the same gene.\n",{"name":5,"tools":24,"mutating":42,"description":43},[25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41],"genomi.describe_context","pharmacogenomics.review_medication","pharmacogenomics.describe_gene_requirements","pharmacogenomics.preflight_pharmcat","pharmacogenomics.prepare_outside_call_tsv","pharmacogenomics.validate_outside_call_tsv","pharmacogenomics.import_pharmcat_artifacts","pharmacogenomics.check_pharmcat","pharmacogenomics.run_pharmcat","pharmacogenomics.fetch_clinpgx","pharmacogenomics.fetch_fda_labels","pharmacogenomics.fetch_pgxdb","variant.resolve","active_genome_index.classify_genotype_support","research.list_sources","research.record","research.query",true,"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.\n","master","1df4f5bfb635e2d08f93a1102b70b840fbe80d86","skills\u002Fpharmacogenomics",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":54,"prompt":64,"zipAvailable":42},[55,58,61],{"tool":56,"command":57},"npx","npx skills add exon-research\u002Fgenomi --skill pharmacogenomics",{"tool":59,"command":60},"bunx","bunx skills add exon-research\u002Fgenomi --skill pharmacogenomics",{"tool":62,"command":63},"pnpm","pnpm dlx skills add exon-research\u002Fgenomi --skill pharmacogenomics","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fexon-research\u002Fgenomi\u002Fblob\u002Fmaster\u002Fskills\u002Fpharmacogenomics\u002FSKILL.md",[],[67,74,81,88,95,102],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"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":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"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":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"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":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"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":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"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":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":19},"01M7543AQPW2ASRSPW179BSA01","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\u002Fexon-research\u002Fgenomi\u002Fblob\u002Fmaster\u002Fskills\u002Fnutrigenomics\u002FSKILL.md",[],[]]