genomi

Use this skill for genetics, genome source, variant, gene, phenotype, disease, screen, pharmacogenomics, and Genomi install/setup maintenance questions.

Build and inspect ClinVar exact-match evidence and candidate inventories. Use for clinical labels, VUS/conflict, carrier context, and drug-response rows.

Activate this skill for "/genomi decode", "decode my genome", "decode my DNA", "show me the dashboard", "the Genomi dashboard", "one-shot rundown", or any all-at-once request that asks Genomi to compose every capability's findings into a single artifact. This is the whole-genome dashboard kicker — it sweeps every relevant Genomi capability in one shot, not a per-target lookup. Composes evidence from every relevant Genomi capability into a single self-contained Genomi Dashboard.html and returns localhost serve metadata. Active genome required.

Answer drug-response, medication, PharmGKB-style, PGxDB, ATC, DrugBank, gene-drug, and variant-drug questions using public PGx evidence plus local sample genotype support when an Active Genome Index is selected.

Plan rare disease, hereditary disease, cancer risk, carrier-relevance, and observed-condition source investigation from public targets or selected active genome evidence.

Answer specific rsID, allele, gene, region, genotype, and absence/callability questions using explicit session context or public evidence.

Register, parse, and digitize private genome source files into a local Active Genome Index and supporting evidence stores. Use when the session explicitly supplies a VCF/gVCF, BAM, genome.computer .genome/1.0 bundle, 23andMe raw genotype export, AncestryDNA raw genotype export, MyHeritage raw genotype export, FamilyTreeDNA Family Finder export, Living DNA autosomal export, supported source zip/tar, or known Active Genome Index.

Use local ancestry reference-panel tools for 1000 Genomes GRCh37/GRCh38 PCA projection, marker overlap QC, and qualitative reference-neighbor context.

Causal drug-target and mechanism gene prioritization from public source records, drugs, drug classes, mechanisms, and candidate gene lists.

Candidate gene evidence from perturbation, dependency, resistance, sensitivity, viability, or assay-context records.

Default entry for natural-language DNA questions. The host agent resolves intent, reads focused skills, calls narrow evidence tools, and adapts after inspecting tool output.

Fetch reusable public population allele frequencies from gnomAD for a specific variant. Use when the user asks about allele frequency, MAF, population stratification, gnomAD numbers, or rarity of a specific allele.

Compare candidate rsIDs against GWAS Catalog phenotype associations. Use association evidence with source and ancestry limitations.

Maintain agent-authored investigation memory over Genomi evidence links, reviewed source findings, decisions, contradictions, and unresolved questions.

Curated single-marker evidence for declared nutrient-metabolism, food-tolerance, and taste-perception domains. Refuses diet prescriptions, supplement dosing, weight-loss prediction, methylation-cycle prescriptions, microbiome-mediated effects, and other out-of-scope nutrigenomic claims.

Journal sub-skill for focused public/source evidence review and reviewed finding write-back before interpretation or answer synthesis.

Retrieve canonical pathway members, cell-type marker records, and genomic interval feature overlaps from declared analytical sources.

Deterministic sequence utilities for translation, ORFs, restriction sites, Kozak context, primer checks, and local FASTA record matching.

Apply published polygenic scores from PGS Catalog to approved local personal DNA and return raw weighted score plus overlap QC.