菜单
Run analysis scripts: PRS, enrichment, vault audit, PubMed monitoring, consistency checks. Triggers on: /genome-analytics, "run PRS", "audit vault", "check PubMed", "run enrichment", "check consistency", "analyze pathway".
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Universal genome data import supporting 23andMe v4/v5, AncestryDNA, MyHeritage, Nebula, and generic VCF. Also handles imputation prep and post-imputation import. Triggers on: /genome-import, "import my DNA data", "add raw file", "prepare for imputation", "import imputed data".
Goal-driven onboarding for new genome vault users. Triggers on: /genome-onboard, "set up my vault", "I just imported my data", "help me get started with my genome". Two modes: --quick (4 questions, fast vault bootstrap) or --full (22-question interview with validated psychological instruments, generates Profile Card + Action Plan).
Daily health tracking with genetic context: supplements, medications, symptoms, interventions, metrics. Use this skill whenever the user mentions taking supplements, logging symptoms, tracking health, reporting how they feel, or asks about their daily routine. Also triggers on: /genome-log, /log, "daily check-in", "track today", "I took my supplements", "feeling anxious", "my stomach hurts", "forgot my B12", "log symptoms", "how am I doing", "what did I take today". Even casual health mentions like "my nose is stuffed" or "had a rough night" should trigger this skill to offer logging.
Query Obsidian vault frontmatter with SQL-like syntax. Filter, sort, group, and aggregate notes by any frontmatter field. Replaces Dataview for CLI use. Triggers on: /genome-query, "query vault", "find notes", "list genes", "show protocols", "vault stats", "vault schema", "filter by".
Multi-agent validation pipeline for fact-checking claims, verifying evidence tiers, and ensuring prescriber document accuracy. Uses Codex CLI, NotebookLM, PubMed subagents, and Tavily search. Supports: audit (full vault), gene SYMBOL (single gene fact-check), protocol NAME (protocol/report fact-check). Triggers on: /genome-validate, "validate this note", "fact-check", "cross-check claims", "verify evidence", "audit this report", "fact-check gene X", "check protocol X".
Create gene, system, or phenotype notes from SQLite genotype data and templates. Triggers on: /new-gene SYMBOL, /new-system NAME, "add gene X", "create system note", "create phenotype note for X".
| name | genome-analytics |
| description | Run analysis scripts: PRS, enrichment, vault audit, PubMed monitoring, consistency checks. Triggers on: /genome-analytics, "run PRS", "audit vault", "check PubMed", "run enrichment", "check consistency", "analyze pathway". |
Run analysis and quality assurance scripts on the genome vault.
data/genome.dbscripts/analytics/data/output/python3 scripts/analytics/prs_calculator.py --details
Calculates Polygenic Risk Scores for: GAD/Anxiety, Depression, BMI, CAD, T2D, Ankylosing Spondylitis.
Uses scripts/data/prs_snp_weights.json for effect sizes.
python3 scripts/analytics/snp_enrich.py --rsid rs4680
python3 scripts/analytics/snp_enrich.py --gene CYP2D6
Queries SNPedia, ClinVar, MyVariant, gnomAD. Respects rate limits from config.
python3 scripts/analytics/gap_audit.py
python3 scripts/analytics/consistency_checker.py
python3 scripts/analytics/vault_graph_analysis.py
python3 scripts/analytics/evidence_tier_analyzer.py
python3 scripts/analytics/claim_density.py
python3 scripts/analytics/intervention_matrix.py
Checks: schema compliance, link integrity, evidence quality, staleness, claim density.
python3 scripts/analytics/pubmed_monitor.py --months 6
Scans PubMed for new publications on genes in the vault.
python3 scripts/analytics/biomarker_analyzer.py
Trend analysis across lab results, comparison against genetic predictions.
ld_analysis.py — Linkage disequilibrium between vault variantspathway_enrichment.py — KEGG/Reactome pathway analysiseffect_size_aggregator.py — Audit effect sizes vs published dataprediction_tracker.py — Track genetic prediction accuracydata/output/)