菜单
Personalised nutrition report from consumer genetic data (23andMe, AncestryDNA, VCF) — interrogates nutritionally-relevant SNPs and generates actionable dietary guidance, all computed locally.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
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。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/ComeOnOliver/skillshub --skill nutrigx-advisor命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Review product and feature risk before an AI coding agent starts implementation.
Use Xquik for X data and confirmation-gated X actions: tweet search, user lookup, follower export, media download, monitors, webhooks, MCP, and SDK workflows.
Canton Network open-source ecosystem guide covering DAML SDK, Canton runtime, and Splice applications. Use when working with Canton Network, DAML smart contracts, or building decentralized applications.
基于 SOC 职业分类
正在显示 SKILL.md
| name | nutrigx-advisor |
| description | Personalised nutrition report from consumer genetic data (23andMe, AncestryDNA, VCF) — interrogates nutritionally-relevant SNPs and generates actionable dietary guidance, all computed locally. |
| version | 0.1.0 |
| author | David de Lorenzo |
| license | MIT |
| tags | ["nutrigenomics","nutrition","diet","genetics","23andme","ancestrydna","vcf"] |
| metadata | {"openclaw":{"requires":{"bins":["python3"],"env":[],"config":[]},"always":false,"emoji":"🥦","homepage":"https://github.com/ClawBio/ClawBio","os":["darwin","linux"],"install":[{"kind":"pip","package":"pandas numpy matplotlib seaborn","bins":[]},{"kind":"pip","package":"reportlab","bins":[]}],"trigger_keywords":["personalised nutrition","nutrigenomics","diet genetics","MTHFR","APOE","FTO","vitamin D","caffeine metabolism","lactose","omega-3","folate","what should I eat based on my DNA","vitamin absorption genetics","gluten"]}} |
Author: David de Lorenzo (ClawBio Community) Requires: Python 3.11+, pandas, numpy, matplotlib, seaborn, reportlab (optional)
The NutriGx Advisor generates a personalised nutrition report from consumer genetic data (23andMe, AncestryDNA raw files or VCF). It interrogates a curated set of nutritionally-relevant SNPs drawn from GWAS Catalog, ClinVar, and peer-reviewed nutrigenomics literature, then translates genotype calls into actionable dietary and supplementation guidance — all computed locally.
Key outputs
commands.sh, environment.yml, SHA-256 checksums)The Bio Orchestrator should route to this skill when the user says anything like:
.txt or .csv (23andMe), .csv (AncestryDNA), .vcf| Gene | SNP | Nutrient Impact | Evidence |
|---|---|---|---|
| FTO | rs9939609 | Energy balance, fat mass, carb sensitivity | Strong (GWAS) |
| PPARG | rs1801282 | Fat metabolism, insulin sensitivity | Moderate |
| APOA5 | rs662799 | Triglyceride response to dietary fat | Strong |
| TCF7L2 | rs7903146 | Carbohydrate metabolism, T2D risk | Strong |
| ADRB2 | rs1042713 | Fat oxidation, exercise × diet interaction | Moderate |
| Gene | SNP | Nutrient | Effect of risk allele |
|---|
| MTHFR | rs1801133 | Folate / B12 | ↓ 5-MTHF conversion (~70%) |
| MTHFR | rs1801131 | Folate / B12 | ↓ enzyme activity (~30%) |
| MTR | rs1805087 | B12 / homocysteine | ↑ homocysteine risk |
| BCMO1 | rs7501331 | Beta-carotene → Vitamin A | ↓ conversion (~50%) |
| BCMO1 | rs12934922 | Beta-carotene → Vitamin A | ↓ conversion (compound het) |
| VDR | rs2228570 | Vitamin D absorption | ↓ VDR function |
| VDR | rs731236 | Vitamin D | ↓ bone mineral density response |
| GC | rs4588 | Vitamin D binding | ↑ deficiency risk |
| SLC23A1 | rs33972313 | Vitamin C transport | ↓ renal reabsorption |
| ALPL | rs1256335 | Vitamin B6 | ↓ alkaline phosphatase activity |
| Gene | SNP | Nutrient | Effect |
|---|---|---|---|
| FADS1 | rs174546 | LC-PUFA synthesis | ↑/↓ EPA/DHA from ALA |
| FADS2 | rs1535 | LC-PUFA synthesis | Modulates omega-6:omega-3 ratio |
| ELOVL2 | rs953413 | DHA synthesis | ↓ elongation of EPA→DHA |
| APOE | rs429358 | Saturated fat response | ε4 → ↑ LDL-C on high SFA diet |
| APOE | rs7412 | Saturated fat response | Combined with rs429358 for ε typing |
| Gene | SNP | Compound | Effect |
|---|---|---|---|
| CYP1A2 | rs762551 | Caffeine | Slow/Fast metaboliser |
| AHR | rs4410790 | Caffeine | Modulates CYP1A2 induction |
| ADH1B | rs1229984 | Alcohol | Acetaldehyde accumulation risk |
| ALDH2 | rs671 | Alcohol | Asian flush / toxicity risk |
| Gene | SNP | Sensitivity | Effect |
|---|---|---|---|
| MCM6 | rs4988235 | Lactose intolerance | Non-persistence of lactase |
| HLA-DQ2 | Proxy SNPs | Coeliac / gluten | HLA-DQA1/DQB1 risk haplotypes |
| Gene | SNP | Pathway | Effect |
|---|---|---|---|
| SOD2 | rs4880 | Manganese SOD | ↓ mitochondrial antioxidant |
| GPX1 | rs1050450 | Selenium / GSH-Px | ↓ glutathione peroxidase |
| GSTT1 | Deletion | Glutathione-S-trans | Null genotype → ↑ oxidative risk |
| NQO1 | rs1800566 | Coenzyme Q10 | ↓ CoQ10 regeneration |
| COMT | rs4680 | Catechol / B vitamins | Met/Val → methylation load |
parse_input.py)Accepts:
.txt or .csv (tab-separated: rsid, chromosome, position, genotype).csvAuto-detects format from header lines. Normalises alleles to forward strand using a hard-coded reference table (avoids requiring external databases).
extract_genotypes.py)For each SNP in the panel:
"AT", "TT", "AA")"NOT_TESTED" if absent (common for chip-to-chip variation)score_variants.py)Each SNP is scored on a 0 / 0.5 / 1.0 scale:
0.0 — homozygous reference (lowest risk)0.5 — heterozygous1.0 — homozygous risk alleleComposite Nutrient Risk Scores (0–10) are computed per nutrient domain by summing weighted SNP scores. Weights are derived from reported effect sizes (beta coefficients or OR) in the primary literature.
Risk categories:
Important caveat: These are polygenic risk indicators based on common variants. They are not diagnostic. Rare pathogenic variants (e.g. MTHFR compound heterozygosity with high homocysteine) require clinical confirmation.
generate_report.py)Outputs a structured Markdown report with:
repro_bundle.py)Exports to the output directory (not committed to the repo):
commands.sh — full CLI to reproduce analysisenvironment.yml — pinned conda environmentchecksums.txt — SHA-256 checksums of input and output filesprovenance.json — timestamp and ClawBio version tag# From 23andMe raw data
openclaw "Generate my personalised nutrition report from genome.csv"
# From VCF
openclaw "Run NutriGx analysis on variants.vcf and flag any folate pathway risks"
# Targeted query
openclaw "What does my APOE status mean for my saturated fat intake?"
# Generate a random demo patient and run the report
python examples/generate_patient.py --run
skills/nutrigx-advisor/
├── SKILL.md ← this file (agent instructions)
├── nutrigx_advisor.py ← main entry point
├── parse_input.py ← multi-format parser
├── extract_genotypes.py ← SNP lookup engine
├── score_variants.py ← risk scoring algorithm
├── generate_report.py ← Markdown + figures
├── repro_bundle.py ← reproducibility export
├── .gitignore
├── data/
│ └── snp_panel.json ← curated SNP definitions
├── tests/
│ ├── synthetic_patient.csv ← fixed 23andMe-format test data (for pytest)
│ └── test_nutrigx.py ← pytest suite
└── examples/
├── generate_patient.py ← random patient generator (demo use)
├── data/ ← generated patient files land here (gitignored)
└── output/
├── nutrigx_report.md ← pre-rendered demo report
├── nutrigx_radar.png ← demo radar chart (nutrient risk profile)
└── nutrigx_heatmap.png ← demo gene × nutrient heatmap
Note: Runtime output directories and randomly generated patient files are excluded from version control via
.gitignore. Only the pre-rendered demo report inexamples/output/is committed.
All computation runs locally. No genetic data is transmitted. Input files are read-only; no raw genotype data appears in any output file (reports contain only gene names, SNP IDs, and risk categories).
Key literature underpinning the SNP panel and scoring algorithm:
The SNP panel (data/snp_panel.json) is maintained by the skill author.
To suggest additions or corrections, contact David de Lorenzo directly via
GitHub (@drdaviddelorenzo) or open
an issue tagging him in the main ClawBio repository.