{ "schemaVersion": "1.0", "item": { "slug": "nutrigx-advisor", "name": "NutriGx Advisor", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/manuelcorpas/nutrigx-advisor", "canonicalUrl": "https://clawhub.ai/manuelcorpas/nutrigx-advisor", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/nutrigx-advisor", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=nutrigx-advisor", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "data/snp_panel.json", "examples/generate_patient.py", "examples/output/nutrigx_report.md", "extract_genotypes.py", "generate_report.py" ], "primaryDoc": "SKILL.md", "quickSetup": [ "Download the package from Yavira.", "Extract the archive and review SKILL.md first.", "Import or place the package into your OpenClaw setup." ], "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run." } ] }, "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-30T16:55:25.780Z", "expiresAt": "2026-05-07T16:55:25.780Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null }, "scope": "source", "summary": "Source download looks usable.", "detail": "Yavira can redirect you to the upstream package for this source.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/nutrigx-advisor" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] }, "downloadPageUrl": "https://openagent3.xyz/downloads/nutrigx-advisor", "agentPageUrl": "https://openagent3.xyz/skills/nutrigx-advisor/agent", "manifestUrl": "https://openagent3.xyz/skills/nutrigx-advisor/agent.json", "briefUrl": "https://openagent3.xyz/skills/nutrigx-advisor/agent.md" }, "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "NutriGx Advisor — Personalised Nutrition from Genetic Data", "body": "Skill ID: nutrigx-advisor\nVersion: 0.1.0\nStatus: MVP\nAuthor: David de Lorenzo (ClawBio Community)\nRequires: Python 3.11+, pandas, numpy, matplotlib, seaborn, reportlab (optional)" }, { "title": "What This Skill Does", "body": "The NutriGx Advisor generates a personalised nutrition report from consumer\ngenetic data (23andMe, AncestryDNA raw files or VCF). It interrogates a curated\nset of nutritionally-relevant SNPs drawn from GWAS Catalog, ClinVar, and\npeer-reviewed nutrigenomics literature, then translates genotype calls into\nactionable dietary and supplementation guidance — all computed locally.\n\nKey outputs\n\nMarkdown nutrition report with risk scores and recommendations\nRadar chart of nutrient risk profile\nGene × nutrient heatmap\nReproducibility bundle (commands.sh, environment.yml, SHA-256 checksums)" }, { "title": "Trigger Phrases", "body": "The Bio Orchestrator should route to this skill when the user says anything like:\n\n\"personalised nutrition\", \"nutrigenomics\", \"diet genetics\"\n\"what should I eat based on my DNA\"\n\"nutrient metabolism\", \"vitamin absorption genetics\"\n\"MTHFR\", \"APOE\", \"FTO\", \"BCMO1\", \"VDR\", \"FADS1/2\"\n\"folate\", \"omega-3\", \"vitamin D\", \"caffeine metabolism\", \"lactose\", \"gluten\"\nInput files: .txt or .csv (23andMe), .csv (AncestryDNA), .vcf" }, { "title": "Macronutrient Metabolism", "body": "GeneSNPNutrient ImpactEvidenceFTOrs9939609Energy balance, fat mass, carb sensitivityStrong (GWAS)PPARGrs1801282Fat metabolism, insulin sensitivityModerateAPOA5rs662799Triglyceride response to dietary fatStrongTCF7L2rs7903146Carbohydrate metabolism, T2D riskStrongADRB2rs1042713Fat oxidation, exercise × diet interactionModerate" }, { "title": "Micronutrient Metabolism", "body": "GeneSNPNutrientEffect of risk alleleMTHFRrs1801133Folate / B12↓ 5-MTHF conversion (~70%)MTHFRrs1801131Folate / B12↓ enzyme activity (~30%)MTRrs1805087B12 / homocysteine↑ homocysteine riskBCMO1rs7501331Beta-carotene → Vitamin A↓ conversion (~50%)BCMO1rs12934922Beta-carotene → Vitamin A↓ conversion (compound het)VDRrs2228570Vitamin D absorption↓ VDR functionVDRrs731236Vitamin D↓ bone mineral density responseGCrs4588Vitamin D binding↑ deficiency riskSLC23A1rs33972313Vitamin C transport↓ renal reabsorptionALPLrs1256335Vitamin B6↓ alkaline phosphatase activity" }, { "title": "Omega-3 / Fatty Acid Metabolism", "body": "GeneSNPNutrientEffectFADS1rs174546LC-PUFA synthesis↑/↓ EPA/DHA from ALAFADS2rs1535LC-PUFA synthesisModulates omega-6:omega-3 ratioELOVL2rs953413DHA synthesis↓ elongation of EPA→DHAAPOErs429358Saturated fat responseε4 → ↑ LDL-C on high SFA dietAPOErs7412Saturated fat responseCombined with rs429358 for ε typing" }, { "title": "Caffeine & Alcohol", "body": "GeneSNPCompoundEffectCYP1A2rs762551CaffeineSlow/Fast metaboliserAHRrs4410790CaffeineModulates CYP1A2 inductionADH1Brs1229984AlcoholAcetaldehyde accumulation riskALDH2rs671AlcoholAsian flush / toxicity risk" }, { "title": "Food Sensitivities", "body": "GeneSNPSensitivityEffectMCM6rs4988235Lactose intoleranceNon-persistence of lactaseHLA-DQ2Proxy SNPsCoeliac / glutenHLA-DQA1/DQB1 risk haplotypes" }, { "title": "Antioxidant & Detoxification", "body": "GeneSNPPathwayEffectSOD2rs4880Manganese SOD↓ mitochondrial antioxidantGPX1rs1050450Selenium / GSH-Px↓ glutathione peroxidaseGSTT1DeletionGlutathione-S-transNull genotype → ↑ oxidative riskNQO1rs1800566Coenzyme Q10↓ CoQ10 regenerationCOMTrs4680Catechol / B vitaminsMet/Val → methylation load" }, { "title": "1. Input Parsing (parse_input.py)", "body": "Accepts:\n\n23andMe .txt or .csv (tab-separated: rsid, chromosome, position, genotype)\nAncestryDNA .csv\nStandard VCF (extracts GT field)\n\nAuto-detects format from header lines. Normalises alleles to forward strand using\na hard-coded reference table (avoids requiring external databases)." }, { "title": "2. Genotype Extraction (extract_genotypes.py)", "body": "For each SNP in the panel:\n\nLook up rsid in parsed data\nReturn genotype string (e.g. \"AT\", \"TT\", \"AA\")\nFlag as \"NOT_TESTED\" if absent (common for chip-to-chip variation)" }, { "title": "3. Risk Scoring (score_variants.py)", "body": "Each SNP is scored on a 0 / 0.5 / 1.0 scale:\n\n0.0 — homozygous reference (lowest risk)\n0.5 — heterozygous\n1.0 — homozygous risk allele\n\nComposite Nutrient Risk Scores (0–10) are computed per nutrient domain by\nsumming weighted SNP scores. Weights are derived from reported effect sizes\n(beta coefficients or OR) in the primary literature.\n\nRisk categories:\n\n0–3: Low risk — standard dietary advice applies\n3–6: Moderate risk — dietary optimisation recommended\n6–10: Elevated risk — consider testing and targeted supplementation\n\nImportant caveat: These are polygenic risk indicators based on common\nvariants. They are not diagnostic. Rare pathogenic variants (e.g. MTHFR\ncompound heterozygosity with high homocysteine) require clinical confirmation." }, { "title": "4. Report Generation (generate_report.py)", "body": "Outputs a structured Markdown report with:\n\nExecutive summary (top 3 personalised findings)\nPer-nutrient sections: genotype table → interpretation → recommendation\nRadar chart (matplotlib) of nutrient risk scores\nGene × nutrient heatmap (seaborn)\nSupplement interactions table\nDisclaimer section\nReproducibility block" }, { "title": "5. Reproducibility Bundle (repro_bundle.py)", "body": "Exports to the output directory (not committed to the repo):\n\ncommands.sh — full CLI to reproduce analysis\nenvironment.yml — pinned conda environment\nchecksums.txt — SHA-256 checksums of input and output files\nprovenance.json — timestamp and ClawBio version tag" }, { "title": "Usage", "body": "# From 23andMe raw data\nopenclaw \"Generate my personalised nutrition report from genome.csv\"\n\n# From VCF\nopenclaw \"Run NutriGx analysis on variants.vcf and flag any folate pathway risks\"\n\n# Targeted query\nopenclaw \"What does my APOE status mean for my saturated fat intake?\"\n\n# Generate a random demo patient and run the report\npython examples/generate_patient.py --run" }, { "title": "File Structure", "body": "skills/nutrigx-advisor/\n├── SKILL.md ← this file (agent instructions)\n├── nutrigx_advisor.py ← main entry point\n├── parse_input.py ← multi-format parser\n├── extract_genotypes.py ← SNP lookup engine\n├── score_variants.py ← risk scoring algorithm\n├── generate_report.py ← Markdown + figures\n├── repro_bundle.py ← reproducibility export\n├── .gitignore\n├── data/\n│ └── snp_panel.json ← curated SNP definitions\n├── tests/\n│ ├── synthetic_patient.csv ← fixed 23andMe-format test data (for pytest)\n│ └── test_nutrigx.py ← pytest suite\n└── examples/\n ├── generate_patient.py ← random patient generator (demo use)\n ├── data/ ← generated patient files land here (gitignored)\n └── output/\n ├── nutrigx_report.md ← pre-rendered demo report\n ├── nutrigx_radar.png ← demo radar chart (nutrient risk profile)\n └── nutrigx_heatmap.png ← demo gene × nutrient heatmap\n\nNote: Runtime output directories and randomly generated patient files are\nexcluded from version control via .gitignore. Only the pre-rendered demo\nreport in examples/output/ is committed." }, { "title": "Privacy", "body": "All computation runs locally. No genetic data is transmitted. Input files are\nread-only; no raw genotype data appears in any output file (reports contain only\ngene names, SNP IDs, and risk categories)." }, { "title": "Limitations & Disclaimer", "body": "Not a medical device. This skill provides educational, research-oriented\nnutrigenomics analysis. It does not constitute medical advice.\nCommon variants only. The panel covers SNPs with MAF > 1% in at least one\nmajor population. Rare pathogenic variants are out of scope.\nPopulation context. Effect sizes are predominantly derived from European\nGWAS cohorts. Risk estimates may not generalise equally across all ancestries.\nGene–environment interaction. Genetic risk scores interact with baseline\ndiet, lifestyle, microbiome, and epigenetic state. A \"high risk\" score does not\nmean a nutrient deficiency is present — it means the individual may benefit from\nmonitoring.\nSimpson's Paradox note. Population-level associations used to derive weights\nmay not reflect individual trajectories (see Corpas 2025, Nutrigenomics and\nthe Ecological Fallacy)." }, { "title": "Roadmap", "body": "v0.2: Microbiome × genotype interaction module (16S rRNA input)\n v0.3: Longitudinal tracking — compare reports across time\n v0.4: HLA typing for immune-mediated food reactions (coeliac, gluten sensitivity)\n v0.5: Integration with NeoTree neonatal data for maternal nutrition risk scoring\n v1.0: Multi-omics integration (metabolomics + genomics + dietary recall)" }, { "title": "References", "body": "Key literature underpinning the SNP panel and scoring algorithm:\n\nCorbin JM & Ruczinski I (2023). Nutrigenomics: current state and future directions. Annu Rev Nutr.\nFenech M et al. (2011). Nutrigenetics and nutrigenomics: viewpoints on the current status. J Nutrigenet Nutrigenomics.\nStover PJ (2006). Influence of human genetic variation on nutritional requirements. Am J Clin Nutr.\nPhillips CM (2013). Nutrigenetics and metabolic disease: current status and implications for personalised nutrition. Nutrients.\nMinihane AM et al. (2015). APOE genotype, cardiovascular risk and responsiveness to dietary fat manipulation. Proc Nutr Soc.\nFrayling TM et al. (2007). A common variant in the FTO gene is associated with body mass index. Science.\nPare G et al. (2010). MTHFR variants and cardiovascular risk. Hum Genet.\nLecerf JM & de Lorgeril M (2011). Dietary cholesterol: from physiology to cardiovascular risk. Br J Nutr.\nTanaka T et al. (2009). Genome-wide association study of plasma polyunsaturated fatty acids in the InCHIANTI Study. PLoS Genet (FADS1/2).\nCornelis MC et al. (2006). Coffee, CYP1A2 genotype, and risk of myocardial infarction. JAMA." }, { "title": "Contributing", "body": "The SNP panel (data/snp_panel.json) is maintained by the skill author.\nTo suggest additions or corrections, contact David de Lorenzo directly via\nGitHub (@drdaviddelorenzo) or open\nan issue tagging him in the main ClawBio repository." } ], "body": "NutriGx Advisor — Personalised Nutrition from Genetic Data\n\nSkill ID: nutrigx-advisor\nVersion: 0.1.0\nStatus: MVP\nAuthor: David de Lorenzo (ClawBio Community) Requires: Python 3.11+, pandas, numpy, matplotlib, seaborn, reportlab (optional)\n\nWhat This Skill Does\n\nThe 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.\n\nKey outputs\n\nMarkdown nutrition report with risk scores and recommendations\nRadar chart of nutrient risk profile\nGene × nutrient heatmap\nReproducibility bundle (commands.sh, environment.yml, SHA-256 checksums)\nTrigger Phrases\n\nThe Bio Orchestrator should route to this skill when the user says anything like:\n\n\"personalised nutrition\", \"nutrigenomics\", \"diet genetics\"\n\"what should I eat based on my DNA\"\n\"nutrient metabolism\", \"vitamin absorption genetics\"\n\"MTHFR\", \"APOE\", \"FTO\", \"BCMO1\", \"VDR\", \"FADS1/2\"\n\"folate\", \"omega-3\", \"vitamin D\", \"caffeine metabolism\", \"lactose\", \"gluten\"\nInput files: .txt or .csv (23andMe), .csv (AncestryDNA), .vcf\nCurated SNP Panel\nMacronutrient Metabolism\nGene\tSNP\tNutrient Impact\tEvidence\nFTO\trs9939609\tEnergy balance, fat mass, carb sensitivity\tStrong (GWAS)\nPPARG\trs1801282\tFat metabolism, insulin sensitivity\tModerate\nAPOA5\trs662799\tTriglyceride response to dietary fat\tStrong\nTCF7L2\trs7903146\tCarbohydrate metabolism, T2D risk\tStrong\nADRB2\trs1042713\tFat oxidation, exercise × diet interaction\tModerate\nMicronutrient Metabolism\nGene\tSNP\tNutrient\tEffect of risk allele\nMTHFR\trs1801133\tFolate / B12\t↓ 5-MTHF conversion (~70%)\nMTHFR\trs1801131\tFolate / B12\t↓ enzyme activity (~30%)\nMTR\trs1805087\tB12 / homocysteine\t↑ homocysteine risk\nBCMO1\trs7501331\tBeta-carotene → Vitamin A\t↓ conversion (~50%)\nBCMO1\trs12934922\tBeta-carotene → Vitamin A\t↓ conversion (compound het)\nVDR\trs2228570\tVitamin D absorption\t↓ VDR function\nVDR\trs731236\tVitamin D\t↓ bone mineral density response\nGC\trs4588\tVitamin D binding\t↑ deficiency risk\nSLC23A1\trs33972313\tVitamin C transport\t↓ renal reabsorption\nALPL\trs1256335\tVitamin B6\t↓ alkaline phosphatase activity\nOmega-3 / Fatty Acid Metabolism\nGene\tSNP\tNutrient\tEffect\nFADS1\trs174546\tLC-PUFA synthesis\t↑/↓ EPA/DHA from ALA\nFADS2\trs1535\tLC-PUFA synthesis\tModulates omega-6:omega-3 ratio\nELOVL2\trs953413\tDHA synthesis\t↓ elongation of EPA→DHA\nAPOE\trs429358\tSaturated fat response\tε4 → ↑ LDL-C on high SFA diet\nAPOE\trs7412\tSaturated fat response\tCombined with rs429358 for ε typing\nCaffeine & Alcohol\nGene\tSNP\tCompound\tEffect\nCYP1A2\trs762551\tCaffeine\tSlow/Fast metaboliser\nAHR\trs4410790\tCaffeine\tModulates CYP1A2 induction\nADH1B\trs1229984\tAlcohol\tAcetaldehyde accumulation risk\nALDH2\trs671\tAlcohol\tAsian flush / toxicity risk\nFood Sensitivities\nGene\tSNP\tSensitivity\tEffect\nMCM6\trs4988235\tLactose intolerance\tNon-persistence of lactase\nHLA-DQ2\tProxy SNPs\tCoeliac / gluten\tHLA-DQA1/DQB1 risk haplotypes\nAntioxidant & Detoxification\nGene\tSNP\tPathway\tEffect\nSOD2\trs4880\tManganese SOD\t↓ mitochondrial antioxidant\nGPX1\trs1050450\tSelenium / GSH-Px\t↓ glutathione peroxidase\nGSTT1\tDeletion\tGlutathione-S-trans\tNull genotype → ↑ oxidative risk\nNQO1\trs1800566\tCoenzyme Q10\t↓ CoQ10 regeneration\nCOMT\trs4680\tCatechol / B vitamins\tMet/Val → methylation load\nAlgorithm\n1. Input Parsing (parse_input.py)\n\nAccepts:\n\n23andMe .txt or .csv (tab-separated: rsid, chromosome, position, genotype)\nAncestryDNA .csv\nStandard VCF (extracts GT field)\n\nAuto-detects format from header lines. Normalises alleles to forward strand using a hard-coded reference table (avoids requiring external databases).\n\n2. Genotype Extraction (extract_genotypes.py)\n\nFor each SNP in the panel:\n\nLook up rsid in parsed data\nReturn genotype string (e.g. \"AT\", \"TT\", \"AA\")\nFlag as \"NOT_TESTED\" if absent (common for chip-to-chip variation)\n3. Risk Scoring (score_variants.py)\n\nEach SNP is scored on a 0 / 0.5 / 1.0 scale:\n\n0.0 — homozygous reference (lowest risk)\n0.5 — heterozygous\n1.0 — homozygous risk allele\n\nComposite 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.\n\nRisk categories:\n\n0–3: Low risk — standard dietary advice applies\n3–6: Moderate risk — dietary optimisation recommended\n6–10: Elevated risk — consider testing and targeted supplementation\n\nImportant 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.\n\n4. Report Generation (generate_report.py)\n\nOutputs a structured Markdown report with:\n\nExecutive summary (top 3 personalised findings)\nPer-nutrient sections: genotype table → interpretation → recommendation\nRadar chart (matplotlib) of nutrient risk scores\nGene × nutrient heatmap (seaborn)\nSupplement interactions table\nDisclaimer section\nReproducibility block\n5. Reproducibility Bundle (repro_bundle.py)\n\nExports to the output directory (not committed to the repo):\n\ncommands.sh — full CLI to reproduce analysis\nenvironment.yml — pinned conda environment\nchecksums.txt — SHA-256 checksums of input and output files\nprovenance.json — timestamp and ClawBio version tag\nUsage\n# From 23andMe raw data\nopenclaw \"Generate my personalised nutrition report from genome.csv\"\n\n# From VCF\nopenclaw \"Run NutriGx analysis on variants.vcf and flag any folate pathway risks\"\n\n# Targeted query\nopenclaw \"What does my APOE status mean for my saturated fat intake?\"\n\n# Generate a random demo patient and run the report\npython examples/generate_patient.py --run\n\nFile Structure\nskills/nutrigx-advisor/\n├── SKILL.md ← this file (agent instructions)\n├── nutrigx_advisor.py ← main entry point\n├── parse_input.py ← multi-format parser\n├── extract_genotypes.py ← SNP lookup engine\n├── score_variants.py ← risk scoring algorithm\n├── generate_report.py ← Markdown + figures\n├── repro_bundle.py ← reproducibility export\n├── .gitignore\n├── data/\n│ └── snp_panel.json ← curated SNP definitions\n├── tests/\n│ ├── synthetic_patient.csv ← fixed 23andMe-format test data (for pytest)\n│ └── test_nutrigx.py ← pytest suite\n└── examples/\n ├── generate_patient.py ← random patient generator (demo use)\n ├── data/ ← generated patient files land here (gitignored)\n └── output/\n ├── nutrigx_report.md ← pre-rendered demo report\n ├── nutrigx_radar.png ← demo radar chart (nutrient risk profile)\n └── nutrigx_heatmap.png ← demo gene × nutrient heatmap\n\n\nNote: Runtime output directories and randomly generated patient files are excluded from version control via .gitignore. Only the pre-rendered demo report in examples/output/ is committed.\n\nPrivacy\n\nAll 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).\n\nLimitations & Disclaimer\nNot a medical device. This skill provides educational, research-oriented nutrigenomics analysis. It does not constitute medical advice.\nCommon variants only. The panel covers SNPs with MAF > 1% in at least one major population. Rare pathogenic variants are out of scope.\nPopulation context. Effect sizes are predominantly derived from European GWAS cohorts. Risk estimates may not generalise equally across all ancestries.\nGene–environment interaction. Genetic risk scores interact with baseline diet, lifestyle, microbiome, and epigenetic state. A \"high risk\" score does not mean a nutrient deficiency is present — it means the individual may benefit from monitoring.\nSimpson's Paradox note. Population-level associations used to derive weights may not reflect individual trajectories (see Corpas 2025, Nutrigenomics and the Ecological Fallacy).\nRoadmap\n v0.2: Microbiome × genotype interaction module (16S rRNA input)\n v0.3: Longitudinal tracking — compare reports across time\n v0.4: HLA typing for immune-mediated food reactions (coeliac, gluten sensitivity)\n v0.5: Integration with NeoTree neonatal data for maternal nutrition risk scoring\n v1.0: Multi-omics integration (metabolomics + genomics + dietary recall)\nReferences\n\nKey literature underpinning the SNP panel and scoring algorithm:\n\nCorbin JM & Ruczinski I (2023). Nutrigenomics: current state and future directions. Annu Rev Nutr.\nFenech M et al. (2011). Nutrigenetics and nutrigenomics: viewpoints on the current status. J Nutrigenet Nutrigenomics.\nStover PJ (2006). Influence of human genetic variation on nutritional requirements. Am J Clin Nutr.\nPhillips CM (2013). Nutrigenetics and metabolic disease: current status and implications for personalised nutrition. Nutrients.\nMinihane AM et al. (2015). APOE genotype, cardiovascular risk and responsiveness to dietary fat manipulation. Proc Nutr Soc.\nFrayling TM et al. (2007). A common variant in the FTO gene is associated with body mass index. Science.\nPare G et al. (2010). MTHFR variants and cardiovascular risk. Hum Genet.\nLecerf JM & de Lorgeril M (2011). Dietary cholesterol: from physiology to cardiovascular risk. Br J Nutr.\nTanaka T et al. (2009). Genome-wide association study of plasma polyunsaturated fatty acids in the InCHIANTI Study. PLoS Genet (FADS1/2).\nCornelis MC et al. (2006). Coffee, CYP1A2 genotype, and risk of myocardial infarction. JAMA.\nContributing\n\nThe 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." }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/manuelcorpas/nutrigx-advisor", "publisherUrl": "https://clawhub.ai/manuelcorpas/nutrigx-advisor", "owner": "manuelcorpas", "version": "0.2.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/nutrigx-advisor", "downloadUrl": "https://openagent3.xyz/downloads/nutrigx-advisor", "agentUrl": "https://openagent3.xyz/skills/nutrigx-advisor/agent", "manifestUrl": "https://openagent3.xyz/skills/nutrigx-advisor/agent.json", "briefUrl": "https://openagent3.xyz/skills/nutrigx-advisor/agent.md" } }