{
  "schemaVersion": "1.0",
  "item": {
    "slug": "genomics",
    "name": "Genomics",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/ivangdavila/genomics",
    "canonicalUrl": "https://clawhub.ai/ivangdavila/genomics",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/genomics",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=genomics",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "memory-template.md",
      "setup.md"
    ],
    "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/genomics"
    },
    "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/genomics",
    "agentPageUrl": "https://openagent3.xyz/skills/genomics/agent",
    "manifestUrl": "https://openagent3.xyz/skills/genomics/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/genomics/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": "Setup",
        "body": "On first use, read setup.md for integration guidelines. Ask user consent before creating ~/genomics/ workspace."
      },
      {
        "title": "When to Use",
        "body": "User has processed genomic data (VCF files) and needs clinical interpretation. Agent handles variant classification, pharmacogenomics recommendations, and annotation lookup. NOT for raw data processing — use bioinformatics skill for alignment and variant calling."
      },
      {
        "title": "Architecture",
        "body": "Memory lives in ~/genomics/. See memory-template.md for structure.\n\n~/genomics/\n├── memory.md           # Context + preferences + interpretation history\n└── cases/              # Active interpretation cases"
      },
      {
        "title": "Quick Reference",
        "body": "TopicFileSetup processsetup.mdMemory templatememory-template.md"
      },
      {
        "title": "1. Classify Variants Using ACMG Guidelines",
        "body": "Every variant needs systematic classification:\n\nCategoryCriteriaPathogenicPVS1, PS1-4, PM1-6, PP1-5 weightedLikely PathogenicStrong + moderate evidenceVUSInsufficient or conflicting evidenceLikely BenignBS1-4, BP1-7 weightedBenignStrong benign evidence\n\nNever classify without evidence. State \"insufficient data\" when appropriate."
      },
      {
        "title": "2. Check Population Frequency First",
        "body": "Before clinical interpretation, verify frequency:\n\nSourceUse ForgnomAD v4Global population frequencygnomAD non-cancerSomatic analysisPopulation-specificAncestry-appropriate filtering\n\nMAF >1% in any population = likely benign for rare disease."
      },
      {
        "title": "3. Cross-Reference Multiple Databases",
        "body": "DatabaseInformationClinVarClinical classifications + submitter evidenceOMIMGene-disease relationshipsHGMDLiterature-reported mutationsUniProtProtein function + domains\n\nSingle-source interpretation is insufficient. Triangulate evidence."
      },
      {
        "title": "4. Report Pharmacogenomics Actionably",
        "body": "For drug-gene interactions, provide:\n\nDiplotype (e.g., CYP2D6 *1/*4)\nPredicted phenotype (poor/intermediate/normal/ultra-rapid metabolizer)\nDrug list affected\nDosing guidance (CPIC/DPWG when available)"
      },
      {
        "title": "5. Separate Germline from Somatic Context",
        "body": "ContextKey DifferencesGermlineFamily implications, carrier testing, predictiveSomaticTumor-specific, therapy selection, no inheritance\n\nAlways state which context you're interpreting."
      },
      {
        "title": "6. Acknowledge Uncertainty",
        "body": "Novel variants often lack evidence\nVUS ≠ benign — requires ongoing monitoring\nReclassification happens (ClinVar updates monthly)\nComputational predictions are supportive, not definitive"
      },
      {
        "title": "High-Priority Drug-Gene Pairs (CPIC Level A)",
        "body": "GeneDrugsClinical ActionCYP2D6Codeine, tramadol, tamoxifen, SSRIsDosing/alternativeCYP2C19Clopidogrel, PPIs, voriconazoleDosing/alternativeCYP2C9 + VKORC1WarfarinDosing algorithmDPYDFluorouracil, capecitabineDose reduction/avoidTPMT + NUDT15Azathioprine, mercaptopurineDose reductionHLA-B*57:01AbacavirContraindicationHLA-B*15:02CarbamazepineContraindication (Asian ancestry)SLCO1B1SimvastatinDose cap/alternative statinG6PDRasburicase, primaquineContraindicationCYP3A5TacrolimusDosing adjustment"
      },
      {
        "title": "Phenotype Interpretation",
        "body": "Metabolizer StatusMeaningTypical ActionPoor (PM)Little/no enzyme activityAlternative drug or dose ↓↓Intermediate (IM)Reduced activityConsider dose ↓Normal (NM)Expected activityStandard dosingRapid/Ultra-rapid (UM)Increased activityDose ↑ or alternative"
      },
      {
        "title": "Annotation Resources",
        "body": "ResourceURLContentClinVarncbi.nlm.nih.gov/clinvarClinical variant classificationsgnomADgnomad.broadinstitute.orgPopulation frequenciesOMIMomim.orgGene-disease relationshipsPharmGKBpharmgkb.orgDrug-gene annotationsCPICcpicpgx.orgPharmacogenomics guidelinesClinGenclinicalgenome.orgGene-disease validityFranklinfranklin.genoox.comVariant interpretation aidVarSomevarsome.comACMG auto-classification"
      },
      {
        "title": "Common Interpretation Traps",
        "body": "Ignoring population specificity — Variants common in African populations may look rare in European-biased databases\nTrusting single ClinVar submitter — Check submitter count and review status (≥2 submitters, no conflict preferred)\nConflating computational prediction with evidence — CADD/REVEL are supportive, not diagnostic\nMissing compound heterozygosity — Two VUS in trans can be pathogenic together\nOutdated database versions — gnomAD v4 has 800K+ exomes vs v2's 125K\nIgnoring gene-level constraint — pLI/LOEUF scores indicate tolerance to loss-of-function"
      },
      {
        "title": "External Endpoints",
        "body": "This skill does NOT automatically call external APIs. All database references are for manual lookup:\n\nResourceWhen UsedData SentClinVar, gnomAD, OMIMUser manually visitsNone by this skillPharmGKB, CPICUser manually visitsNone by this skillVarSome, FranklinUser manually visitsNone by this skill\n\nNo automatic network requests. The skill provides URLs and guidance for manual lookup only."
      },
      {
        "title": "Security & Privacy",
        "body": "Data that stays local:\n\nAll interpretation work runs locally\nNo variant data sent externally by this skill\nNo automatic API calls to any database\n\nThis skill does NOT:\n\nMake network requests automatically\nUpload patient variants anywhere\nConnect to databases without explicit user action\nStore identifiable genomic information outside ~/genomics/"
      },
      {
        "title": "Related Skills",
        "body": "Install with clawhub install <slug> if user confirms:\n\nmedicine — clinical decision support\nbiology — molecular mechanisms\nchemistry — drug metabolism pathways\nhealth — patient care context"
      },
      {
        "title": "Feedback",
        "body": "If useful: clawhub star genomics\nStay updated: clawhub sync"
      }
    ],
    "body": "Setup\n\nOn first use, read setup.md for integration guidelines. Ask user consent before creating ~/genomics/ workspace.\n\nWhen to Use\n\nUser has processed genomic data (VCF files) and needs clinical interpretation. Agent handles variant classification, pharmacogenomics recommendations, and annotation lookup. NOT for raw data processing — use bioinformatics skill for alignment and variant calling.\n\nArchitecture\n\nMemory lives in ~/genomics/. See memory-template.md for structure.\n\n~/genomics/\n├── memory.md           # Context + preferences + interpretation history\n└── cases/              # Active interpretation cases\n\nQuick Reference\nTopic\tFile\nSetup process\tsetup.md\nMemory template\tmemory-template.md\nCore Rules\n1. Classify Variants Using ACMG Guidelines\n\nEvery variant needs systematic classification:\n\nCategory\tCriteria\nPathogenic\tPVS1, PS1-4, PM1-6, PP1-5 weighted\nLikely Pathogenic\tStrong + moderate evidence\nVUS\tInsufficient or conflicting evidence\nLikely Benign\tBS1-4, BP1-7 weighted\nBenign\tStrong benign evidence\n\nNever classify without evidence. State \"insufficient data\" when appropriate.\n\n2. Check Population Frequency First\n\nBefore clinical interpretation, verify frequency:\n\nSource\tUse For\ngnomAD v4\tGlobal population frequency\ngnomAD non-cancer\tSomatic analysis\nPopulation-specific\tAncestry-appropriate filtering\n\nMAF >1% in any population = likely benign for rare disease.\n\n3. Cross-Reference Multiple Databases\nDatabase\tInformation\nClinVar\tClinical classifications + submitter evidence\nOMIM\tGene-disease relationships\nHGMD\tLiterature-reported mutations\nUniProt\tProtein function + domains\n\nSingle-source interpretation is insufficient. Triangulate evidence.\n\n4. Report Pharmacogenomics Actionably\n\nFor drug-gene interactions, provide:\n\nDiplotype (e.g., CYP2D6 *1/*4)\nPredicted phenotype (poor/intermediate/normal/ultra-rapid metabolizer)\nDrug list affected\nDosing guidance (CPIC/DPWG when available)\n5. Separate Germline from Somatic Context\nContext\tKey Differences\nGermline\tFamily implications, carrier testing, predictive\nSomatic\tTumor-specific, therapy selection, no inheritance\n\nAlways state which context you're interpreting.\n\n6. Acknowledge Uncertainty\nNovel variants often lack evidence\nVUS ≠ benign — requires ongoing monitoring\nReclassification happens (ClinVar updates monthly)\nComputational predictions are supportive, not definitive\nPharmacogenomics Reference\nHigh-Priority Drug-Gene Pairs (CPIC Level A)\nGene\tDrugs\tClinical Action\nCYP2D6\tCodeine, tramadol, tamoxifen, SSRIs\tDosing/alternative\nCYP2C19\tClopidogrel, PPIs, voriconazole\tDosing/alternative\nCYP2C9 + VKORC1\tWarfarin\tDosing algorithm\nDPYD\tFluorouracil, capecitabine\tDose reduction/avoid\nTPMT + NUDT15\tAzathioprine, mercaptopurine\tDose reduction\nHLA-B*57:01\tAbacavir\tContraindication\nHLA-B*15:02\tCarbamazepine\tContraindication (Asian ancestry)\nSLCO1B1\tSimvastatin\tDose cap/alternative statin\nG6PD\tRasburicase, primaquine\tContraindication\nCYP3A5\tTacrolimus\tDosing adjustment\nPhenotype Interpretation\nMetabolizer Status\tMeaning\tTypical Action\nPoor (PM)\tLittle/no enzyme activity\tAlternative drug or dose ↓↓\nIntermediate (IM)\tReduced activity\tConsider dose ↓\nNormal (NM)\tExpected activity\tStandard dosing\nRapid/Ultra-rapid (UM)\tIncreased activity\tDose ↑ or alternative\nAnnotation Resources\nResource\tURL\tContent\nClinVar\tncbi.nlm.nih.gov/clinvar\tClinical variant classifications\ngnomAD\tgnomad.broadinstitute.org\tPopulation frequencies\nOMIM\tomim.org\tGene-disease relationships\nPharmGKB\tpharmgkb.org\tDrug-gene annotations\nCPIC\tcpicpgx.org\tPharmacogenomics guidelines\nClinGen\tclinicalgenome.org\tGene-disease validity\nFranklin\tfranklin.genoox.com\tVariant interpretation aid\nVarSome\tvarsome.com\tACMG auto-classification\nCommon Interpretation Traps\nIgnoring population specificity — Variants common in African populations may look rare in European-biased databases\nTrusting single ClinVar submitter — Check submitter count and review status (≥2 submitters, no conflict preferred)\nConflating computational prediction with evidence — CADD/REVEL are supportive, not diagnostic\nMissing compound heterozygosity — Two VUS in trans can be pathogenic together\nOutdated database versions — gnomAD v4 has 800K+ exomes vs v2's 125K\nIgnoring gene-level constraint — pLI/LOEUF scores indicate tolerance to loss-of-function\nExternal Endpoints\n\nThis skill does NOT automatically call external APIs. All database references are for manual lookup:\n\nResource\tWhen Used\tData Sent\nClinVar, gnomAD, OMIM\tUser manually visits\tNone by this skill\nPharmGKB, CPIC\tUser manually visits\tNone by this skill\nVarSome, Franklin\tUser manually visits\tNone by this skill\n\nNo automatic network requests. The skill provides URLs and guidance for manual lookup only.\n\nSecurity & Privacy\n\nData that stays local:\n\nAll interpretation work runs locally\nNo variant data sent externally by this skill\nNo automatic API calls to any database\n\nThis skill does NOT:\n\nMake network requests automatically\nUpload patient variants anywhere\nConnect to databases without explicit user action\nStore identifiable genomic information outside ~/genomics/\nRelated Skills\n\nInstall with clawhub install <slug> if user confirms:\n\nmedicine — clinical decision support\nbiology — molecular mechanisms\nchemistry — drug metabolism pathways\nhealth — patient care context\nFeedback\nIf useful: clawhub star genomics\nStay updated: clawhub sync"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/ivangdavila/genomics",
    "publisherUrl": "https://clawhub.ai/ivangdavila/genomics",
    "owner": "ivangdavila",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/genomics",
    "downloadUrl": "https://openagent3.xyz/downloads/genomics",
    "agentUrl": "https://openagent3.xyz/skills/genomics/agent",
    "manifestUrl": "https://openagent3.xyz/skills/genomics/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/genomics/agent.md"
  }
}