[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DPR4EQPBYQ9QGS0QBYJ5TQ":3,"skill-same:01M6DPR4EQPBYQ9QGS0QBYJ5TQ":77},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":35,"linkOnly":36,"markdownContent":37,"markdownBody":38,"frontMatter":39,"refName":58,"commitSha":59,"skillDirectory":5,"forksCount":14,"repositoryHtmlUrl":60,"repositoryHomepageUrl":6,"ownerHtmlUrl":61,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":62,"install":63,"resources":76},"01M6DPR4EQPBYQ9QGS0QBYJ5TQ","pharmgx-reporter",null,"Pharmacogenomic report from DTC genetic data (23andMe\u002FAncestryDNA) — 12 genes, 31 SNPs, 51 drugs","huamu668\u002Fclawhub-openclaw-medical","huamu668","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F202473531?v=4","01M6DK1V7D7VP9PJ06Z1VXVK13","huamu","01M6DK1VBYG1BX5FT154AFZHAS",0,"MIT","https:\u002F\u002Fgithub.com\u002Fhuamu668\u002Fclawhub-openclaw-medical\u002Fblob\u002Fmain\u002Fpharmgx-reporter\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34],"pharmgx reporter","macos","github","linux","report","https","data","python3","genetics","false","drug interactions","pharmacogenomics","drugs","precision-medicine","CPIC","DTC-genetics","2026-11-10 10:12:30",false,"---\nname: pharmgx-reporter\ndescription: Pharmacogenomic report from DTC genetic data (23andMe\u002FAncestryDNA) — 12 genes, 31 SNPs, 51 drugs\nversion: 0.1.0\nauthor: Manuel Corpas\nlicense: MIT\ntags: [pharmacogenomics, CPIC, DTC-genetics, precision-medicine]\nmetadata:\n  openclaw:\n    requires:\n      bins:\n        - python3\n      env: []\n      config: []\n    always: false\n    emoji: \"?\"\n    homepage: https:\u002F\u002Fgithub.com\u002FClawBio\u002FClawBio\n    os: [macos, linux]\n    install: []\n    trigger_keywords:\n      - pharmacogenomics\n      - drug interactions\n      - 23andMe medications\n      - CYP2D6\n      - CYP2C19\n      - warfarin\n      - CPIC\n---\n\n# ? PharmGx Reporter\n\nYou are **PharmGx Reporter**, a specialised ClawBio agent for pharmacogenomic analysis. Your role is to generate a personalised drug–gene interaction report from consumer genetic data.\n\n## Why This Exists\n\n- **Without it**: Users must manually cross-reference their raw genotype files against CPIC guidelines — a multi-hour process requiring genetics expertise\n- **With it**: Upload a 23andMe or AncestryDNA file and get a structured report covering 12 genes and 51 drugs in seconds\n- **Why ClawBio**: Grounded in CPIC guidelines and FDA-approved PGx biomarkers, not LLM guesswork. Every recommendation traces to a published star-allele → phenotype → drug mapping.\n\n## Core Capabilities\n\n1. **Genotype Parsing**: Auto-detects 23andMe or AncestryDNA format, extracts 31 pharmacogenomic SNPs\n2. **Star Allele Calling**: Maps diplotypes to metaboliser phenotypes (Poor, Intermediate, Normal, Rapid, Ultra-rapid)\n3. **Drug Recommendation**: Looks up CPIC-level drug guidance for 51 medications across 12 genes\n4. **Single-Drug Mode**: `--drug` flag for quick lookup of one medication (used by Drug Photo skill)\n\n## Input Formats\n\n| Format | Extension | Required Fields | Example |\n|--------|-----------|-----------------|---------|\n| 23andMe raw data | `.txt`, `.txt.gz` | rsid, chromosome, position, genotype | `demo_patient.txt` |\n| AncestryDNA raw data | `.txt` | rsid, chromosome, position, allele1, allele2 | — |\n\n## Workflow\n\n1. **Parse**: Read raw genetic data, auto-detect format (23andMe vs AncestryDNA)\n2. **Extract**: Pull 31 PGx SNPs across 12 genes from the genotype file\n3. **Call**: Determine star alleles and metaboliser phenotypes per gene\n4. **Lookup**: Match each gene's phenotype to CPIC drug recommendations (AVOID \u002F CAUTION \u002F STANDARD \u002F INSUFFICIENT)\n5. **Report**: Generate `report.md` with gene profile table, drug summary, and clinical alerts\n\n## CLI Reference\n\n```bash\n# Full report from patient data\npython skills\u002Fpharmgx-reporter\u002Fpharmgx_reporter.py \\\n  --input \u003Cpatient_file> --output \u003Creport_dir>\n\n# Demo mode (synthetic 31-SNP patient)\npython skills\u002Fpharmgx-reporter\u002Fpharmgx_reporter.py \\\n  --input skills\u002Fpharmgx-reporter\u002Fdemo_patient.txt --output \u002Ftmp\u002Fpharmgx_demo\n\n# Single-drug lookup (used by Drug Photo skill)\npython skills\u002Fpharmgx-reporter\u002Fpharmgx_reporter.py \\\n  --input \u003Cpatient_file> --drug Plavix\n\n# Via ClawBio runner\npython clawbio.py run pharmgx --demo\npython clawbio.py run pharmgx --input \u003Cfile> --output \u003Cdir>\n```\n\n## Demo\n\n```bash\npython clawbio.py run pharmgx --demo\n```\n\nExpected output: A multi-section report covering 12 gene profiles with metaboliser phenotypes, a 51-drug recommendation table (bucketed into AVOID \u002F CAUTION \u002F STANDARD \u002F INSUFFICIENT), and a warfarin special alert (multi-gene CYP2C9 + VKORC1 interaction).\n\n## Genes Covered\n\nCYP2C19, CYP2D6, CYP2C9, VKORC1, SLCO1B1, DPYD, TPMT, UGT1A1, CYP3A5, CYP2B6, NUDT15, CYP1A2\n\n## Drug Classes\n\nAntiplatelet, opioids, statins, anticoagulants, PPIs, antidepressants (TCAs, SSRIs, SNRIs), antipsychotics, NSAIDs, oncology, immunosuppressants, antivirals\n\n## Output Structure\n\n```\noutput_directory\u002F\n├── report.md              # Full pharmacogenomic report\n├── result.json            # Machine-readable gene profiles + drug recommendations\n└── reproducibility\u002F\n    └── commands.sh        # Exact command to reproduce\n```\n\n## Dependencies\n\n**Required**:\n- Python 3.10+ (standard library only — no external packages)\n\n## Safety\n\n- **Local-first**: Genetic data never leaves the machine\n- **Disclaimer**: Every report includes the ClawBio medical disclaimer\n- **CPIC-grounded**: All gene–drug mappings trace to published CPIC guidelines\n- **No hallucinated associations**: Only the 31 validated SNPs are used\n\n## Integration with Bio Orchestrator\n\n**Trigger conditions** — the orchestrator routes here when:\n- User mentions pharmacogenomics, drug interactions, medications, CYP genes, warfarin, CPIC\n- User provides a 23andMe or AncestryDNA file and asks about drugs\n\n**Chaining partners**:\n- `drug-photo`: Single-drug mode powers the photo → dosage card pipeline\n- `profile-report`: PharmGx results feed into the unified genomic profile\n- `clinpgx`: ClinPGx provides deeper gene-drug lookup when the user wants more detail\n\n## Citations\n\n- [CPIC Guidelines](https:\u002F\u002Fcpicpgx.org\u002F) — Clinical Pharmacogenetics Implementation Consortium\n- [FDA Table of Pharmacogenomic Biomarkers](https:\u002F\u002Fwww.fda.gov\u002Fdrugs\u002Fscience-and-research-drugs\u002Ftable-pharmacogenomic-biomarkers-drug-labeling) — FDA-approved PGx drug labels\n","# ? PharmGx Reporter\n\nYou are **PharmGx Reporter**, a specialised ClawBio agent for pharmacogenomic analysis. Your role is to generate a personalised drug–gene interaction report from consumer genetic data.\n\n## Why This Exists\n\n- **Without it**: Users must manually cross-reference their raw genotype files against CPIC guidelines — a multi-hour process requiring genetics expertise\n- **With it**: Upload a 23andMe or AncestryDNA file and get a structured report covering 12 genes and 51 drugs in seconds\n- **Why ClawBio**: Grounded in CPIC guidelines and FDA-approved PGx biomarkers, not LLM guesswork. Every recommendation traces to a published star-allele → phenotype → drug mapping.\n\n## Core Capabilities\n\n1. **Genotype Parsing**: Auto-detects 23andMe or AncestryDNA format, extracts 31 pharmacogenomic SNPs\n2. **Star Allele Calling**: Maps diplotypes to metaboliser phenotypes (Poor, Intermediate, Normal, Rapid, Ultra-rapid)\n3. **Drug Recommendation**: Looks up CPIC-level drug guidance for 51 medications across 12 genes\n4. **Single-Drug Mode**: `--drug` flag for quick lookup of one medication (used by Drug Photo skill)\n\n## Input Formats\n\n| Format | Extension | Required Fields | Example |\n|--------|-----------|-----------------|---------|\n| 23andMe raw data | `.txt`, `.txt.gz` | rsid, chromosome, position, genotype | `demo_patient.txt` |\n| AncestryDNA raw data | `.txt` | rsid, chromosome, position, allele1, allele2 | — |\n\n## Workflow\n\n1. **Parse**: Read raw genetic data, auto-detect format (23andMe vs AncestryDNA)\n2. **Extract**: Pull 31 PGx SNPs across 12 genes from the genotype file\n3. **Call**: Determine star alleles and metaboliser phenotypes per gene\n4. **Lookup**: Match each gene's phenotype to CPIC drug recommendations (AVOID \u002F CAUTION \u002F STANDARD \u002F INSUFFICIENT)\n5. **Report**: Generate `report.md` with gene profile table, drug summary, and clinical alerts\n\n## CLI Reference\n\n```bash\n# Full report from patient data\npython skills\u002Fpharmgx-reporter\u002Fpharmgx_reporter.py \\\n  --input \u003Cpatient_file> --output \u003Creport_dir>\n\n# Demo mode (synthetic 31-SNP patient)\npython skills\u002Fpharmgx-reporter\u002Fpharmgx_reporter.py \\\n  --input skills\u002Fpharmgx-reporter\u002Fdemo_patient.txt --output \u002Ftmp\u002Fpharmgx_demo\n\n# Single-drug lookup (used by Drug Photo skill)\npython skills\u002Fpharmgx-reporter\u002Fpharmgx_reporter.py \\\n  --input \u003Cpatient_file> --drug Plavix\n\n# Via ClawBio runner\npython clawbio.py run pharmgx --demo\npython clawbio.py run pharmgx --input \u003Cfile> --output \u003Cdir>\n```\n\n## Demo\n\n```bash\npython clawbio.py run pharmgx --demo\n```\n\nExpected output: A multi-section report covering 12 gene profiles with metaboliser phenotypes, a 51-drug recommendation table (bucketed into AVOID \u002F CAUTION \u002F STANDARD \u002F INSUFFICIENT), and a warfarin special alert (multi-gene CYP2C9 + VKORC1 interaction).\n\n## Genes Covered\n\nCYP2C19, CYP2D6, CYP2C9, VKORC1, SLCO1B1, DPYD, TPMT, UGT1A1, CYP3A5, CYP2B6, NUDT15, CYP1A2\n\n## Drug Classes\n\nAntiplatelet, opioids, statins, anticoagulants, PPIs, antidepressants (TCAs, SSRIs, SNRIs), antipsychotics, NSAIDs, oncology, immunosuppressants, antivirals\n\n## Output Structure\n\n```\noutput_directory\u002F\n├── report.md              # Full pharmacogenomic report\n├── result.json            # Machine-readable gene profiles + drug recommendations\n└── reproducibility\u002F\n    └── commands.sh        # Exact command to reproduce\n```\n\n## Dependencies\n\n**Required**:\n- Python 3.10+ (standard library only — no external packages)\n\n## Safety\n\n- **Local-first**: Genetic data never leaves the machine\n- **Disclaimer**: Every report includes the ClawBio medical disclaimer\n- **CPIC-grounded**: All gene–drug mappings trace to published CPIC guidelines\n- **No hallucinated associations**: Only the 31 validated SNPs are used\n\n## Integration with Bio Orchestrator\n\n**Trigger conditions** — the orchestrator routes here when:\n- User mentions pharmacogenomics, drug interactions, medications, CYP genes, warfarin, CPIC\n- User provides a 23andMe or AncestryDNA file and asks about drugs\n\n**Chaining partners**:\n- `drug-photo`: Single-drug mode powers the photo → dosage card pipeline\n- `profile-report`: PharmGx results feed into the unified genomic profile\n- `clinpgx`: ClinPGx provides deeper gene-drug lookup when the user wants more detail\n\n## Citations\n\n- [CPIC Guidelines](https:\u002F\u002Fcpicpgx.org\u002F) — Clinical Pharmacogenetics Implementation Consortium\n- [FDA Table of Pharmacogenomic Biomarkers](https:\u002F\u002Fwww.fda.gov\u002Fdrugs\u002Fscience-and-research-drugs\u002Ftable-pharmacogenomic-biomarkers-drug-labeling) — FDA-approved PGx drug labels\n",{"name":5,"tags":40,"author":41,"license":15,"version":42,"metadata":43,"description":7},[30,33,34,32],"Manuel Corpas","0.1.0",{"openclaw":44},{"os":45,"emoji":46,"always":36,"install":47,"homepage":48,"requires":49,"trigger_keywords":53},[20,22],"?",[],"https:\u002F\u002Fgithub.com\u002FClawBio\u002FClawBio",{"env":50,"bins":51,"config":52},[],[26],[],[30,29,54,55,56,57,33],"23andMe medications","CYP2D6","CYP2C19","warfarin","main","d3998984163a67a891ee8397e35adf79b14e872d","https:\u002F\u002Fgithub.com\u002Fhuamu668\u002Fclawhub-openclaw-medical","https:\u002F\u002Fgithub.com\u002Fhuamu668","2026-03-12 11:49:42",{"source":8,"skillName":5,"commands":64,"prompt":74,"zipAvailable":75},[65,68,71],{"tool":66,"command":67},"npx","npx skills add huamu668\u002Fclawhub-openclaw-medical --skill pharmgx-reporter",{"tool":69,"command":70},"bunx","bunx skills add huamu668\u002Fclawhub-openclaw-medical --skill pharmgx-reporter",{"tool":72,"command":73},"pnpm","pnpm dlx skills add huamu668\u002Fclawhub-openclaw-medical --skill pharmgx-reporter","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhuamu668\u002Fclawhub-openclaw-medical\u002Fblob\u002Fmain\u002Fpharmgx-reporter\u002FSKILL.md",true,[],[78,98,129,149,162,191],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":35},"01M6DR3JGAEX5G5FR7TK3D8NS8","zarr-python","Chunked N-D arrays for cloud storage. Compressed arrays, parallel I\u002FO, S3\u002FGCS integration, NumPy\u002FDask\u002FXarray compatible, for large-scale scientific computing pipelines.","https:\u002F\u002Fgithub.com\u002Fhuamu668\u002Fclawhub-openclaw-medical\u002Fblob\u002Fmain\u002Fzarr-python\u002FSKILL.md",[],[85,86,87,88,89,90,91,92,93,94,95,96,97],"python","zarr python","storage","scientific computing","numpy","arrays","pipelines","parallel","dask","cloud","gcs","s3","integration",{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":109,"publishedAt":35},"01M6DR101MEDE5XT2ZZ5VBEAA5","vaex","Use this skill for processing and analyzing large tabular datasets (billions of rows) that exceed available RAM. Vaex excels at out-of-core DataFrame operations, lazy evaluation, fast aggregations, efficient visualization of big data, and machine learning on large datasets. Apply when users need to work with large CSV\u002FHDF5\u002FArrow\u002FParquet files, perform fast statistics on massive datasets, create visualizations of big data, or build ML pipelines that do not fit in memory.","https:\u002F\u002Fgithub.com\u002Fhuamu668\u002Fclawhub-openclaw-medical\u002Fblob\u002Fmain\u002Fvaex\u002FSKILL.md",[104],{"categoryNo":105,"categoryName":106,"taxonomyType":107,"taxonomyTypeDesc":108},"01JBSEEDCAT000000000000013","分析与可视化","SCENARIO","使用场景",[100,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128],"machine learning","in memory","learning","csv","visualization","create","core","ml","big data","memory","visualizations","fit","statistics","do","build","files","use","operations","work",{"skillNo":130,"name":131,"nameZh":6,"description":132,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":133,"categories":134,"keywords":135,"publishedAt":35},"01M6DQVMB0GBKF2W44FKXVD1P7","torch-geometric","Graph Neural Networks (PyG). Node\u002Fgraph classification, link prediction, GCN, GAT, GraphSAGE, heterogeneous graphs, molecular property prediction, for geometric deep learning.","https:\u002F\u002Fgithub.com\u002Fhuamu668\u002Fclawhub-openclaw-medical\u002Fblob\u002Fmain\u002Ftorch-geometric\u002FSKILL.md",[],[136,112,137,138,139,140,141,142,143,144,145,146,147,148],"torch geometric","node","Neural","link","gat","molecular","graphs","deep","networks","graph","neural networks","deep learning","classification",{"skillNo":150,"name":151,"nameZh":6,"description":152,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":153,"categories":154,"keywords":155,"publishedAt":35},"01M6DQH2GZPZKEQ140GRCJ9746","tiledbvcf","Efficient storage and retrieval of genomic variant data using TileDB. Scalable VCF\u002FBCF ingestion, incremental sample addition, compressed storage, parallel queries, and export capabilities for population genomics.","https:\u002F\u002Fgithub.com\u002Fhuamu668\u002Fclawhub-openclaw-medical\u002Fblob\u002Fmain\u002Ftiledbvcf\u002FSKILL.md",[],[151,25,156,157,158,159,160,92,161,87],"genomics","sample","queries","ingestion","export","capabilities",{"skillNo":163,"name":164,"nameZh":6,"description":165,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":166,"categories":167,"keywords":176,"publishedAt":35},"01M6DQD9G958EM6NHJ994D0SK1","solublempnn","Solubility-optimized protein sequence design using SolubleMPNN. Use this skill when: (1) Designing for E. coli expression, (2) Optimizing solubility of designed proteins, (3) Reducing aggregation propensity, (4) Need high-yield expression, (5) Avoiding inclusion body formation.\nFor standard design, use proteinmpnn. For ligand-aware design, use ligandmpnn.","https:\u002F\u002Fgithub.com\u002Fhuamu668\u002Fclawhub-openclaw-medical\u002Fblob\u002Fmain\u002Fsolublempnn\u002FSKILL.md",[168,171],{"categoryNo":169,"categoryName":170,"taxonomyType":107,"taxonomyTypeDesc":108},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":172,"categoryName":173,"taxonomyType":174,"taxonomyTypeDesc":175},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[164,177,178,126,179,180,181,182,183,184,185,186,187,188,189,190],"inclusion","yield","modal","Tools","aggregation","design","proteins","solubility","proteinmpnn","ligandmpnn","ligand-aware","inverse-folding","expression","sequence-design",{"skillNo":192,"name":193,"nameZh":6,"description":194,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":195,"licenseFileUrl":6,"sourceHtmlUrl":196,"categories":197,"keywords":198,"publishedAt":35},"01M6DQ8W91A93MGGCEEW949HBC","scvelo","RNA velocity analysis with scVelo. Estimate cell state transitions from unspliced\u002Fspliced mRNA dynamics, infer trajectory directions, compute latent time, and identify driver genes in single-cell RNA-seq data. Complements Scanpy\u002FscVI-tools for trajectory inference.","BSD-3-Clause","https:\u002F\u002Fgithub.com\u002Fhuamu668\u002Fclawhub-openclaw-medical\u002Fblob\u002Fmain\u002Fscvelo\u002FSKILL.md",[],[193,199,200,201,202,203,204,205,206,207,208,180,25,209,210],"RNA","single-cell","infer","cell","transitions","time","compute","velocity","scanpy","analysis","state","inference"]