[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6ECBF24SF11C7RXP6WGF7S2":3,"skill-same:01M6ECBF24SF11C7RXP6WGF7S2":80},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":25,"publishedAt":29,"linkOnly":30,"markdownContent":31,"markdownBody":31,"frontMatter":32,"refName":33,"commitSha":34,"skillDirectory":35,"forksCount":36,"repositoryHtmlUrl":37,"repositoryHomepageUrl":38,"ownerHtmlUrl":39,"ownerBlogUrl":6,"ownerDescription":40,"updatedAt":41,"install":42,"resources":55},"01M6ECBF24SF11C7RXP6WGF7S2","metabolomics-workbench-database",null,"ComeOnOliver\u002Fskillshub","ComeOnOliver","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F43215937?v=4","01M6E5JNFECJAAVFE0W7SMWWD2","Haoran Shu","01M6E5JNNDQS7AJZDYFQ8TPZCK",67,"MIT","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002FK-Dense-AI\u002Fclaude-scientific-skills\u002Fmetabolomics-workbench-database\u002FSKILL.md",[17,22],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",[26,27,28],"database","metabolomics workbench database","metabolomics","2026-11-10 10:12:30",false,"# Metabolomics Workbench Database\n\n## Overview\n\nThe Metabolomics Workbench is a comprehensive NIH Common Fund-sponsored platform hosted at UCSD that serves as the primary repository for metabolomics research data. It provides programmatic access to over 4,200 processed studies (3,790+ publicly available), standardized metabolite nomenclature through RefMet, and powerful search capabilities across multiple analytical platforms (GC-MS, LC-MS, NMR).\n\n## When to Use This Skill\n\nThis skill should be used when querying metabolite structures, accessing study data, standardizing nomenclature, performing mass spectrometry searches, or retrieving gene\u002Fprotein-metabolite associations through the Metabolomics Workbench REST API.\n\n## Core Capabilities\n\n### 1. Querying Metabolite Structures and Data\n\nAccess comprehensive metabolite information including structures, identifiers, and cross-references to external databases.\n\n**Key operations:**\n- Retrieve compound data by various identifiers (PubChem CID, InChI Key, KEGG ID, HMDB ID, etc.)\n- Download molecular structures as MOL files or PNG images\n- Access standardized compound classifications\n- Cross-reference between different metabolite databases\n\n**Example queries:**\n```python\nimport requests\n\n# Get compound information by PubChem CID\nresponse = requests.get('https:\u002F\u002Fwww.metabolomicsworkbench.org\u002Frest\u002Fcompound\u002Fpubchem_cid\u002F5281365\u002Fall\u002Fjson')\n\n# Download molecular structure as PNG\nresponse = requests.get('https:\u002F\u002Fwww.metabolomicsworkbench.org\u002Frest\u002Fcompound\u002Fregno\u002F11\u002Fpng')\n\n# Get compound name by registry number\nresponse = requests.get('https:\u002F\u002Fwww.metabolomicsworkbench.org\u002Frest\u002Fcompound\u002Fregno\u002F11\u002Fname\u002Fjson')\n```\n\n### 2. Accessing Study Metadata and Experimental Results\n\nQuery metabolomics studies by various criteria and retrieve complete experimental datasets.\n\n**Key operations:**\n- Search studies by metabolite, institute, investigator, or title\n- Access study summaries, experimental factors, and analysis details\n- Retrieve complete experimental data in various formats\n- Download mwTab format files for complete study information\n- Query untargeted metabolomics data\n\n**Example queries:**\n```python\n# List all available public studies\nresponse = requests.get('https:\u002F\u002Fwww.metabolomicsworkbench.org\u002Frest\u002Fstudy\u002Fstudy_id\u002FST\u002Favailable\u002Fjson')\n\n# Get study summary\nresponse = requests.get('https:\u002F\u002Fwww.metabolomicsworkbench.org\u002Frest\u002Fstudy\u002Fstudy_id\u002FST000001\u002Fsummary\u002Fjson')\n\n# Retrieve experimental data\nresponse = requests.get('https:\u002F\u002Fwww.metabolomicsworkbench.org\u002Frest\u002Fstudy\u002Fstudy_id\u002FST000001\u002Fdata\u002Fjson')\n\n# Find studies containing a specific metabolite\nresponse = requests.get('https:\u002F\u002Fwww.metabolomicsworkbench.org\u002Frest\u002Fstudy\u002Frefmet_name\u002FTyrosine\u002Fsummary\u002Fjson')\n```\n\n### 3. Standardizing Metabolite Nomenclature with RefMet\n\nUse the RefMet database to standardize metabolite names and access systematic classification across four structural resolution levels.\n\n**Key operations:**\n- Match common metabolite names to standardized RefMet names\n- Query by chemical formula, exact mass, or InChI Key\n- Access hierarchical classification (super class, main class, sub class)\n- Retrieve all RefMet entries or filter by classification\n\n**Example queries:**\n```python\n# Standardize a metabolite name\nresponse = requests.get('https:\u002F\u002Fwww.metabolomicsworkbench.org\u002Frest\u002Frefmet\u002Fmatch\u002Fcitrate\u002Fname\u002Fjson')\n\n# Query by molecular formula\nresponse = requests.get('https:\u002F\u002Fwww.metabolomicsworkbench.org\u002Frest\u002Frefmet\u002Fformula\u002FC12H24O2\u002Fall\u002Fjson')\n\n# Get all metabolites in a specific class\nresponse = requests.get('https:\u002F\u002Fwww.metabolomicsworkbench.org\u002Frest\u002Frefmet\u002Fmain_class\u002FFatty%20Acids\u002Fall\u002Fjson')\n\n# Retrieve complete RefMet database\nresponse = requests.get('https:\u002F\u002Fwww.metabolomicsworkbench.org\u002Frest\u002Frefmet\u002Fall\u002Fjson')\n```\n\n### 4. Performing Mass Spectrometry Searches\n\nSearch for compounds by mass-to-charge ratio (m\u002Fz) with specified ion adducts and tolerance levels.\n\n**Key operations:**\n- Search precursor ion masses across multiple databases (Metabolomics Workbench, LIPIDS, RefMet)\n- Specify ion adduct types (M+H, M-H, M+Na, M+NH4, M+2H, etc.)\n- Calculate exact masses for known metabolites with specific adducts\n- Set mass tolerance for flexible matching\n\n**Example queries:**\n```python\n# Search by m\u002Fz value with M+H adduct\nresponse = requests.get('https:\u002F\u002Fwww.metabolomicsworkbench.org\u002Frest\u002Fmoverz\u002FMB\u002F635.52\u002FM+H\u002F0.5\u002Fjson')\n\n# Calculate exact mass for a metabolite with specific adduct\nresponse = requests.get('https:\u002F\u002Fwww.metabolomicsworkbench.org\u002Frest\u002Fmoverz\u002Fexactmass\u002FPC(34:1)\u002FM+H\u002Fjson')\n\n# Search across RefMet database\nresponse = requests.get('https:\u002F\u002Fwww.metabolomicsworkbench.org\u002Frest\u002Fmoverz\u002FREFMET\u002F200.15\u002FM-H\u002F0.3\u002Fjson')\n```\n\n### 5. Filtering Studies by Analytical and Biological Parameters\n\nUse the MetStat context to find studies matching specific experimental conditions.\n\n**Key operations:**\n- Filter by analytical method (LCMS, GCMS, NMR)\n- Specify ionization polarity (POSITIVE, NEGATIVE)\n- Filter by chromatography type (HILIC, RP, GC)\n- Target specific species, sample sources, or diseases\n- Combine multiple filters using semicolon-delimited format\n\n**Example queries:**\n```python\n# Find human blood studies on diabetes using LC-MS\nresponse = requests.get('https:\u002F\u002Fwww.metabolomicsworkbench.org\u002Frest\u002Fmetstat\u002FLCMS;POSITIVE;HILIC;Human;Blood;Diabetes\u002Fjson')\n\n# Find all human blood studies containing tyrosine\nresponse = requests.get('https:\u002F\u002Fwww.metabolomicsworkbench.org\u002Frest\u002Fmetstat\u002F;;;Human;Blood;;;Tyrosine\u002Fjson')\n\n# Filter by analytical method only\nresponse = requests.get('https:\u002F\u002Fwww.metabolomicsworkbench.org\u002Frest\u002Fmetstat\u002FGCMS;;;;;;\u002Fjson')\n```\n\n### 6. Accessing Gene and Protein Information\n\nRetrieve gene and protein data associated with metabolic pathways and metabolite metabolism.\n\n**Key operations:**\n- Query genes by symbol, name, or ID\n- Access protein sequences and annotations\n- Cross-reference between gene IDs, RefSeq IDs, and UniProt IDs\n- Retrieve gene-metabolite associations\n\n**Example queries:**\n```python\n# Get gene information by symbol\nresponse = requests.get('https:\u002F\u002Fwww.metabolomicsworkbench.org\u002Frest\u002Fgene\u002Fgene_symbol\u002FACACA\u002Fall\u002Fjson')\n\n# Retrieve protein data by UniProt ID\nresponse = requests.get('https:\u002F\u002Fwww.metabolomicsworkbench.org\u002Frest\u002Fprotein\u002Funiprot_id\u002FQ13085\u002Fall\u002Fjson')\n```\n\n## Common Workflows\n\n### Workflow 1: Finding Studies for a Specific Metabolite\n\nTo find all studies containing measurements of a specific metabolite:\n\n1. First standardize the metabolite name using RefMet:\n   ```python\n   response = requests.get('https:\u002F\u002Fwww.metabolomicsworkbench.org\u002Frest\u002Frefmet\u002Fmatch\u002Fglucose\u002Fname\u002Fjson')\n   ```\n\n2. Use the standardized name to search for studies:\n   ```python\n   response = requests.get('https:\u002F\u002Fwww.metabolomicsworkbench.org\u002Frest\u002Fstudy\u002Frefmet_name\u002FGlucose\u002Fsummary\u002Fjson')\n   ```\n\n3. Retrieve experimental data from specific studies:\n   ```python\n   response = requests.get('https:\u002F\u002Fwww.metabolomicsworkbench.org\u002Frest\u002Fstudy\u002Fstudy_id\u002FST000001\u002Fdata\u002Fjson')\n   ```\n\n### Workflow 2: Identifying Compounds from MS Data\n\nTo identify potential compounds from mass spectrometry m\u002Fz values:\n\n1. Perform m\u002Fz search with appropriate adduct and tolerance:\n   ```python\n   response = requests.get('https:\u002F\u002Fwww.metabolomicsworkbench.org\u002Frest\u002Fmoverz\u002FMB\u002F180.06\u002FM+H\u002F0.5\u002Fjson')\n   ```\n\n2. Review candidate compounds from results\n\n3. Retrieve detailed information for candidate compounds:\n   ```python\n   response = requests.get('https:\u002F\u002Fwww.metabolomicsworkbench.org\u002Frest\u002Fcompound\u002Fregno\u002F{regno}\u002Fall\u002Fjson')\n   ```\n\n4. Download structures for confirmation:\n   ```python\n   response = requests.get('https:\u002F\u002Fwww.metabolomicsworkbench.org\u002Frest\u002Fcompound\u002Fregno\u002F{regno}\u002Fpng')\n   ```\n\n### Workflow 3: Exploring Disease-Specific Metabolomics\n\nTo find metabolomics studies for a specific disease and analytical platform:\n\n1. Use MetStat to filter studies:\n   ```python\n   response = requests.get('https:\u002F\u002Fwww.metabolomicsworkbench.org\u002Frest\u002Fmetstat\u002FLCMS;POSITIVE;;Human;;Cancer\u002Fjson')\n   ```\n\n2. Review study IDs from results\n\n3. Access detailed study information:\n   ```python\n   response = requests.get('https:\u002F\u002Fwww.metabolomicsworkbench.org\u002Frest\u002Fstudy\u002Fstudy_id\u002FST{ID}\u002Fsummary\u002Fjson')\n   ```\n\n4. Retrieve complete experimental data:\n   ```python\n   response = requests.get('https:\u002F\u002Fwww.metabolomicsworkbench.org\u002Frest\u002Fstudy\u002Fstudy_id\u002FST{ID}\u002Fdata\u002Fjson')\n   ```\n\n## Output Formats\n\nThe API supports two primary output formats:\n- **JSON** (default): Machine-readable format, ideal for programmatic access\n- **TXT**: Human-readable tab-delimited text format\n\nSpecify format by appending `\u002Fjson` or `\u002Ftxt` to API URLs. When format is omitted, JSON is returned by default.\n\n## Best Practices\n\n1. **Use RefMet for standardization**: Always standardize metabolite names through RefMet before searching studies to ensure consistent nomenclature\n\n2. **Specify appropriate adducts**: When performing m\u002Fz searches, use the correct ion adduct type for your analytical method (e.g., M+H for positive mode ESI)\n\n3. **Set reasonable tolerances**: Use appropriate mass tolerance values (typically 0.5 Da for low-resolution, 0.01 Da for high-resolution MS)\n\n4. **Cache reference data**: Consider caching frequently used reference data (RefMet database, compound information) to minimize API calls\n\n5. **Handle pagination**: For large result sets, be prepared to handle multiple data structures in responses\n\n6. **Validate identifiers**: Cross-reference metabolite identifiers across multiple databases when possible to ensure correct compound identification\n\n## Resources\n\n### references\u002F\n\nDetailed API reference documentation is available in `references\u002Fapi_reference.md`, including:\n- Complete REST API endpoint specifications\n- All available contexts (compound, study, refmet, metstat, gene, protein, moverz)\n- Input\u002Foutput parameter details\n- Ion adduct types for mass spectrometry\n- Additional query examples\n\nLoad this reference file when detailed API specifications are needed or when working with less common endpoints.\n",{},"main","def8531e65114c0fca8fb8551c1871ee0eed705c","skills\u002FK-Dense-AI\u002Fclaude-scientific-skills\u002Fmetabolomics-workbench-database",24,"https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub","https:\u002F\u002Fskillshub.wtf","https:\u002F\u002Fgithub.com\u002FComeOnOliver","AI & Blockchain Engineer\r\n","2026-06-24 22:07:19",{"source":7,"skillName":5,"commands":43,"prompt":53,"zipAvailable":54},[44,47,50],{"tool":45,"command":46},"npx","npx skills add ComeOnOliver\u002Fskillshub --skill metabolomics-workbench-database",{"tool":48,"command":49},"bunx","bunx skills add ComeOnOliver\u002Fskillshub --skill metabolomics-workbench-database",{"tool":51,"command":52},"pnpm","pnpm dlx skills add ComeOnOliver\u002Fskillshub --skill metabolomics-workbench-database","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002FK-Dense-AI\u002Fclaude-scientific-skills\u002Fmetabolomics-workbench-database\u002FSKILL.md",true,[56,62,66,70,74],{"path":57,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":60,"sourceHtmlUrl":61},"BENCHMARK.md","REFERENCE","参考文档",4341,"https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Fnemo-mbridge-mlm-bridge-training\u002FBENCHMARK.md",{"path":63,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":64,"sourceHtmlUrl":65},"card.yaml",2031,"https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Fnemo-mbridge-mlm-bridge-training\u002Fcard.yaml",{"path":67,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":68,"sourceHtmlUrl":69},"evals\u002Fevals.json",1673,"https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Fnemo-mbridge-mlm-bridge-training\u002Fevals\u002Fevals.json",{"path":71,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":72,"sourceHtmlUrl":73},"skill-card.md",3824,"https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Fnemo-mbridge-mlm-bridge-training\u002Fskill-card.md",{"path":75,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":78,"sourceHtmlUrl":79},"skill.oms.sig","OTHER","其他",4821,"https:\u002F\u002Fgithub.com\u002Fpattanation\u002FNorvik\u002Fblob\u002Fclaude\u002Finstall-gsd-build-foQdV\u002F.agents\u002Fskills\u002Fnemo-mbridge-mlm-bridge-training\u002Fskill.oms.sig",[81,91,101,110,116,123],{"skillNo":82,"name":83,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":87,"publishedAt":29},"01M6FKJN13GMG4KY57J3QD8GY5","model-hierarchy-skill","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzscole\u002Fmodel-hierarchy-skill\u002Fmodel-hierarchy-skill\u002FSKILL.md",[86],{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},[88,89,90],"model","model hierarchy","model hierarchy skill",{"skillNo":92,"name":93,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":97,"publishedAt":29},"01M6FKJJJ6GCAMR4PPPRD12M5X","zoom-mcp","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fzoom-mcp\u002FSKILL.md",[96],{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},[98,99,100],"MCP","zoom","zoom mcp",{"skillNo":102,"name":103,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":29},"01M6FKJE3KYT3KPEZMEEHYKA6K","zoom-apps-sdk","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fzoom-apps-sdk\u002FSKILL.md",[],[107,108,109,99],"sdk","zoom apps sdk","apps",{"skillNo":111,"name":112,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":29},"01M6FKJ9EDH9Q5VWDF8HAJRSP0","windows","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fwindows\u002FSKILL.md",[],[112],{"skillNo":117,"name":118,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":122,"publishedAt":29},"01M6FKJ666BEEFC3AE9GJ72Q93","whiteboard","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fwhiteboard\u002FSKILL.md",[121],{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},[118],{"skillNo":124,"name":125,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":126,"categories":127,"keywords":128,"publishedAt":29},"01M6FKJ21WFCDGTJQ2Q91T9DVW","websockets","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fwebsockets\u002FSKILL.md",[],[125]]