[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DAX453D746Q0Q26MESSGHC":3,"skill-same:01M6DAX453D746Q0Q26MESSGHC":95},{"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":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":14,"repositoryHtmlUrl":52,"repositoryHomepageUrl":6,"ownerHtmlUrl":53,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":54,"install":55,"resources":68},"01M6DAX453D746Q0Q26MESSGHC","tooluniverse-sdk",null,"Build AI scientist systems using ToolUniverse Python SDK for scientific research. Use when users need to access 1000++ scientific tools through Python code, create scientific workflows, perform drug discovery, protein analysis, genomics analysis, literature research, or any computational biology task. Triggers include requests to use scientific tools programmatically, build research pipelines, analyze biological data, search literature, predict drug properties, or create AI-powered scientific workflows.","Prekzursil\u002Fagent-skills-toolchain","Prekzursil","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F54636077?v=4","01M6DACZ1PCQHD99SCR1YXG28B","Andrei Mihai Visalon","01M6DACZ670WZF535V3WYYSS4Z",0,"MIT","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-sdk\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"sdk","tooluniverse sdk","python sdk","python","triggers","computational","computational biology","task","build","properties","use","research","analyze","access","discovery","analysis","search","code","create","workflows","2026-11-10 10:12:30",false,"---\nname: tooluniverse-sdk\ndescription: Build AI scientist systems using ToolUniverse Python SDK for scientific research. Use when users need to access 1000++ scientific tools through Python code, create scientific workflows, perform drug discovery, protein analysis, genomics analysis, literature research, or any computational biology task. Triggers include requests to use scientific tools programmatically, build research pipelines, analyze biological data, search literature, predict drug properties, or create AI-powered scientific workflows.\n---\n\n# ToolUniverse Python SDK\n\n**3 calling patterns -- start with pattern 1:**\n1. `tu.run({\"name\": ..., \"arguments\": ...})` -- single tool call, dict API (most portable)\n2. `tu.tools.ToolName(param=value)` -- function API (recommended for interactive use)\n3. Direct class instantiation -- advanced, bypasses caching\u002Fhooks\n\n## Installation\n\n```bash\npip install tooluniverse              # Standard\npip install tooluniverse[embedding]   # Embedding search (GPU)\npip install tooluniverse[all]         # All features\n```\n\n```bash\nexport OPENAI_API_KEY=\"sk-...\"  # Required for LLM tool search\nexport NCBI_API_KEY=\"...\"       # Optional\n```\n\n## Quick Start\n\n```python\nfrom tooluniverse import ToolUniverse\n\ntu = ToolUniverse()\ntu.load_tools()  # REQUIRED before any tool call\n\n# Find tools\ntools = tu.run({\"name\": \"Tool_Finder_Keyword\", \"arguments\": {\"description\": \"protein structure\", \"limit\": 10}})\n\n# Execute (dict API)\nresult = tu.run({\"name\": \"UniProt_get_entry_by_accession\", \"arguments\": {\"accession\": \"P05067\"}})\n\n# Execute (function API)\nresult = tu.tools.UniProt_get_entry_by_accession(accession=\"P05067\")\n```\n\n## Core Patterns\n\n### Batch Execution\n\n```python\ncalls = [\n    {\"name\": \"UniProt_get_entry_by_accession\", \"arguments\": {\"accession\": \"P05067\"}},\n    {\"name\": \"UniProt_get_entry_by_accession\", \"arguments\": {\"accession\": \"P12345\"}},\n]\nresults = tu.run_batch(calls)\n```\n\n### Scientific Workflow\n\n```python\ndef drug_discovery_pipeline(disease_id):\n    tu = ToolUniverse(use_cache=True)\n    tu.load_tools()\n    try:\n        targets = tu.tools.OpenTargets_get_associated_targets_by_disease_efoId(efoId=disease_id)\n        compound_calls = [\n            {\"name\": \"ChEMBL_search_molecule_by_target\",\n             \"arguments\": {\"target_id\": t['id'], \"limit\": 10}}\n            for t in targets['data'][:5]\n        ]\n        compounds = tu.run_batch(compound_calls)\n        return {\"targets\": targets, \"compounds\": compounds}\n    finally:\n        tu.close()\n```\n\n## Configuration\n\n```python\n# Caching\ntu = ToolUniverse(use_cache=True)\nstats = tu.get_cache_stats()\ntu.clear_cache()\n\n# Hooks (auto-summarization of large outputs)\ntu = ToolUniverse(hooks_enabled=True)\n\n# Load specific categories\ntu.load_tools(categories=[\"proteins\", \"drugs\"])\n```\n\n## Critical Notes\n\n1. **Always call `load_tools()`** before using any tools\n2. **Tool Finder returns nested structure**: access via `tools['tools']` after `isinstance(tools, dict)` check\n3. **Tool names are case-sensitive**: `UniProt_get_entry_by_accession` not `uniprot_get_...`\n4. **Check required params**: `tu.all_tool_dict[\"ToolName\"]['parameter'].get('required', [])`\n5. **Cache deterministic calls** (ML predictions, DB queries); don't cache real-time data\n\n## Error Handling\n\n```python\nfrom tooluniverse.exceptions import ToolError, ToolUnavailableError, ToolValidationError\n\ntry:\n    result = tu.tools.some_tool(param=\"value\")\nexcept ToolUnavailableError:\n    ...  # Tool service down\nexcept ToolValidationError as e:\n    tool_info = tu.all_tool_dict[\"some_tool\"]\n    print(f\"Required: {tool_info['parameter'].get('required', [])}\")\n```\n\n## Tool Categories\n\n| Category | Tools | Use Cases |\n|----------|-------|-----------|\n| Proteins | UniProt, RCSB PDB, AlphaFold | Protein analysis, structure |\n| Drugs | DrugBank, ChEMBL, PubChem | Drug discovery, compounds |\n| Genomics | Ensembl, NCBI Gene, gnomAD | Gene analysis, variants |\n| Diseases | OpenTargets, ClinVar | Disease-target associations |\n| Literature | PubMed, Europe PMC | Literature search |\n| ML Models | ADMET-AI, AlphaFold | Predictions, modeling |\n| Pathways | KEGG, Reactome | Pathway analysis |\n\n## Resources\n\n- **Docs**: https:\u002F\u002Fzitniklab.hms.harvard.edu\u002FToolUniverse\u002F\n- **GitHub**: https:\u002F\u002Fgithub.com\u002Fmims-harvard\u002FToolUniverse\n- See [REFERENCE.md](REFERENCE.md) for detailed guides.\n","# ToolUniverse Python SDK\n\n**3 calling patterns -- start with pattern 1:**\n1. `tu.run({\"name\": ..., \"arguments\": ...})` -- single tool call, dict API (most portable)\n2. `tu.tools.ToolName(param=value)` -- function API (recommended for interactive use)\n3. Direct class instantiation -- advanced, bypasses caching\u002Fhooks\n\n## Installation\n\n```bash\npip install tooluniverse              # Standard\npip install tooluniverse[embedding]   # Embedding search (GPU)\npip install tooluniverse[all]         # All features\n```\n\n```bash\nexport OPENAI_API_KEY=\"sk-...\"  # Required for LLM tool search\nexport NCBI_API_KEY=\"...\"       # Optional\n```\n\n## Quick Start\n\n```python\nfrom tooluniverse import ToolUniverse\n\ntu = ToolUniverse()\ntu.load_tools()  # REQUIRED before any tool call\n\n# Find tools\ntools = tu.run({\"name\": \"Tool_Finder_Keyword\", \"arguments\": {\"description\": \"protein structure\", \"limit\": 10}})\n\n# Execute (dict API)\nresult = tu.run({\"name\": \"UniProt_get_entry_by_accession\", \"arguments\": {\"accession\": \"P05067\"}})\n\n# Execute (function API)\nresult = tu.tools.UniProt_get_entry_by_accession(accession=\"P05067\")\n```\n\n## Core Patterns\n\n### Batch Execution\n\n```python\ncalls = [\n    {\"name\": \"UniProt_get_entry_by_accession\", \"arguments\": {\"accession\": \"P05067\"}},\n    {\"name\": \"UniProt_get_entry_by_accession\", \"arguments\": {\"accession\": \"P12345\"}},\n]\nresults = tu.run_batch(calls)\n```\n\n### Scientific Workflow\n\n```python\ndef drug_discovery_pipeline(disease_id):\n    tu = ToolUniverse(use_cache=True)\n    tu.load_tools()\n    try:\n        targets = tu.tools.OpenTargets_get_associated_targets_by_disease_efoId(efoId=disease_id)\n        compound_calls = [\n            {\"name\": \"ChEMBL_search_molecule_by_target\",\n             \"arguments\": {\"target_id\": t['id'], \"limit\": 10}}\n            for t in targets['data'][:5]\n        ]\n        compounds = tu.run_batch(compound_calls)\n        return {\"targets\": targets, \"compounds\": compounds}\n    finally:\n        tu.close()\n```\n\n## Configuration\n\n```python\n# Caching\ntu = ToolUniverse(use_cache=True)\nstats = tu.get_cache_stats()\ntu.clear_cache()\n\n# Hooks (auto-summarization of large outputs)\ntu = ToolUniverse(hooks_enabled=True)\n\n# Load specific categories\ntu.load_tools(categories=[\"proteins\", \"drugs\"])\n```\n\n## Critical Notes\n\n1. **Always call `load_tools()`** before using any tools\n2. **Tool Finder returns nested structure**: access via `tools['tools']` after `isinstance(tools, dict)` check\n3. **Tool names are case-sensitive**: `UniProt_get_entry_by_accession` not `uniprot_get_...`\n4. **Check required params**: `tu.all_tool_dict[\"ToolName\"]['parameter'].get('required', [])`\n5. **Cache deterministic calls** (ML predictions, DB queries); don't cache real-time data\n\n## Error Handling\n\n```python\nfrom tooluniverse.exceptions import ToolError, ToolUnavailableError, ToolValidationError\n\ntry:\n    result = tu.tools.some_tool(param=\"value\")\nexcept ToolUnavailableError:\n    ...  # Tool service down\nexcept ToolValidationError as e:\n    tool_info = tu.all_tool_dict[\"some_tool\"]\n    print(f\"Required: {tool_info['parameter'].get('required', [])}\")\n```\n\n## Tool Categories\n\n| Category | Tools | Use Cases |\n|----------|-------|-----------|\n| Proteins | UniProt, RCSB PDB, AlphaFold | Protein analysis, structure |\n| Drugs | DrugBank, ChEMBL, PubChem | Drug discovery, compounds |\n| Genomics | Ensembl, NCBI Gene, gnomAD | Gene analysis, variants |\n| Diseases | OpenTargets, ClinVar | Disease-target associations |\n| Literature | PubMed, Europe PMC | Literature search |\n| ML Models | ADMET-AI, AlphaFold | Predictions, modeling |\n| Pathways | KEGG, Reactome | Pathway analysis |\n\n## Resources\n\n- **Docs**: https:\u002F\u002Fzitniklab.hms.harvard.edu\u002FToolUniverse\u002F\n- **GitHub**: https:\u002F\u002Fgithub.com\u002Fmims-harvard\u002FToolUniverse\n- See [REFERENCE.md](REFERENCE.md) for detailed guides.\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Flibrary\u002Fskills\u002Ftooluniverse-sdk","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":56,"prompt":66,"zipAvailable":67},[57,60,63],{"tool":58,"command":59},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-sdk",{"tool":61,"command":62},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-sdk",{"tool":64,"command":65},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-sdk","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-sdk\u002FSKILL.md",true,[69,75,79,83,87,91],{"path":70,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":73,"sourceHtmlUrl":74},"REFERENCE.md","REFERENCE","参考文档",12271,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-sdk\u002FREFERENCE.md",{"path":76,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":77,"sourceHtmlUrl":78},"references\u002Fhooks-patterns.md",6316,"https:\u002F\u002Fgithub.com\u002Fxiaoyuge886\u002Fharness_assistance\u002Fblob\u002Frefactor\u002Funified-packaging\u002Fdata\u002Fplugins\u002Fclaude-plugins-official-main\u002Fplugins\u002Fclaude-code-setup\u002Fskills\u002Fclaude-automation-recommender\u002Freferences\u002Fhooks-patterns.md",{"path":80,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":81,"sourceHtmlUrl":82},"references\u002Fmcp-servers.md",7419,"https:\u002F\u002Fgithub.com\u002Fxiaoyuge886\u002Fharness_assistance\u002Fblob\u002Frefactor\u002Funified-packaging\u002Fdata\u002Fplugins\u002Fclaude-plugins-official-main\u002Fplugins\u002Fclaude-code-setup\u002Fskills\u002Fclaude-automation-recommender\u002Freferences\u002Fmcp-servers.md",{"path":84,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":85,"sourceHtmlUrl":86},"references\u002Fplugins-reference.md",3016,"https:\u002F\u002Fgithub.com\u002Fxiaoyuge886\u002Fharness_assistance\u002Fblob\u002Frefactor\u002Funified-packaging\u002Fdata\u002Fplugins\u002Fclaude-plugins-official-main\u002Fplugins\u002Fclaude-code-setup\u002Fskills\u002Fclaude-automation-recommender\u002Freferences\u002Fplugins-reference.md",{"path":88,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":89,"sourceHtmlUrl":90},"references\u002Fskills-reference.md",9612,"https:\u002F\u002Fgithub.com\u002Fxiaoyuge886\u002Fharness_assistance\u002Fblob\u002Frefactor\u002Funified-packaging\u002Fdata\u002Fplugins\u002Fclaude-plugins-official-main\u002Fplugins\u002Fclaude-code-setup\u002Fskills\u002Fclaude-automation-recommender\u002Freferences\u002Fskills-reference.md",{"path":92,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":93,"sourceHtmlUrl":94},"references\u002Fsubagent-templates.md",5049,"https:\u002F\u002Fgithub.com\u002Fxiaoyuge886\u002Fharness_assistance\u002Fblob\u002Frefactor\u002Funified-packaging\u002Fdata\u002Fplugins\u002Fclaude-plugins-official-main\u002Fplugins\u002Fclaude-code-setup\u002Fskills\u002Fclaude-automation-recommender\u002Freferences\u002Fsubagent-templates.md",[96,116,144,171,185,201],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":44},"01M6DF7D7478R55P46REYH4QAC","clarify-requirements","Resolve genuine pre-execution ambiguity by scanning repo context, generating 1-6 grounded options, and asking 1-3 focused questions via AskUserQuestion. NOT for mid-task use (injection risk); NOT when the goal is already unambiguous; use to disambiguate vague prompts before any file edits.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fworkspace-hooks\u002Fskills\u002Fclarify-requirements\u002FSKILL.md",[],[103,104,105,106,107,31,108,109,110,34,111,112,113,114,115],"clarify requirements","clarify","requirements","risk","options","prompts","goal","scanning","context","repo","injection","execution","file",{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":125,"publishedAt":44},"01M6DF79CA4BHJS66J8EZDBPWJ","openmm-md","Run FREE, open-source, Windows-native GPU molecular dynamics via the openmm-md MCP (OpenMM + CUDA on the local NVIDIA GPU). Use for protein \u002F protein-ligand MD when you want a free stack or are on Windows without a Schrodinger license. Covers the full workflow (prepare, solvate, minimize, equilibrate, production, analyze, mmgbsa) AND an honest decision guide vs Schrodinger Desmond, including how to run Desmond legitimately on Linux or a cloud GPU with a real license. This is a deliberately LESSER free alternative and does NOT replace the schrodinger MCP tools. Do NOT use it to pick a free tool when a validated FEP+, WaterMap, IFD-MD, or Prime MM-GBSA result is actually required.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fmcp\u002Fopenmm-md-mcp\u002Fskill\u002Fopenmm-md\u002FSKILL.md",[122],{"categoryNo":123,"categoryName":124,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[126,127,128,129,130,36,131,132,133,134,135,136,137,138,34,139,140,141,142,143],"openmm md","how","decision","pick","linux","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":145,"name":146,"nameZh":6,"description":147,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":148,"categories":149,"keywords":156,"publishedAt":44},"01M6DF76C1MG85VEWP8VZCBNMN","visual-review","Take screenshots of web pages and UI using Playwright for visual review and iteration","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fvisual-review\u002FSKILL.md",[150,153],{"categoryNo":151,"categoryName":152,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":154,"categoryName":155,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[157,158,159,160,161,162,163,164,165,166,127,167,168,169,170],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":172,"name":173,"nameZh":6,"description":174,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":175,"categories":176,"keywords":177,"publishedAt":44},"01M6DF73AQVCBZKEN0YXEX9FXP","status","Diagnostic status report — shows metaswarm installation state, project setup, and potential issues","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstatus\u002FSKILL.md",[],[173,178,179,180,181,182,183,184],"setup","report","project","installation","project setup","issues","state",{"skillNo":186,"name":187,"nameZh":6,"description":188,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":189,"categories":190,"keywords":192,"publishedAt":44},"01M6DF6X6C2XB0P6GX76P7TTYV","start","Use when starting work on any task, when the user mentions metaswarm, or when the user wants to begin tracked development work","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstart\u002FSKILL.md",[191],{"categoryNo":123,"categoryName":124,"taxonomyType":21,"taxonomyTypeDesc":22},[187,193,31,194,195,196,34,197,198,199,200],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":202,"name":178,"nameZh":6,"description":203,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":204,"categories":205,"keywords":206,"publishedAt":44},"01M6DF6QMJ9AJKFKHHKRT005PQ","Interactive project setup — detects your project, configures metaswarm, writes project-local files","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fsetup\u002FSKILL.md",[],[178,180,141,207,182,208],"files","interactive"]