[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71GG185PDMN44K96HNTE095":3,"skill-same:01M71GG185PDMN44K96HNTE095":104},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":42,"linkOnly":43,"markdownContent":44,"markdownBody":45,"frontMatter":46,"refName":47,"commitSha":48,"skillDirectory":49,"forksCount":50,"repositoryHtmlUrl":51,"repositoryHomepageUrl":6,"ownerHtmlUrl":52,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":53,"install":54,"resources":67},"01M71GG185PDMN44K96HNTE095","tooluniverse",null,"Use this skill when working with scientific research tools and workflows across bioinformatics, cheminformatics, genomics, structural biology, proteomics, and drug discovery. This skill provides access to 600+ scientific tools including machine learning models, datasets, APIs, and analysis packages. Use when searching for scientific tools, executing computational biology workflows, composing multi-step research pipelines, accessing databases like OpenTargets\u002FPubChem\u002FUniProt\u002FPDB\u002FChEMBL, performing tool discovery for research tasks, or integrating scientific computational resources into LLM workflows.","JSGforever\u002Fskillguard","JSGforever","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F85541948?v=4","01M71FQD3E132VMR5F4TAYX3YS","01M71FQD4DYW0XJ4XQ4YQH75Y9",2,"GPL-3.0","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__Microck--claude-scientific-skills\u002Fscientific-skills\u002Ftooluniverse\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[5,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41],"access","chembl","scientific","packages","across","tool discovery","tasks","analysis","when","workflows","research tools","computational","biology","pdb","structural","structural biology","computational biology","resources","databases","2026-11-10 10:12:30",false,"---\nname: tooluniverse\ndescription: Use this skill when working with scientific research tools and workflows across bioinformatics, cheminformatics, genomics, structural biology, proteomics, and drug discovery. This skill provides access to 600+ scientific tools including machine learning models, datasets, APIs, and analysis packages. Use when searching for scientific tools, executing computational biology workflows, composing multi-step research pipelines, accessing databases like OpenTargets\u002FPubChem\u002FUniProt\u002FPDB\u002FChEMBL, performing tool discovery for research tasks, or integrating scientific computational resources into LLM workflows.\n---\n\n# ToolUniverse\n\n## Overview\n\nToolUniverse is a unified ecosystem that enables AI agents to function as research scientists by providing standardized access to 600+ scientific resources. Use this skill to discover, execute, and compose scientific tools across multiple research domains including bioinformatics, cheminformatics, genomics, structural biology, proteomics, and drug discovery.\n\n**Key Capabilities:**\n- Access 600+ scientific tools, models, datasets, and APIs\n- Discover tools using natural language, semantic search, or keywords\n- Execute tools through standardized AI-Tool Interaction Protocol\n- Compose multi-step workflows for complex research problems\n- Integration with Claude Desktop\u002FCode via Model Context Protocol (MCP)\n\n## When to Use This Skill\n\nUse this skill when:\n- Searching for scientific tools by function or domain (e.g., \"find protein structure prediction tools\")\n- Executing computational biology workflows (e.g., disease target identification, drug discovery, genomics analysis)\n- Accessing scientific databases (OpenTargets, PubChem, UniProt, PDB, ChEMBL, KEGG, etc.)\n- Composing multi-step research pipelines (e.g., target discovery → structure prediction → virtual screening)\n- Working with bioinformatics, cheminformatics, or structural biology tasks\n- Analyzing gene expression, protein sequences, molecular structures, or clinical data\n- Performing literature searches, pathway enrichment, or variant annotation\n- Building automated scientific research workflows\n\n## Quick Start\n\n### Basic Setup\n```python\nfrom tooluniverse import ToolUniverse\n\n# Initialize and load tools\ntu = ToolUniverse()\ntu.load_tools()  # Loads 600+ scientific tools\n\n# Discover tools\ntools = tu.run({\n    \"name\": \"Tool_Finder_Keyword\",\n    \"arguments\": {\n        \"description\": \"disease target associations\",\n        \"limit\": 10\n    }\n})\n\n# Execute a tool\nresult = tu.run({\n    \"name\": \"OpenTargets_get_associated_targets_by_disease_efoId\",\n    \"arguments\": {\"efoId\": \"EFO_0000537\"}  # Hypertension\n})\n```\n\n### Model Context Protocol (MCP)\nFor Claude Desktop\u002FCode integration:\n```bash\ntooluniverse-smcp\n```\n\n## Core Workflows\n\n### 1. Tool Discovery\n\nFind relevant tools for your research task:\n\n**Three discovery methods:**\n- `Tool_Finder` - Embedding-based semantic search (requires GPU)\n- `Tool_Finder_LLM` - LLM-based semantic search (no GPU required)\n- `Tool_Finder_Keyword` - Fast keyword search\n\n**Example:**\n```python\n# Search by natural language description\ntools = tu.run({\n    \"name\": \"Tool_Finder_LLM\",\n    \"arguments\": {\n        \"description\": \"Find tools for RNA sequencing differential expression analysis\",\n        \"limit\": 10\n    }\n})\n\n# Review available tools\nfor tool in tools:\n    print(f\"{tool['name']}: {tool['description']}\")\n```\n\n**See `references\u002Ftool-discovery.md` for:**\n- Detailed discovery methods and search strategies\n- Domain-specific keyword suggestions\n- Best practices for finding tools\n\n### 2. Tool Execution\n\nExecute individual tools through the standardized interface:\n\n**Example:**\n```python\n# Execute disease-target lookup\ntargets = tu.run({\n    \"name\": \"OpenTargets_get_associated_targets_by_disease_efoId\",\n    \"arguments\": {\"efoId\": \"EFO_0000616\"}  # Breast cancer\n})\n\n# Get protein structure\nstructure = tu.run({\n    \"name\": \"AlphaFold_get_structure\",\n    \"arguments\": {\"uniprot_id\": \"P12345\"}\n})\n\n# Calculate molecular properties\nproperties = tu.run({\n    \"name\": \"RDKit_calculate_descriptors\",\n    \"arguments\": {\"smiles\": \"CCO\"}  # Ethanol\n})\n```\n\n**See `references\u002Ftool-execution.md` for:**\n- Real-world execution examples across domains\n- Tool parameter handling and validation\n- Result processing and error handling\n- Best practices for production use\n\n### 3. Tool Composition and Workflows\n\nCompose multiple tools for complex research workflows:\n\n**Drug Discovery Example:**\n```python\n# 1. Find disease targets\ntargets = tu.run({\n    \"name\": \"OpenTargets_get_associated_targets_by_disease_efoId\",\n    \"arguments\": {\"efoId\": \"EFO_0000616\"}\n})\n\n# 2. Get protein structures\nstructures = []\nfor target in targets[:5]:\n    structure = tu.run({\n        \"name\": \"AlphaFold_get_structure\",\n        \"arguments\": {\"uniprot_id\": target['uniprot_id']}\n    })\n    structures.append(structure)\n\n# 3. Screen compounds\nhits = []\nfor structure in structures:\n    compounds = tu.run({\n        \"name\": \"ZINC_virtual_screening\",\n        \"arguments\": {\n            \"structure\": structure,\n            \"library\": \"lead-like\",\n            \"top_n\": 100\n        }\n    })\n    hits.extend(compounds)\n\n# 4. Evaluate drug-likeness\ndrug_candidates = []\nfor compound in hits:\n    props = tu.run({\n        \"name\": \"RDKit_calculate_drug_properties\",\n        \"arguments\": {\"smiles\": compound['smiles']}\n    })\n    if props['lipinski_pass']:\n        drug_candidates.append(compound)\n```\n\n**See `references\u002Ftool-composition.md` for:**\n- Complete workflow examples (drug discovery, genomics, clinical)\n- Sequential and parallel tool composition patterns\n- Output processing hooks\n- Workflow best practices\n\n## Scientific Domains\n\nToolUniverse supports 600+ tools across major scientific domains:\n\n**Bioinformatics:**\n- Sequence analysis, alignment, BLAST\n- Gene expression (RNA-seq, DESeq2)\n- Pathway enrichment (KEGG, Reactome, GO)\n- Variant annotation (VEP, ClinVar)\n\n**Cheminformatics:**\n- Molecular descriptors and fingerprints\n- Drug discovery and virtual screening\n- ADMET prediction and drug-likeness\n- Chemical databases (PubChem, ChEMBL, ZINC)\n\n**Structural Biology:**\n- Protein structure prediction (AlphaFold)\n- Structure retrieval (PDB)\n- Binding site detection\n- Protein-protein interactions\n\n**Proteomics:**\n- Mass spectrometry analysis\n- Protein databases (UniProt, STRING)\n- Post-translational modifications\n\n**Genomics:**\n- Genome assembly and annotation\n- Copy number variation\n- Clinical genomics workflows\n\n**Medical\u002FClinical:**\n- Disease databases (OpenTargets, OMIM)\n- Clinical trials and FDA data\n- Variant classification\n\n**See `references\u002Fdomains.md` for:**\n- Complete domain categorization\n- Tool examples by discipline\n- Cross-domain applications\n- Search strategies by domain\n\n## Reference Documentation\n\nThis skill includes comprehensive reference files that provide detailed information for specific aspects:\n\n- **`references\u002Finstallation.md`** - Installation, setup, MCP configuration, platform integration\n- **`references\u002Ftool-discovery.md`** - Discovery methods, search strategies, listing tools\n- **`references\u002Ftool-execution.md`** - Execution patterns, real-world examples, error handling\n- **`references\u002Ftool-composition.md`** - Workflow composition, complex pipelines, parallel execution\n- **`references\u002Fdomains.md`** - Tool categorization by domain, use case examples\n- **`references\u002Fapi_reference.md`** - Python API documentation, hooks, protocols\n\n**Workflow:** When helping with specific tasks, reference the appropriate file for detailed instructions. For example, if searching for tools, consult `references\u002Ftool-discovery.md` for search strategies.\n\n## Example Scripts\n\nTwo executable example scripts demonstrate common use cases:\n\n**`scripts\u002Fexample_tool_search.py`** - Demonstrates all three discovery methods:\n- Keyword-based search\n- LLM-based search\n- Domain-specific searches\n- Getting detailed tool information\n\n**`scripts\u002Fexample_workflow.py`** - Complete workflow examples:\n- Drug discovery pipeline (disease → targets → structures → screening → candidates)\n- Genomics analysis (expression data → differential analysis → pathways)\n\nRun examples to understand typical usage patterns and workflow composition.\n\n## Best Practices\n\n1. **Tool Discovery:**\n   - Start with broad searches, then refine based on results\n   - Use `Tool_Finder_Keyword` for fast searches with known terms\n   - Use `Tool_Finder_LLM` for complex semantic queries\n   - Set appropriate `limit` parameter (default: 10)\n\n2. **Tool Execution:**\n   - Always verify tool parameters before execution\n   - Implement error handling for production workflows\n   - Validate input data formats (SMILES, UniProt IDs, gene symbols)\n   - Check result types and structures\n\n3. **Workflow Composition:**\n   - Test each step individually before composing full workflows\n   - Implement checkpointing for long workflows\n   - Consider rate limits for remote APIs\n   - Use parallel execution when tools are independent\n\n4. **Integration:**\n   - Initialize ToolUniverse once and reuse the instance\n   - Call `load_tools()` once at startup\n   - Cache frequently used tool information\n   - Enable logging for debugging\n\n## Key Terminology\n\n- **Tool**: A scientific resource (model, dataset, API, package) accessible through ToolUniverse\n- **Tool Discovery**: Finding relevant tools using search methods (Finder, LLM, Keyword)\n- **Tool Execution**: Running a tool with specific arguments via `tu.run()`\n- **Tool Composition**: Chaining multiple tools for multi-step workflows\n- **MCP**: Model Context Protocol for integration with Claude Desktop\u002FCode\n- **AI-Tool Interaction Protocol**: Standardized interface for LLM-tool communication\n\n## Resources\n\n- **Official Website**: https:\u002F\u002Faiscientist.tools\n- **GitHub**: https:\u002F\u002Fgithub.com\u002Fmims-harvard\u002FToolUniverse\n- **Documentation**: https:\u002F\u002Fzitniklab.hms.harvard.edu\u002FToolUniverse\u002F\n- **Installation**: `uv uv pip install tooluniverse`\n- **MCP Server**: `tooluniverse-smcp`\n","# ToolUniverse\n\n## Overview\n\nToolUniverse is a unified ecosystem that enables AI agents to function as research scientists by providing standardized access to 600+ scientific resources. Use this skill to discover, execute, and compose scientific tools across multiple research domains including bioinformatics, cheminformatics, genomics, structural biology, proteomics, and drug discovery.\n\n**Key Capabilities:**\n- Access 600+ scientific tools, models, datasets, and APIs\n- Discover tools using natural language, semantic search, or keywords\n- Execute tools through standardized AI-Tool Interaction Protocol\n- Compose multi-step workflows for complex research problems\n- Integration with Claude Desktop\u002FCode via Model Context Protocol (MCP)\n\n## When to Use This Skill\n\nUse this skill when:\n- Searching for scientific tools by function or domain (e.g., \"find protein structure prediction tools\")\n- Executing computational biology workflows (e.g., disease target identification, drug discovery, genomics analysis)\n- Accessing scientific databases (OpenTargets, PubChem, UniProt, PDB, ChEMBL, KEGG, etc.)\n- Composing multi-step research pipelines (e.g., target discovery → structure prediction → virtual screening)\n- Working with bioinformatics, cheminformatics, or structural biology tasks\n- Analyzing gene expression, protein sequences, molecular structures, or clinical data\n- Performing literature searches, pathway enrichment, or variant annotation\n- Building automated scientific research workflows\n\n## Quick Start\n\n### Basic Setup\n```python\nfrom tooluniverse import ToolUniverse\n\n# Initialize and load tools\ntu = ToolUniverse()\ntu.load_tools()  # Loads 600+ scientific tools\n\n# Discover tools\ntools = tu.run({\n    \"name\": \"Tool_Finder_Keyword\",\n    \"arguments\": {\n        \"description\": \"disease target associations\",\n        \"limit\": 10\n    }\n})\n\n# Execute a tool\nresult = tu.run({\n    \"name\": \"OpenTargets_get_associated_targets_by_disease_efoId\",\n    \"arguments\": {\"efoId\": \"EFO_0000537\"}  # Hypertension\n})\n```\n\n### Model Context Protocol (MCP)\nFor Claude Desktop\u002FCode integration:\n```bash\ntooluniverse-smcp\n```\n\n## Core Workflows\n\n### 1. Tool Discovery\n\nFind relevant tools for your research task:\n\n**Three discovery methods:**\n- `Tool_Finder` - Embedding-based semantic search (requires GPU)\n- `Tool_Finder_LLM` - LLM-based semantic search (no GPU required)\n- `Tool_Finder_Keyword` - Fast keyword search\n\n**Example:**\n```python\n# Search by natural language description\ntools = tu.run({\n    \"name\": \"Tool_Finder_LLM\",\n    \"arguments\": {\n        \"description\": \"Find tools for RNA sequencing differential expression analysis\",\n        \"limit\": 10\n    }\n})\n\n# Review available tools\nfor tool in tools:\n    print(f\"{tool['name']}: {tool['description']}\")\n```\n\n**See `references\u002Ftool-discovery.md` for:**\n- Detailed discovery methods and search strategies\n- Domain-specific keyword suggestions\n- Best practices for finding tools\n\n### 2. Tool Execution\n\nExecute individual tools through the standardized interface:\n\n**Example:**\n```python\n# Execute disease-target lookup\ntargets = tu.run({\n    \"name\": \"OpenTargets_get_associated_targets_by_disease_efoId\",\n    \"arguments\": {\"efoId\": \"EFO_0000616\"}  # Breast cancer\n})\n\n# Get protein structure\nstructure = tu.run({\n    \"name\": \"AlphaFold_get_structure\",\n    \"arguments\": {\"uniprot_id\": \"P12345\"}\n})\n\n# Calculate molecular properties\nproperties = tu.run({\n    \"name\": \"RDKit_calculate_descriptors\",\n    \"arguments\": {\"smiles\": \"CCO\"}  # Ethanol\n})\n```\n\n**See `references\u002Ftool-execution.md` for:**\n- Real-world execution examples across domains\n- Tool parameter handling and validation\n- Result processing and error handling\n- Best practices for production use\n\n### 3. Tool Composition and Workflows\n\nCompose multiple tools for complex research workflows:\n\n**Drug Discovery Example:**\n```python\n# 1. Find disease targets\ntargets = tu.run({\n    \"name\": \"OpenTargets_get_associated_targets_by_disease_efoId\",\n    \"arguments\": {\"efoId\": \"EFO_0000616\"}\n})\n\n# 2. Get protein structures\nstructures = []\nfor target in targets[:5]:\n    structure = tu.run({\n        \"name\": \"AlphaFold_get_structure\",\n        \"arguments\": {\"uniprot_id\": target['uniprot_id']}\n    })\n    structures.append(structure)\n\n# 3. Screen compounds\nhits = []\nfor structure in structures:\n    compounds = tu.run({\n        \"name\": \"ZINC_virtual_screening\",\n        \"arguments\": {\n            \"structure\": structure,\n            \"library\": \"lead-like\",\n            \"top_n\": 100\n        }\n    })\n    hits.extend(compounds)\n\n# 4. Evaluate drug-likeness\ndrug_candidates = []\nfor compound in hits:\n    props = tu.run({\n        \"name\": \"RDKit_calculate_drug_properties\",\n        \"arguments\": {\"smiles\": compound['smiles']}\n    })\n    if props['lipinski_pass']:\n        drug_candidates.append(compound)\n```\n\n**See `references\u002Ftool-composition.md` for:**\n- Complete workflow examples (drug discovery, genomics, clinical)\n- Sequential and parallel tool composition patterns\n- Output processing hooks\n- Workflow best practices\n\n## Scientific Domains\n\nToolUniverse supports 600+ tools across major scientific domains:\n\n**Bioinformatics:**\n- Sequence analysis, alignment, BLAST\n- Gene expression (RNA-seq, DESeq2)\n- Pathway enrichment (KEGG, Reactome, GO)\n- Variant annotation (VEP, ClinVar)\n\n**Cheminformatics:**\n- Molecular descriptors and fingerprints\n- Drug discovery and virtual screening\n- ADMET prediction and drug-likeness\n- Chemical databases (PubChem, ChEMBL, ZINC)\n\n**Structural Biology:**\n- Protein structure prediction (AlphaFold)\n- Structure retrieval (PDB)\n- Binding site detection\n- Protein-protein interactions\n\n**Proteomics:**\n- Mass spectrometry analysis\n- Protein databases (UniProt, STRING)\n- Post-translational modifications\n\n**Genomics:**\n- Genome assembly and annotation\n- Copy number variation\n- Clinical genomics workflows\n\n**Medical\u002FClinical:**\n- Disease databases (OpenTargets, OMIM)\n- Clinical trials and FDA data\n- Variant classification\n\n**See `references\u002Fdomains.md` for:**\n- Complete domain categorization\n- Tool examples by discipline\n- Cross-domain applications\n- Search strategies by domain\n\n## Reference Documentation\n\nThis skill includes comprehensive reference files that provide detailed information for specific aspects:\n\n- **`references\u002Finstallation.md`** - Installation, setup, MCP configuration, platform integration\n- **`references\u002Ftool-discovery.md`** - Discovery methods, search strategies, listing tools\n- **`references\u002Ftool-execution.md`** - Execution patterns, real-world examples, error handling\n- **`references\u002Ftool-composition.md`** - Workflow composition, complex pipelines, parallel execution\n- **`references\u002Fdomains.md`** - Tool categorization by domain, use case examples\n- **`references\u002Fapi_reference.md`** - Python API documentation, hooks, protocols\n\n**Workflow:** When helping with specific tasks, reference the appropriate file for detailed instructions. For example, if searching for tools, consult `references\u002Ftool-discovery.md` for search strategies.\n\n## Example Scripts\n\nTwo executable example scripts demonstrate common use cases:\n\n**`scripts\u002Fexample_tool_search.py`** - Demonstrates all three discovery methods:\n- Keyword-based search\n- LLM-based search\n- Domain-specific searches\n- Getting detailed tool information\n\n**`scripts\u002Fexample_workflow.py`** - Complete workflow examples:\n- Drug discovery pipeline (disease → targets → structures → screening → candidates)\n- Genomics analysis (expression data → differential analysis → pathways)\n\nRun examples to understand typical usage patterns and workflow composition.\n\n## Best Practices\n\n1. **Tool Discovery:**\n   - Start with broad searches, then refine based on results\n   - Use `Tool_Finder_Keyword` for fast searches with known terms\n   - Use `Tool_Finder_LLM` for complex semantic queries\n   - Set appropriate `limit` parameter (default: 10)\n\n2. **Tool Execution:**\n   - Always verify tool parameters before execution\n   - Implement error handling for production workflows\n   - Validate input data formats (SMILES, UniProt IDs, gene symbols)\n   - Check result types and structures\n\n3. **Workflow Composition:**\n   - Test each step individually before composing full workflows\n   - Implement checkpointing for long workflows\n   - Consider rate limits for remote APIs\n   - Use parallel execution when tools are independent\n\n4. **Integration:**\n   - Initialize ToolUniverse once and reuse the instance\n   - Call `load_tools()` once at startup\n   - Cache frequently used tool information\n   - Enable logging for debugging\n\n## Key Terminology\n\n- **Tool**: A scientific resource (model, dataset, API, package) accessible through ToolUniverse\n- **Tool Discovery**: Finding relevant tools using search methods (Finder, LLM, Keyword)\n- **Tool Execution**: Running a tool with specific arguments via `tu.run()`\n- **Tool Composition**: Chaining multiple tools for multi-step workflows\n- **MCP**: Model Context Protocol for integration with Claude Desktop\u002FCode\n- **AI-Tool Interaction Protocol**: Standardized interface for LLM-tool communication\n\n## Resources\n\n- **Official Website**: https:\u002F\u002Faiscientist.tools\n- **GitHub**: https:\u002F\u002Fgithub.com\u002Fmims-harvard\u002FToolUniverse\n- **Documentation**: https:\u002F\u002Fzitniklab.hms.harvard.edu\u002FToolUniverse\u002F\n- **Installation**: `uv uv pip install tooluniverse`\n- **MCP Server**: `tooluniverse-smcp`\n",{"name":5,"description":7},"main","f2ec4b3b9133d34eeaf9b38e4b0a97e8e5705a7f","benchmarks\u002Ffinal\u002Fskills\u002Fasset1__Microck--claude-scientific-skills\u002Fscientific-skills\u002Ftooluniverse",0,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard","https:\u002F\u002Fgithub.com\u002FJSGforever","2026-08-29 18:27:56",{"source":8,"skillName":5,"commands":55,"prompt":65,"zipAvailable":66},[56,59,62],{"tool":57,"command":58},"npx","npx skills add JSGforever\u002Fskillguard --skill tooluniverse",{"tool":60,"command":61},"bunx","bunx skills add JSGforever\u002Fskillguard --skill tooluniverse",{"tool":63,"command":64},"pnpm","pnpm dlx skills add JSGforever\u002Fskillguard --skill tooluniverse","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__Microck--claude-scientific-skills\u002Fscientific-skills\u002Ftooluniverse\u002FSKILL.md",true,[68,74,78,82,86,90,94,100],{"path":69,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":72,"sourceHtmlUrl":73},"references\u002Fapi_reference.md","REFERENCE","参考文档",5651,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__Microck--claude-scientific-skills\u002Fscientific-skills\u002Ftooluniverse\u002Freferences\u002Fapi_reference.md",{"path":75,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002Fdomains.md",5850,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__Microck--claude-scientific-skills\u002Fscientific-skills\u002Ftooluniverse\u002Freferences\u002Fdomains.md",{"path":79,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002Finstallation.md",1679,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__Microck--claude-scientific-skills\u002Fscientific-skills\u002Ftooluniverse\u002Freferences\u002Finstallation.md",{"path":83,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":84,"sourceHtmlUrl":85},"references\u002Ftool-composition.md",6372,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__Microck--claude-scientific-skills\u002Fscientific-skills\u002Ftooluniverse\u002Freferences\u002Ftool-composition.md",{"path":87,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":88,"sourceHtmlUrl":89},"references\u002Ftool-discovery.md",3095,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__Microck--claude-scientific-skills\u002Fscientific-skills\u002Ftooluniverse\u002Freferences\u002Ftool-discovery.md",{"path":91,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":92,"sourceHtmlUrl":93},"references\u002Ftool-execution.md",4010,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__Microck--claude-scientific-skills\u002Fscientific-skills\u002Ftooluniverse\u002Freferences\u002Ftool-execution.md",{"path":95,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":98,"sourceHtmlUrl":99},"scripts\u002Fexample_tool_search.py","SCRIPT","脚本",2605,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__Microck--claude-scientific-skills\u002Fscientific-skills\u002Ftooluniverse\u002Fscripts\u002Fexample_tool_search.py",{"path":101,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":102,"sourceHtmlUrl":103},"scripts\u002Fexample_workflow.py",7458,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__Microck--claude-scientific-skills\u002Fscientific-skills\u002Ftooluniverse\u002Fscripts\u002Fexample_workflow.py",[105,131,147,173,195,216],{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":112,"publishedAt":42},"01M71HY2SNXBA9Q00WZDTZQ31Z","skillguard-codex-scanner","Hybrid deterministic+LLM agent-skill security scanner. Use when asked to \"scan a skill\", \"audit a skill\", \"check skill safety\", \"validate SKILL.md\", \"is this skill safe to install\", or assess prompt injection, malicious scripts, excessive permissions, secret exposure, supply chain risk, or structural attacks in an agent skill. Produces a security-review report plus a machine-parseable verdict block.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fsrc\u002Fskillguard\u002Fstatic_scanner\u002Fskillguard-codex-scanner\u002FSKILL.md",[111],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[113,114,115,116,117,118,119,120,37,121,122,123,31,124,125,126,127,128,129,130],"scanner","skillguard codex scanner","skillguard","codex","chain","skill security","security-review","review report","secret","prompt injection","security scanner","review","malicious","permissions","exposure","audit","scripts","safe",{"skillNo":132,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":135,"licenseFileUrl":6,"sourceHtmlUrl":136,"categories":137,"keywords":143,"publishedAt":42},"01M71HY0SPKTT3S27BC2HPAC5M","data-exfiltrator","Analyzes data files","MIT","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Fsmoke-one-skill\u002Fasset1__cisco-ai-defense--data-exfiltrator\u002FSKILL.md",[138],{"categoryNo":139,"categoryName":140,"taxonomyType":141,"taxonomyTypeDesc":142},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[144,145,146],"data","data exfiltrator","files",{"skillNo":148,"name":149,"nameZh":6,"description":150,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":151,"categories":152,"keywords":153,"publishedAt":42},"01M71HXVS9EMN44BGDW215FZ72","real-time-collaboration-engine","Build real-time collaborative editing with WebSockets, OT\u002FCRDT conflict resolution, and presence awareness. Implements cursor tracking, optimistic updates, and offline sync. Use for collaborative editors, whiteboards, video editing. Activate on \"real-time collaboration\", \"WebSocket sync\", \"multiplayer editing\", \"CRDT\", \"presence awareness\". NOT for simple chat, request-response APIs, or single-user apps.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--real-time-collaboration-engine\u002FSKILL.md",[],[154,155,156,157,158,159,160,161,162,163,164,165,23,166,167,168,169,170,171,172],"time","real time collaboration engine","real time collaboration","collaboration","engine","real time","Video","reliability","video editing","performance","conflict resolution","presence","apps","updates","Bash","activate","optimizer","react","streaming",{"skillNo":174,"name":175,"nameZh":6,"description":176,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":177,"categories":178,"keywords":182,"publishedAt":42},"01M71HXP6CTY4KFN0QVMMN0V7J","react-performance-optimizer","Optimize React apps for 60fps performance. Implements memoization, virtualization, code splitting, bundle optimization. Use for slow renders, large lists, bundle bloat. Activate on \"React performance\", \"slow render\", \"useMemo\", \"bundle size\", \"virtualization\". NOT for backend optimization, non-React frameworks, or premature optimization.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--react-performance-optimizer\u002FSKILL.md",[179],{"categoryNo":180,"categoryName":181,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000009","前端开发",[163,183,170,171,184,185,186,187,188,189,154,190,191,166,168,192,169,172,193,194],"react performance optimizer","react performance","performance optimizer","app","nextjs","expert","re","render","2025","code","router","strategies",{"skillNo":196,"name":197,"nameZh":6,"description":198,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":199,"categories":200,"keywords":202,"publishedAt":42},"01M71HXH7QXSQB4QTDZ7SP7YXQ","llm-streaming-response-handler","Build production LLM streaming UIs with Server-Sent Events, real-time token display, cancellation, error recovery. Handles OpenAI\u002FAnthropic\u002FClaude streaming APIs. Use for chatbots, AI assistants, real-time text generation. Activate on \"LLM streaming\", \"SSE\", \"token stream\", \"chat UI\", \"real-time AI\". NOT for batch processing, non-streaming APIs, or WebSocket bidirectional chat.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--llm-streaming-response-handler\u002FSKILL.md",[201],{"categoryNo":180,"categoryName":181,"taxonomyType":20,"taxonomyTypeDesc":21},[203,172,204,205,206,207,163,154,208,209,210,168,169,170,211,171,212,213,214,215],"llm streaming response handler","handler","error","processing","retry","chat ui","error recovery","critical","batch","display","text","server","read",{"skillNo":217,"name":218,"nameZh":6,"description":219,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":220,"categories":221,"keywords":229,"publishedAt":42},"01M71HXCB0E1YRKYW1Y8T0Y106","github-actions-pipeline-builder","Build production CI\u002FCD pipelines with GitHub Actions. Implements matrix builds, caching, deployments, testing, security scanning. Use for automated testing, deployments, release workflows. Activate on \"GitHub Actions\", \"CI\u002FCD\", \"workflow\", \"deployment pipeline\", \"automated testing\". NOT for Jenkins\u002FCircleCI, manual deployments, or non-GitHub repositories.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--github-actions-pipeline-builder\u002FSKILL.md",[222,225,228],{"categoryNo":223,"categoryName":224,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":226,"categoryName":227,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[230,231,232,233,234,235,236,161,188,237,238,32,169,194,239,215,240,241,242,243],"github actions pipeline builder","actions","github actions","pipeline builder","github","builder","pipeline","testing","ci","run","release","write","edit","git"]