[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BJWNWSTMPRNVZHN4GXHTWV":3,"skill-same:01M7BJWNWSTMPRNVZHN4GXHTWV":71},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M7BJWNWSTMPRNVZHN4GXHTWV","biomni",null,"Autonomous biomedical AI agent framework for executing complex research tasks across genomics, drug discovery, molecular biology, and clinical analysis. Use this skill when conducting multi-step biomedical research including CRISPR screening design, single-cell RNA-seq analysis, ADMET prediction, GWAS interpretation, rare disease diagnosis, or lab protocol optimization. Leverages LLM reasoning with code execution and integrated biomedical databases.","YYC-Cube\u002FYYC3-Knowledge-Base","YYC-Cube","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F235006543?v=4","01M79J2PH4SWD2X0825X6PN748","yyc3","01M79J2PHVK3F6ZBYT8K2SCZCW",1,"MIT","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-AI-应用工具\u002FYYC3-AI-应用工具-claude-code-templates-main\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fbiomni\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: biomni\ndescription: Autonomous biomedical AI agent framework for executing complex research tasks across genomics, drug discovery, molecular biology, and clinical analysis. Use this skill when conducting multi-step biomedical research including CRISPR screening design, single-cell RNA-seq analysis, ADMET prediction, GWAS interpretation, rare disease diagnosis, or lab protocol optimization. Leverages LLM reasoning with code execution and integrated biomedical databases.\n---\n\n# Biomni\n\n## Overview\n\nBiomni is an open-source biomedical AI agent framework from Stanford's SNAP lab that autonomously executes complex research tasks across biomedical domains. Use this skill when working on multi-step biological reasoning tasks, analyzing biomedical data, or conducting research spanning genomics, drug discovery, molecular biology, and clinical analysis.\n\n## Core Capabilities\n\nBiomni excels at:\n\n1. **Multi-step biological reasoning** - Autonomous task decomposition and planning for complex biomedical queries\n2. **Code generation and execution** - Dynamic analysis pipeline creation for data processing\n3. **Knowledge retrieval** - Access to ~11GB of integrated biomedical databases and literature\n4. **Cross-domain problem solving** - Unified interface for genomics, proteomics, drug discovery, and clinical tasks\n\n## When to Use This Skill\n\nUse biomni for:\n- **CRISPR screening** - Design screens, prioritize genes, analyze knockout effects\n- **Single-cell RNA-seq** - Cell type annotation, differential expression, trajectory analysis\n- **Drug discovery** - ADMET prediction, target identification, compound optimization\n- **GWAS analysis** - Variant interpretation, causal gene identification, pathway enrichment\n- **Clinical genomics** - Rare disease diagnosis, variant pathogenicity, phenotype-genotype mapping\n- **Lab protocols** - Protocol optimization, literature synthesis, experimental design\n\n## Quick Start\n\n### Installation and Setup\n\nInstall Biomni and configure API keys for LLM providers:\n\n```bash\nuv pip install biomni --upgrade\n```\n\nConfigure API keys (store in `.env` file or environment variables):\n```bash\nexport ANTHROPIC_API_KEY=\"your-key-here\"\n# Optional: OpenAI, Azure, Google, Groq, AWS Bedrock keys\n```\n\nUse `scripts\u002Fsetup_environment.py` for interactive setup assistance.\n\n### Basic Usage Pattern\n\n```python\nfrom biomni.agent import A1\n\n# Initialize agent with data path and LLM choice\nagent = A1(path='.\u002Fdata', llm='claude-sonnet-4-20250514')\n\n# Execute biomedical task autonomously\nagent.go(\"Your biomedical research question or task\")\n\n# Save conversation history and results\nagent.save_conversation_history(\"report.pdf\")\n```\n\n## Working with Biomni\n\n### 1. Agent Initialization\n\nThe A1 class is the primary interface for biomni:\n\n```python\nfrom biomni.agent import A1\nfrom biomni.config import default_config\n\n# Basic initialization\nagent = A1(\n    path='.\u002Fdata',  # Path to data lake (~11GB downloaded on first use)\n    llm='claude-sonnet-4-20250514'  # LLM model selection\n)\n\n# Advanced configuration\ndefault_config.llm = \"gpt-4\"\ndefault_config.timeout_seconds = 1200\ndefault_config.max_iterations = 50\n```\n\n**Supported LLM Providers:**\n- Anthropic Claude (recommended): `claude-sonnet-4-20250514`, `claude-opus-4-20250514`\n- OpenAI: `gpt-4`, `gpt-4-turbo`\n- Azure OpenAI: via Azure configuration\n- Google Gemini: `gemini-2.0-flash-exp`\n- Groq: `llama-3.3-70b-versatile`\n- AWS Bedrock: Various models via Bedrock API\n\nSee `references\u002Fllm_providers.md` for detailed LLM configuration instructions.\n\n### 2. Task Execution Workflow\n\nBiomni follows an autonomous agent workflow:\n\n```python\n# Step 1: Initialize agent\nagent = A1(path='.\u002Fdata', llm='claude-sonnet-4-20250514')\n\n# Step 2: Execute task with natural language query\nresult = agent.go(\"\"\"\nDesign a CRISPR screen to identify genes regulating autophagy in\nHEK293 cells. Prioritize genes based on essentiality and pathway\nrelevance.\n\"\"\")\n\n# Step 3: Review generated code and analysis\n# Agent autonomously:\n# - Decomposes task into sub-steps\n# - Retrieves relevant biological knowledge\n# - Generates and executes analysis code\n# - Interprets results and provides insights\n\n# Step 4: Save results\nagent.save_conversation_history(\"autophagy_screen_report.pdf\")\n```\n\n### 3. Common Task Patterns\n\n#### CRISPR Screening Design\n```python\nagent.go(\"\"\"\nDesign a genome-wide CRISPR knockout screen for identifying genes\naffecting [phenotype] in [cell type]. Include:\n1. sgRNA library design\n2. Gene prioritization criteria\n3. Expected hit genes based on pathway analysis\n\"\"\")\n```\n\n#### Single-Cell RNA-seq Analysis\n```python\nagent.go(\"\"\"\nAnalyze this single-cell RNA-seq dataset:\n- Perform quality control and filtering\n- Identify cell populations via clustering\n- Annotate cell types using marker genes\n- Conduct differential expression between conditions\nFile path: [path\u002Fto\u002Fdata.h5ad]\n\"\"\")\n```\n\n#### Drug ADMET Prediction\n```python\nagent.go(\"\"\"\nPredict ADMET properties for these drug candidates:\n[SMILES strings or compound IDs]\nFocus on:\n- Absorption (Caco-2 permeability, HIA)\n- Distribution (plasma protein binding, BBB penetration)\n- Metabolism (CYP450 interaction)\n- Excretion (clearance)\n- Toxicity (hERG liability, hepatotoxicity)\n\"\"\")\n```\n\n#### GWAS Variant Interpretation\n```python\nagent.go(\"\"\"\nInterpret GWAS results for [trait\u002Fdisease]:\n- Identify genome-wide significant variants\n- Map variants to causal genes\n- Perform pathway enrichment analysis\n- Predict functional consequences\nSummary statistics file: [path\u002Fto\u002Fgwas_summary.txt]\n\"\"\")\n```\n\nSee `references\u002Fuse_cases.md` for comprehensive task examples across all biomedical domains.\n\n### 4. Data Integration\n\nBiomni integrates ~11GB of biomedical knowledge sources:\n- **Gene databases** - Ensembl, NCBI Gene, UniProt\n- **Protein structures** - PDB, AlphaFold\n- **Clinical datasets** - ClinVar, OMIM, HPO\n- **Literature indices** - PubMed abstracts, biomedical ontologies\n- **Pathway databases** - KEGG, Reactome, GO\n\nData is automatically downloaded to the specified `path` on first use.\n\n### 5. MCP Server Integration\n\nExtend biomni with external tools via Model Context Protocol:\n\n```python\n# MCP servers can provide:\n# - FDA drug databases\n# - Web search for literature\n# - Custom biomedical APIs\n# - Laboratory equipment interfaces\n\n# Configure MCP servers in .biomni\u002Fmcp_config.json\n```\n\n### 6. Evaluation Framework\n\nBenchmark agent performance on biomedical tasks:\n\n```python\nfrom biomni.eval import BiomniEval1\n\nevaluator = BiomniEval1()\n\n# Evaluate on specific task types\nscore = evaluator.evaluate(\n    task_type='crispr_design',\n    instance_id='test_001',\n    answer=agent_output\n)\n\n# Access evaluation dataset\ndataset = evaluator.load_dataset()\n```\n\n## Best Practices\n\n### Task Formulation\n- **Be specific** - Include biological context, organism, cell type, conditions\n- **Specify outputs** - Clearly state desired analysis outputs and formats\n- **Provide data paths** - Include file paths for datasets to analyze\n- **Set constraints** - Mention time\u002Fcomputational limits if relevant\n\n### Security Considerations\n⚠️ **Important**: Biomni executes LLM-generated code with full system privileges. For production use:\n- Run in isolated environments (Docker, VMs)\n- Avoid exposing sensitive credentials\n- Review generated code before execution in sensitive contexts\n- Use sandboxed execution environments when possible\n\n### Performance Optimization\n- **Choose appropriate LLMs** - Claude Sonnet 4 recommended for balance of speed\u002Fquality\n- **Set reasonable timeouts** - Adjust `default_config.timeout_seconds` for complex tasks\n- **Monitor iterations** - Track `max_iterations` to prevent runaway loops\n- **Cache data** - Reuse downloaded data lake across sessions\n\n### Result Documentation\n```python\n# Always save conversation history for reproducibility\nagent.save_conversation_history(\"results\u002Fproject_name_YYYYMMDD.pdf\")\n\n# Include in reports:\n# - Original task description\n# - Generated analysis code\n# - Results and interpretations\n# - Data sources used\n```\n\n## Resources\n\n### References\nDetailed documentation available in the `references\u002F` directory:\n\n- **`api_reference.md`** - Complete API documentation for A1 class, configuration, and evaluation\n- **`llm_providers.md`** - LLM provider setup (Anthropic, OpenAI, Azure, Google, Groq, AWS)\n- **`use_cases.md`** - Comprehensive task examples for all biomedical domains\n\n### Scripts\nHelper scripts in the `scripts\u002F` directory:\n\n- **`setup_environment.py`** - Interactive environment and API key configuration\n- **`generate_report.py`** - Enhanced PDF report generation with custom formatting\n\n### External Resources\n- **GitHub**: https:\u002F\u002Fgithub.com\u002Fsnap-stanford\u002Fbiomni\n- **Web Platform**: https:\u002F\u002Fbiomni.stanford.edu\n- **Paper**: https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.05.30.656746v1\n- **Model**: https:\u002F\u002Fhuggingface.co\u002Fbiomni\u002FBiomni-R0-32B-Preview\n- **Evaluation Dataset**: https:\u002F\u002Fhuggingface.co\u002Fdatasets\u002Fbiomni\u002FEval1\n\n## Troubleshooting\n\n### Common Issues\n\n**Data download fails**\n```python\n# Manually trigger data lake download\nagent = A1(path='.\u002Fdata', llm='your-llm')\n# First .go() call will download data\n```\n\n**API key errors**\n```bash\n# Verify environment variables\necho $ANTHROPIC_API_KEY\n# Or check .env file in working directory\n```\n\n**Timeout on complex tasks**\n```python\nfrom biomni.config import default_config\ndefault_config.timeout_seconds = 3600  # 1 hour\n```\n\n**Memory issues with large datasets**\n- Use streaming for large files\n- Process data in chunks\n- Increase system memory allocation\n\n### Getting Help\n\nFor issues or questions:\n- GitHub Issues: https:\u002F\u002Fgithub.com\u002Fsnap-stanford\u002Fbiomni\u002Fissues\n- Documentation: Check `references\u002F` files for detailed guidance\n- Community: Stanford SNAP lab and biomni contributors\n","# Biomni\n\n## Overview\n\nBiomni is an open-source biomedical AI agent framework from Stanford's SNAP lab that autonomously executes complex research tasks across biomedical domains. Use this skill when working on multi-step biological reasoning tasks, analyzing biomedical data, or conducting research spanning genomics, drug discovery, molecular biology, and clinical analysis.\n\n## Core Capabilities\n\nBiomni excels at:\n\n1. **Multi-step biological reasoning** - Autonomous task decomposition and planning for complex biomedical queries\n2. **Code generation and execution** - Dynamic analysis pipeline creation for data processing\n3. **Knowledge retrieval** - Access to ~11GB of integrated biomedical databases and literature\n4. **Cross-domain problem solving** - Unified interface for genomics, proteomics, drug discovery, and clinical tasks\n\n## When to Use This Skill\n\nUse biomni for:\n- **CRISPR screening** - Design screens, prioritize genes, analyze knockout effects\n- **Single-cell RNA-seq** - Cell type annotation, differential expression, trajectory analysis\n- **Drug discovery** - ADMET prediction, target identification, compound optimization\n- **GWAS analysis** - Variant interpretation, causal gene identification, pathway enrichment\n- **Clinical genomics** - Rare disease diagnosis, variant pathogenicity, phenotype-genotype mapping\n- **Lab protocols** - Protocol optimization, literature synthesis, experimental design\n\n## Quick Start\n\n### Installation and Setup\n\nInstall Biomni and configure API keys for LLM providers:\n\n```bash\nuv pip install biomni --upgrade\n```\n\nConfigure API keys (store in `.env` file or environment variables):\n```bash\nexport ANTHROPIC_API_KEY=\"your-key-here\"\n# Optional: OpenAI, Azure, Google, Groq, AWS Bedrock keys\n```\n\nUse `scripts\u002Fsetup_environment.py` for interactive setup assistance.\n\n### Basic Usage Pattern\n\n```python\nfrom biomni.agent import A1\n\n# Initialize agent with data path and LLM choice\nagent = A1(path='.\u002Fdata', llm='claude-sonnet-4-20250514')\n\n# Execute biomedical task autonomously\nagent.go(\"Your biomedical research question or task\")\n\n# Save conversation history and results\nagent.save_conversation_history(\"report.pdf\")\n```\n\n## Working with Biomni\n\n### 1. Agent Initialization\n\nThe A1 class is the primary interface for biomni:\n\n```python\nfrom biomni.agent import A1\nfrom biomni.config import default_config\n\n# Basic initialization\nagent = A1(\n    path='.\u002Fdata',  # Path to data lake (~11GB downloaded on first use)\n    llm='claude-sonnet-4-20250514'  # LLM model selection\n)\n\n# Advanced configuration\ndefault_config.llm = \"gpt-4\"\ndefault_config.timeout_seconds = 1200\ndefault_config.max_iterations = 50\n```\n\n**Supported LLM Providers:**\n- Anthropic Claude (recommended): `claude-sonnet-4-20250514`, `claude-opus-4-20250514`\n- OpenAI: `gpt-4`, `gpt-4-turbo`\n- Azure OpenAI: via Azure configuration\n- Google Gemini: `gemini-2.0-flash-exp`\n- Groq: `llama-3.3-70b-versatile`\n- AWS Bedrock: Various models via Bedrock API\n\nSee `references\u002Fllm_providers.md` for detailed LLM configuration instructions.\n\n### 2. Task Execution Workflow\n\nBiomni follows an autonomous agent workflow:\n\n```python\n# Step 1: Initialize agent\nagent = A1(path='.\u002Fdata', llm='claude-sonnet-4-20250514')\n\n# Step 2: Execute task with natural language query\nresult = agent.go(\"\"\"\nDesign a CRISPR screen to identify genes regulating autophagy in\nHEK293 cells. Prioritize genes based on essentiality and pathway\nrelevance.\n\"\"\")\n\n# Step 3: Review generated code and analysis\n# Agent autonomously:\n# - Decomposes task into sub-steps\n# - Retrieves relevant biological knowledge\n# - Generates and executes analysis code\n# - Interprets results and provides insights\n\n# Step 4: Save results\nagent.save_conversation_history(\"autophagy_screen_report.pdf\")\n```\n\n### 3. Common Task Patterns\n\n#### CRISPR Screening Design\n```python\nagent.go(\"\"\"\nDesign a genome-wide CRISPR knockout screen for identifying genes\naffecting [phenotype] in [cell type]. Include:\n1. sgRNA library design\n2. Gene prioritization criteria\n3. Expected hit genes based on pathway analysis\n\"\"\")\n```\n\n#### Single-Cell RNA-seq Analysis\n```python\nagent.go(\"\"\"\nAnalyze this single-cell RNA-seq dataset:\n- Perform quality control and filtering\n- Identify cell populations via clustering\n- Annotate cell types using marker genes\n- Conduct differential expression between conditions\nFile path: [path\u002Fto\u002Fdata.h5ad]\n\"\"\")\n```\n\n#### Drug ADMET Prediction\n```python\nagent.go(\"\"\"\nPredict ADMET properties for these drug candidates:\n[SMILES strings or compound IDs]\nFocus on:\n- Absorption (Caco-2 permeability, HIA)\n- Distribution (plasma protein binding, BBB penetration)\n- Metabolism (CYP450 interaction)\n- Excretion (clearance)\n- Toxicity (hERG liability, hepatotoxicity)\n\"\"\")\n```\n\n#### GWAS Variant Interpretation\n```python\nagent.go(\"\"\"\nInterpret GWAS results for [trait\u002Fdisease]:\n- Identify genome-wide significant variants\n- Map variants to causal genes\n- Perform pathway enrichment analysis\n- Predict functional consequences\nSummary statistics file: [path\u002Fto\u002Fgwas_summary.txt]\n\"\"\")\n```\n\nSee `references\u002Fuse_cases.md` for comprehensive task examples across all biomedical domains.\n\n### 4. Data Integration\n\nBiomni integrates ~11GB of biomedical knowledge sources:\n- **Gene databases** - Ensembl, NCBI Gene, UniProt\n- **Protein structures** - PDB, AlphaFold\n- **Clinical datasets** - ClinVar, OMIM, HPO\n- **Literature indices** - PubMed abstracts, biomedical ontologies\n- **Pathway databases** - KEGG, Reactome, GO\n\nData is automatically downloaded to the specified `path` on first use.\n\n### 5. MCP Server Integration\n\nExtend biomni with external tools via Model Context Protocol:\n\n```python\n# MCP servers can provide:\n# - FDA drug databases\n# - Web search for literature\n# - Custom biomedical APIs\n# - Laboratory equipment interfaces\n\n# Configure MCP servers in .biomni\u002Fmcp_config.json\n```\n\n### 6. Evaluation Framework\n\nBenchmark agent performance on biomedical tasks:\n\n```python\nfrom biomni.eval import BiomniEval1\n\nevaluator = BiomniEval1()\n\n# Evaluate on specific task types\nscore = evaluator.evaluate(\n    task_type='crispr_design',\n    instance_id='test_001',\n    answer=agent_output\n)\n\n# Access evaluation dataset\ndataset = evaluator.load_dataset()\n```\n\n## Best Practices\n\n### Task Formulation\n- **Be specific** - Include biological context, organism, cell type, conditions\n- **Specify outputs** - Clearly state desired analysis outputs and formats\n- **Provide data paths** - Include file paths for datasets to analyze\n- **Set constraints** - Mention time\u002Fcomputational limits if relevant\n\n### Security Considerations\n⚠️ **Important**: Biomni executes LLM-generated code with full system privileges. For production use:\n- Run in isolated environments (Docker, VMs)\n- Avoid exposing sensitive credentials\n- Review generated code before execution in sensitive contexts\n- Use sandboxed execution environments when possible\n\n### Performance Optimization\n- **Choose appropriate LLMs** - Claude Sonnet 4 recommended for balance of speed\u002Fquality\n- **Set reasonable timeouts** - Adjust `default_config.timeout_seconds` for complex tasks\n- **Monitor iterations** - Track `max_iterations` to prevent runaway loops\n- **Cache data** - Reuse downloaded data lake across sessions\n\n### Result Documentation\n```python\n# Always save conversation history for reproducibility\nagent.save_conversation_history(\"results\u002Fproject_name_YYYYMMDD.pdf\")\n\n# Include in reports:\n# - Original task description\n# - Generated analysis code\n# - Results and interpretations\n# - Data sources used\n```\n\n## Resources\n\n### References\nDetailed documentation available in the `references\u002F` directory:\n\n- **`api_reference.md`** - Complete API documentation for A1 class, configuration, and evaluation\n- **`llm_providers.md`** - LLM provider setup (Anthropic, OpenAI, Azure, Google, Groq, AWS)\n- **`use_cases.md`** - Comprehensive task examples for all biomedical domains\n\n### Scripts\nHelper scripts in the `scripts\u002F` directory:\n\n- **`setup_environment.py`** - Interactive environment and API key configuration\n- **`generate_report.py`** - Enhanced PDF report generation with custom formatting\n\n### External Resources\n- **GitHub**: https:\u002F\u002Fgithub.com\u002Fsnap-stanford\u002Fbiomni\n- **Web Platform**: https:\u002F\u002Fbiomni.stanford.edu\n- **Paper**: https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.1101\u002F2025.05.30.656746v1\n- **Model**: https:\u002F\u002Fhuggingface.co\u002Fbiomni\u002FBiomni-R0-32B-Preview\n- **Evaluation Dataset**: https:\u002F\u002Fhuggingface.co\u002Fdatasets\u002Fbiomni\u002FEval1\n\n## Troubleshooting\n\n### Common Issues\n\n**Data download fails**\n```python\n# Manually trigger data lake download\nagent = A1(path='.\u002Fdata', llm='your-llm')\n# First .go() call will download data\n```\n\n**API key errors**\n```bash\n# Verify environment variables\necho $ANTHROPIC_API_KEY\n# Or check .env file in working directory\n```\n\n**Timeout on complex tasks**\n```python\nfrom biomni.config import default_config\ndefault_config.timeout_seconds = 3600  # 1 hour\n```\n\n**Memory issues with large datasets**\n- Use streaming for large files\n- Process data in chunks\n- Increase system memory allocation\n\n### Getting Help\n\nFor issues or questions:\n- GitHub Issues: https:\u002F\u002Fgithub.com\u002Fsnap-stanford\u002Fbiomni\u002Fissues\n- Documentation: Check `references\u002F` files for detailed guidance\n- Community: Stanford SNAP lab and biomni contributors\n",{"name":5,"description":7},"main","87afe6ce96220accf50a345dea46784c8c9f210e","YYC3-AI-应用工具\u002FYYC3-AI-应用工具-claude-code-templates-main\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fbiomni",0,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base","https:\u002F\u002Fkb.yyc3.top\u002F","https:\u002F\u002Fgithub.com\u002FYYC-Cube","万象归元于云枢 | 深栈智启新纪元","2026-11-10 10:37:32",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill biomni",{"tool":39,"command":40},"bunx","bunx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill biomni",{"tool":42,"command":43},"pnpm","pnpm dlx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill biomni","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-AI-应用工具\u002FYYC3-AI-应用工具-claude-code-templates-main\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fbiomni\u002FSKILL.md",true,[47,53,57,61,67],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fapi_reference.md","REFERENCE","参考文档",11422,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-AI-应用工具\u002FYYC3-AI-应用工具-claude-code-templates-main\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fbiomni\u002Freferences\u002Fapi_reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fllm_providers.md",11080,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-AI-应用工具\u002FYYC3-AI-应用工具-claude-code-templates-main\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fbiomni\u002Freferences\u002Fllm_providers.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fuse_cases.md",22619,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-AI-应用工具\u002FYYC3-AI-应用工具-claude-code-templates-main\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fbiomni\u002Freferences\u002Fuse_cases.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fgenerate_report.py","SCRIPT","脚本",10810,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-AI-应用工具\u002FYYC3-AI-应用工具-claude-code-templates-main\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fbiomni\u002Fscripts\u002Fgenerate_report.py",{"path":68,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Fsetup_environment.py",10542,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-AI-应用工具\u002FYYC3-AI-应用工具-claude-code-templates-main\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fbiomni\u002Fscripts\u002Fsetup_environment.py",[72,79,86,93,100,107],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M7CTDWHERCXPQCP0K03A86AS","vercel-sandbox","Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across commands, or wants ephemeral isolated browser environments. Triggers include \"Vercel Sandbox browser\", \"microVM Chrome\", \"agent-browser in sandbox\", \"browser automation on Vercel\", or any task requiring Chrome in a Vercel Sandbox.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fvercel-sandbox\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M7CTD8D2BNJY54S65M47HEJA","slack","Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include \"check my Slack\", \"what channels have unreads\", \"send a message to\", \"search Slack for\", \"extract from Slack\", \"find who said\", or any task requiring programmatic Slack interaction.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fslack\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M7CTCSSB8ZP3Q58C3YZDZK1W","electron","Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include \"automate Slack app\", \"control VS Code\", \"interact with Discord app\", \"test this Electron app\", \"connect to desktop app\", or any task requiring automation of a native Electron application.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Felectron\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M7CTCBJY76688V4DCZGWFHGQ","dogfood","Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to \"dogfood\", \"QA\", \"exploratory test\", \"find issues\", \"bug hunt\", \"test this app\u002Fsite\u002Fplatform\", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fdogfood\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":19},"01M7CTC4H0FFGVEAQR9PA4GA1A","agent-browser","Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to \"open a website\", \"fill out a form\", \"click a button\", \"take a screenshot\", \"scrape data from a page\", \"test this web app\", \"login to a site\", \"automate browser actions\", or any task requiring programmatic web interaction.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fagent-browser\u002FSKILL.md",[],[],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":19},"01M7CTBKVFYBG78FDSABSDJTTQ","shadcn","Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn\u002Fui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for \"shadcn init\", \"create an app with --preset\", \"switch to --preset\", and for building a design system or applying a DESIGN.md or brand spec to shadcn\u002Fui.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-UI-界面组件\u002FYYC3-UI-界面组件-ui\u002Fskills\u002Fshadcn\u002FSKILL.md",[],[]]