[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6BXJJDPMFVZG4QMNPZTPVR9":3,"skill-same:01M6BXJJDPMFVZG4QMNPZTPVR9":62},{"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":26,"publishedAt":34,"linkOnly":35,"markdownContent":36,"markdownBody":37,"frontMatter":38,"refName":39,"commitSha":40,"skillDirectory":41,"forksCount":42,"repositoryHtmlUrl":43,"repositoryHomepageUrl":6,"ownerHtmlUrl":44,"ownerBlogUrl":45,"ownerDescription":46,"updatedAt":47,"install":48,"resources":61},"01M6BXJJDPMFVZG4QMNPZTPVR9","AgentDB Vector Search",null,"Implement semantic vector search with AgentDB for intelligent document retrieval, similarity matching, and context-aware querying. Use when building RAG systems, semantic search engines, or intelligent knowledge bases.","diegopacheco\u002Fai-playground","diegopacheco","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F121278?v=4","01M6BXCP8P7GGSJ8M1W2MFDTGT","Diego Pacheco","01M6BXCPD3WM51H465XW9YM4BV",21,"Unlicense","https:\u002F\u002Fgithub.com\u002Fdiegopacheco\u002Fai-playground\u002Fblob\u002Fmain\u002Fpocs\u002Fclaude-flow-fun\u002F.claude\u002Fskills\u002Fagentdb-vector-search\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[27,28,29,5,30,31,32,33],"search","vector","Vector Search","implement","rag","semantic search","knowledge","2026-11-10 10:12:30",false,"---\nname: \"AgentDB Vector Search\"\ndescription: \"Implement semantic vector search with AgentDB for intelligent document retrieval, similarity matching, and context-aware querying. Use when building RAG systems, semantic search engines, or intelligent knowledge bases.\"\n---\n\n# AgentDB Vector Search\n\n## What This Skill Does\n\nImplements vector-based semantic search using AgentDB's high-performance vector database with **150x-12,500x faster** operations than traditional solutions. Features HNSW indexing, quantization, and sub-millisecond search (\u003C100µs).\n\n## Prerequisites\n\n- Node.js 18+\n- AgentDB v1.0.7+ (via agentic-flow or standalone)\n- OpenAI API key (for embeddings) or custom embedding model\n\n## Quick Start with CLI\n\n### Initialize Vector Database\n\n```bash\n# Initialize with default dimensions (1536 for OpenAI ada-002)\nnpx agentdb@latest init .\u002Fvectors.db\n\n# Custom dimensions for different embedding models\nnpx agentdb@latest init .\u002Fvectors.db --dimension 768  # sentence-transformers\nnpx agentdb@latest init .\u002Fvectors.db --dimension 384  # all-MiniLM-L6-v2\n\n# Use preset configurations\nnpx agentdb@latest init .\u002Fvectors.db --preset small   # \u003C10K vectors\nnpx agentdb@latest init .\u002Fvectors.db --preset medium  # 10K-100K vectors\nnpx agentdb@latest init .\u002Fvectors.db --preset large   # >100K vectors\n\n# In-memory database for testing\nnpx agentdb@latest init .\u002Fvectors.db --in-memory\n```\n\n### Query Vector Database\n\n```bash\n# Basic similarity search\nnpx agentdb@latest query .\u002Fvectors.db \"[0.1,0.2,0.3,...]\"\n\n# Top-k results\nnpx agentdb@latest query .\u002Fvectors.db \"[0.1,0.2,0.3]\" -k 10\n\n# With similarity threshold (cosine similarity)\nnpx agentdb@latest query .\u002Fvectors.db \"0.1 0.2 0.3\" -t 0.75 -m cosine\n\n# Different distance metrics\nnpx agentdb@latest query .\u002Fvectors.db \"[...]\" -m euclidean  # L2 distance\nnpx agentdb@latest query .\u002Fvectors.db \"[...]\" -m dot        # Dot product\n\n# JSON output for automation\nnpx agentdb@latest query .\u002Fvectors.db \"[...]\" -f json -k 5\n\n# Verbose output with distances\nnpx agentdb@latest query .\u002Fvectors.db \"[...]\" -v\n```\n\n### Import\u002FExport Vectors\n\n```bash\n# Export vectors to JSON\nnpx agentdb@latest export .\u002Fvectors.db .\u002Fbackup.json\n\n# Import vectors from JSON\nnpx agentdb@latest import .\u002Fbackup.json\n\n# Get database statistics\nnpx agentdb@latest stats .\u002Fvectors.db\n```\n\n## Quick Start with API\n\n```typescript\nimport { createAgentDBAdapter, computeEmbedding } from 'agentic-flow\u002Freasoningbank';\n\n\u002F\u002F Initialize with vector search optimizations\nconst adapter = await createAgentDBAdapter({\n  dbPath: '.agentdb\u002Fvectors.db',\n  enableLearning: false,       \u002F\u002F Vector search only\n  enableReasoning: true,       \u002F\u002F Enable semantic matching\n  quantizationType: 'binary',  \u002F\u002F 32x memory reduction\n  cacheSize: 1000,             \u002F\u002F Fast retrieval\n});\n\n\u002F\u002F Store document with embedding\nconst text = \"The quantum computer achieved 100 qubits\";\nconst embedding = await computeEmbedding(text);\n\nawait adapter.insertPattern({\n  id: '',\n  type: 'document',\n  domain: 'technology',\n  pattern_data: JSON.stringify({\n    embedding,\n    text,\n    metadata: { category: \"quantum\", date: \"2025-01-15\" }\n  }),\n  confidence: 1.0,\n  usage_count: 0,\n  success_count: 0,\n  created_at: Date.now(),\n  last_used: Date.now(),\n});\n\n\u002F\u002F Semantic search with MMR (Maximal Marginal Relevance)\nconst queryEmbedding = await computeEmbedding(\"quantum computing advances\");\nconst results = await adapter.retrieveWithReasoning(queryEmbedding, {\n  domain: 'technology',\n  k: 10,\n  useMMR: true,              \u002F\u002F Diverse results\n  synthesizeContext: true,    \u002F\u002F Rich context\n});\n```\n\n## Core Features\n\n### 1. Vector Storage\n```typescript\n\u002F\u002F Store with automatic embedding\nawait db.storeWithEmbedding({\n  content: \"Your document text\",\n  metadata: { source: \"docs\", page: 42 }\n});\n```\n\n### 2. Similarity Search\n```typescript\n\u002F\u002F Find similar documents\nconst similar = await db.findSimilar(\"quantum computing\", {\n  limit: 5,\n  minScore: 0.75\n});\n```\n\n### 3. Hybrid Search (Vector + Metadata)\n```typescript\n\u002F\u002F Combine vector similarity with metadata filtering\nconst results = await db.hybridSearch({\n  query: \"machine learning models\",\n  filters: {\n    category: \"research\",\n    date: { $gte: \"2024-01-01\" }\n  },\n  limit: 20\n});\n```\n\n## Advanced Usage\n\n### RAG (Retrieval Augmented Generation)\n```typescript\n\u002F\u002F Build RAG pipeline\nasync function ragQuery(question: string) {\n  \u002F\u002F 1. Get relevant context\n  const context = await db.searchSimilar(\n    await embed(question),\n    { limit: 5, threshold: 0.7 }\n  );\n\n  \u002F\u002F 2. Generate answer with context\n  const prompt = `Context: ${context.map(c => c.text).join('\\n')}\nQuestion: ${question}`;\n\n  return await llm.generate(prompt);\n}\n```\n\n### Batch Operations\n```typescript\n\u002F\u002F Efficient batch storage\nawait db.batchStore(documents.map(doc => ({\n  text: doc.content,\n  embedding: doc.vector,\n  metadata: doc.meta\n})));\n```\n\n## MCP Server Integration\n\n```bash\n# Start AgentDB MCP server for Claude Code\nnpx agentdb@latest mcp\n\n# Add to Claude Code (one-time setup)\nclaude mcp add agentdb npx agentdb@latest mcp\n\n# Now use MCP tools in Claude Code:\n# - agentdb_query: Semantic vector search\n# - agentdb_store: Store documents with embeddings\n# - agentdb_stats: Database statistics\n```\n\n## Performance Benchmarks\n\n```bash\n# Run comprehensive benchmarks\nnpx agentdb@latest benchmark\n\n# Results:\n# ✅ Pattern Search: 150x faster (100µs vs 15ms)\n# ✅ Batch Insert: 500x faster (2ms vs 1s for 100 vectors)\n# ✅ Large-scale Query: 12,500x faster (8ms vs 100s at 1M vectors)\n# ✅ Memory Efficiency: 4-32x reduction with quantization\n```\n\n## Quantization Options\n\nAgentDB provides multiple quantization strategies for memory efficiency:\n\n### Binary Quantization (32x reduction)\n```typescript\nconst adapter = await createAgentDBAdapter({\n  quantizationType: 'binary',  \u002F\u002F 768-dim → 96 bytes\n});\n```\n\n### Scalar Quantization (4x reduction)\n```typescript\nconst adapter = await createAgentDBAdapter({\n  quantizationType: 'scalar',  \u002F\u002F 768-dim → 768 bytes\n});\n```\n\n### Product Quantization (8-16x reduction)\n```typescript\nconst adapter = await createAgentDBAdapter({\n  quantizationType: 'product',  \u002F\u002F 768-dim → 48-96 bytes\n});\n```\n\n## Distance Metrics\n\n```bash\n# Cosine similarity (default, best for most use cases)\nnpx agentdb@latest query .\u002Fdb.sqlite \"[...]\" -m cosine\n\n# Euclidean distance (L2 norm)\nnpx agentdb@latest query .\u002Fdb.sqlite \"[...]\" -m euclidean\n\n# Dot product (for normalized vectors)\nnpx agentdb@latest query .\u002Fdb.sqlite \"[...]\" -m dot\n```\n\n## Advanced Features\n\n### HNSW Indexing\n- **O(log n) search complexity**\n- **Sub-millisecond retrieval** (\u003C100µs)\n- **Automatic index building**\n\n### Caching\n- **1000 pattern in-memory cache**\n- **\u003C1ms pattern retrieval**\n- **Automatic cache invalidation**\n\n### MMR (Maximal Marginal Relevance)\n- **Diverse result sets**\n- **Avoid redundancy**\n- **Balance relevance and diversity**\n\n## Performance Tips\n\n1. **Enable HNSW indexing**: Automatic with AgentDB, 10-100x faster\n2. **Use quantization**: Binary (32x), Scalar (4x), Product (8-16x) memory reduction\n3. **Batch operations**: 500x faster for bulk inserts\n4. **Match dimensions**: 1536 (OpenAI), 768 (sentence-transformers), 384 (MiniLM)\n5. **Similarity threshold**: Start at 0.7 for quality, adjust based on use case\n6. **Enable caching**: 1000 pattern cache for frequent queries\n\n## Troubleshooting\n\n### Issue: Slow search performance\n```bash\n# Check if HNSW indexing is enabled (automatic)\nnpx agentdb@latest stats .\u002Fvectors.db\n\n# Expected: \u003C100µs search time\n```\n\n### Issue: High memory usage\n```bash\n# Enable binary quantization (32x reduction)\n# Use in adapter: quantizationType: 'binary'\n```\n\n### Issue: Poor relevance\n```bash\n# Adjust similarity threshold\nnpx agentdb@latest query .\u002Fdb.sqlite \"[...]\" -t 0.8  # Higher threshold\n\n# Or use MMR for diverse results\n# Use in adapter: useMMR: true\n```\n\n### Issue: Wrong dimensions\n```bash\n# Check embedding model dimensions:\n# - OpenAI ada-002: 1536\n# - sentence-transformers: 768\n# - all-MiniLM-L6-v2: 384\n\nnpx agentdb@latest init .\u002Fdb.sqlite --dimension 768\n```\n\n## Database Statistics\n\n```bash\n# Get comprehensive stats\nnpx agentdb@latest stats .\u002Fvectors.db\n\n# Shows:\n# - Total patterns\u002Fvectors\n# - Database size\n# - Average confidence\n# - Domains distribution\n# - Index status\n```\n\n## Performance Characteristics\n\n- **Vector Search**: \u003C100µs (HNSW indexing)\n- **Pattern Retrieval**: \u003C1ms (with cache)\n- **Batch Insert**: 2ms for 100 vectors\n- **Memory Efficiency**: 4-32x reduction with quantization\n- **Scalability**: Handles 1M+ vectors efficiently\n- **Latency**: Sub-millisecond for most operations\n\n## Learn More\n\n- GitHub: https:\u002F\u002Fgithub.com\u002Fruvnet\u002Fagentic-flow\u002Ftree\u002Fmain\u002Fpackages\u002Fagentdb\n- Documentation: node_modules\u002Fagentic-flow\u002Fdocs\u002FAGENTDB_INTEGRATION.md\n- MCP Integration: `npx agentdb@latest mcp` for Claude Code\n- Website: https:\u002F\u002Fagentdb.ruv.io\n- CLI Help: `npx agentdb@latest --help`\n- Command Help: `npx agentdb@latest help \u003Ccommand>`\n","# AgentDB Vector Search\n\n## What This Skill Does\n\nImplements vector-based semantic search using AgentDB's high-performance vector database with **150x-12,500x faster** operations than traditional solutions. Features HNSW indexing, quantization, and sub-millisecond search (\u003C100µs).\n\n## Prerequisites\n\n- Node.js 18+\n- AgentDB v1.0.7+ (via agentic-flow or standalone)\n- OpenAI API key (for embeddings) or custom embedding model\n\n## Quick Start with CLI\n\n### Initialize Vector Database\n\n```bash\n# Initialize with default dimensions (1536 for OpenAI ada-002)\nnpx agentdb@latest init .\u002Fvectors.db\n\n# Custom dimensions for different embedding models\nnpx agentdb@latest init .\u002Fvectors.db --dimension 768  # sentence-transformers\nnpx agentdb@latest init .\u002Fvectors.db --dimension 384  # all-MiniLM-L6-v2\n\n# Use preset configurations\nnpx agentdb@latest init .\u002Fvectors.db --preset small   # \u003C10K vectors\nnpx agentdb@latest init .\u002Fvectors.db --preset medium  # 10K-100K vectors\nnpx agentdb@latest init .\u002Fvectors.db --preset large   # >100K vectors\n\n# In-memory database for testing\nnpx agentdb@latest init .\u002Fvectors.db --in-memory\n```\n\n### Query Vector Database\n\n```bash\n# Basic similarity search\nnpx agentdb@latest query .\u002Fvectors.db \"[0.1,0.2,0.3,...]\"\n\n# Top-k results\nnpx agentdb@latest query .\u002Fvectors.db \"[0.1,0.2,0.3]\" -k 10\n\n# With similarity threshold (cosine similarity)\nnpx agentdb@latest query .\u002Fvectors.db \"0.1 0.2 0.3\" -t 0.75 -m cosine\n\n# Different distance metrics\nnpx agentdb@latest query .\u002Fvectors.db \"[...]\" -m euclidean  # L2 distance\nnpx agentdb@latest query .\u002Fvectors.db \"[...]\" -m dot        # Dot product\n\n# JSON output for automation\nnpx agentdb@latest query .\u002Fvectors.db \"[...]\" -f json -k 5\n\n# Verbose output with distances\nnpx agentdb@latest query .\u002Fvectors.db \"[...]\" -v\n```\n\n### Import\u002FExport Vectors\n\n```bash\n# Export vectors to JSON\nnpx agentdb@latest export .\u002Fvectors.db .\u002Fbackup.json\n\n# Import vectors from JSON\nnpx agentdb@latest import .\u002Fbackup.json\n\n# Get database statistics\nnpx agentdb@latest stats .\u002Fvectors.db\n```\n\n## Quick Start with API\n\n```typescript\nimport { createAgentDBAdapter, computeEmbedding } from 'agentic-flow\u002Freasoningbank';\n\n\u002F\u002F Initialize with vector search optimizations\nconst adapter = await createAgentDBAdapter({\n  dbPath: '.agentdb\u002Fvectors.db',\n  enableLearning: false,       \u002F\u002F Vector search only\n  enableReasoning: true,       \u002F\u002F Enable semantic matching\n  quantizationType: 'binary',  \u002F\u002F 32x memory reduction\n  cacheSize: 1000,             \u002F\u002F Fast retrieval\n});\n\n\u002F\u002F Store document with embedding\nconst text = \"The quantum computer achieved 100 qubits\";\nconst embedding = await computeEmbedding(text);\n\nawait adapter.insertPattern({\n  id: '',\n  type: 'document',\n  domain: 'technology',\n  pattern_data: JSON.stringify({\n    embedding,\n    text,\n    metadata: { category: \"quantum\", date: \"2025-01-15\" }\n  }),\n  confidence: 1.0,\n  usage_count: 0,\n  success_count: 0,\n  created_at: Date.now(),\n  last_used: Date.now(),\n});\n\n\u002F\u002F Semantic search with MMR (Maximal Marginal Relevance)\nconst queryEmbedding = await computeEmbedding(\"quantum computing advances\");\nconst results = await adapter.retrieveWithReasoning(queryEmbedding, {\n  domain: 'technology',\n  k: 10,\n  useMMR: true,              \u002F\u002F Diverse results\n  synthesizeContext: true,    \u002F\u002F Rich context\n});\n```\n\n## Core Features\n\n### 1. Vector Storage\n```typescript\n\u002F\u002F Store with automatic embedding\nawait db.storeWithEmbedding({\n  content: \"Your document text\",\n  metadata: { source: \"docs\", page: 42 }\n});\n```\n\n### 2. Similarity Search\n```typescript\n\u002F\u002F Find similar documents\nconst similar = await db.findSimilar(\"quantum computing\", {\n  limit: 5,\n  minScore: 0.75\n});\n```\n\n### 3. Hybrid Search (Vector + Metadata)\n```typescript\n\u002F\u002F Combine vector similarity with metadata filtering\nconst results = await db.hybridSearch({\n  query: \"machine learning models\",\n  filters: {\n    category: \"research\",\n    date: { $gte: \"2024-01-01\" }\n  },\n  limit: 20\n});\n```\n\n## Advanced Usage\n\n### RAG (Retrieval Augmented Generation)\n```typescript\n\u002F\u002F Build RAG pipeline\nasync function ragQuery(question: string) {\n  \u002F\u002F 1. Get relevant context\n  const context = await db.searchSimilar(\n    await embed(question),\n    { limit: 5, threshold: 0.7 }\n  );\n\n  \u002F\u002F 2. Generate answer with context\n  const prompt = `Context: ${context.map(c => c.text).join('\\n')}\nQuestion: ${question}`;\n\n  return await llm.generate(prompt);\n}\n```\n\n### Batch Operations\n```typescript\n\u002F\u002F Efficient batch storage\nawait db.batchStore(documents.map(doc => ({\n  text: doc.content,\n  embedding: doc.vector,\n  metadata: doc.meta\n})));\n```\n\n## MCP Server Integration\n\n```bash\n# Start AgentDB MCP server for Claude Code\nnpx agentdb@latest mcp\n\n# Add to Claude Code (one-time setup)\nclaude mcp add agentdb npx agentdb@latest mcp\n\n# Now use MCP tools in Claude Code:\n# - agentdb_query: Semantic vector search\n# - agentdb_store: Store documents with embeddings\n# - agentdb_stats: Database statistics\n```\n\n## Performance Benchmarks\n\n```bash\n# Run comprehensive benchmarks\nnpx agentdb@latest benchmark\n\n# Results:\n# ✅ Pattern Search: 150x faster (100µs vs 15ms)\n# ✅ Batch Insert: 500x faster (2ms vs 1s for 100 vectors)\n# ✅ Large-scale Query: 12,500x faster (8ms vs 100s at 1M vectors)\n# ✅ Memory Efficiency: 4-32x reduction with quantization\n```\n\n## Quantization Options\n\nAgentDB provides multiple quantization strategies for memory efficiency:\n\n### Binary Quantization (32x reduction)\n```typescript\nconst adapter = await createAgentDBAdapter({\n  quantizationType: 'binary',  \u002F\u002F 768-dim → 96 bytes\n});\n```\n\n### Scalar Quantization (4x reduction)\n```typescript\nconst adapter = await createAgentDBAdapter({\n  quantizationType: 'scalar',  \u002F\u002F 768-dim → 768 bytes\n});\n```\n\n### Product Quantization (8-16x reduction)\n```typescript\nconst adapter = await createAgentDBAdapter({\n  quantizationType: 'product',  \u002F\u002F 768-dim → 48-96 bytes\n});\n```\n\n## Distance Metrics\n\n```bash\n# Cosine similarity (default, best for most use cases)\nnpx agentdb@latest query .\u002Fdb.sqlite \"[...]\" -m cosine\n\n# Euclidean distance (L2 norm)\nnpx agentdb@latest query .\u002Fdb.sqlite \"[...]\" -m euclidean\n\n# Dot product (for normalized vectors)\nnpx agentdb@latest query .\u002Fdb.sqlite \"[...]\" -m dot\n```\n\n## Advanced Features\n\n### HNSW Indexing\n- **O(log n) search complexity**\n- **Sub-millisecond retrieval** (\u003C100µs)\n- **Automatic index building**\n\n### Caching\n- **1000 pattern in-memory cache**\n- **\u003C1ms pattern retrieval**\n- **Automatic cache invalidation**\n\n### MMR (Maximal Marginal Relevance)\n- **Diverse result sets**\n- **Avoid redundancy**\n- **Balance relevance and diversity**\n\n## Performance Tips\n\n1. **Enable HNSW indexing**: Automatic with AgentDB, 10-100x faster\n2. **Use quantization**: Binary (32x), Scalar (4x), Product (8-16x) memory reduction\n3. **Batch operations**: 500x faster for bulk inserts\n4. **Match dimensions**: 1536 (OpenAI), 768 (sentence-transformers), 384 (MiniLM)\n5. **Similarity threshold**: Start at 0.7 for quality, adjust based on use case\n6. **Enable caching**: 1000 pattern cache for frequent queries\n\n## Troubleshooting\n\n### Issue: Slow search performance\n```bash\n# Check if HNSW indexing is enabled (automatic)\nnpx agentdb@latest stats .\u002Fvectors.db\n\n# Expected: \u003C100µs search time\n```\n\n### Issue: High memory usage\n```bash\n# Enable binary quantization (32x reduction)\n# Use in adapter: quantizationType: 'binary'\n```\n\n### Issue: Poor relevance\n```bash\n# Adjust similarity threshold\nnpx agentdb@latest query .\u002Fdb.sqlite \"[...]\" -t 0.8  # Higher threshold\n\n# Or use MMR for diverse results\n# Use in adapter: useMMR: true\n```\n\n### Issue: Wrong dimensions\n```bash\n# Check embedding model dimensions:\n# - OpenAI ada-002: 1536\n# - sentence-transformers: 768\n# - all-MiniLM-L6-v2: 384\n\nnpx agentdb@latest init .\u002Fdb.sqlite --dimension 768\n```\n\n## Database Statistics\n\n```bash\n# Get comprehensive stats\nnpx agentdb@latest stats .\u002Fvectors.db\n\n# Shows:\n# - Total patterns\u002Fvectors\n# - Database size\n# - Average confidence\n# - Domains distribution\n# - Index status\n```\n\n## Performance Characteristics\n\n- **Vector Search**: \u003C100µs (HNSW indexing)\n- **Pattern Retrieval**: \u003C1ms (with cache)\n- **Batch Insert**: 2ms for 100 vectors\n- **Memory Efficiency**: 4-32x reduction with quantization\n- **Scalability**: Handles 1M+ vectors efficiently\n- **Latency**: Sub-millisecond for most operations\n\n## Learn More\n\n- GitHub: https:\u002F\u002Fgithub.com\u002Fruvnet\u002Fagentic-flow\u002Ftree\u002Fmain\u002Fpackages\u002Fagentdb\n- Documentation: node_modules\u002Fagentic-flow\u002Fdocs\u002FAGENTDB_INTEGRATION.md\n- MCP Integration: `npx agentdb@latest mcp` for Claude Code\n- Website: https:\u002F\u002Fagentdb.ruv.io\n- CLI Help: `npx agentdb@latest --help`\n- Command Help: `npx agentdb@latest help \u003Ccommand>`\n",{"name":5,"description":7},"main","90d379e95fcc23dd9759654c345424e1752b0f3a","pocs\u002Fclaude-flow-fun\u002F.claude\u002Fskills\u002Fagentdb-vector-search",9,"https:\u002F\u002Fgithub.com\u002Fdiegopacheco\u002Fai-playground","https:\u002F\u002Fgithub.com\u002Fdiegopacheco","http:\u002F\u002Fdiego-pacheco.blogspot.com","Brazilian Hands-on Software Architect | 20+ years in Tech | Author | Father. Opinions are my own!","2026-11-15 01:01:48",{"source":8,"skillName":5,"commands":49,"prompt":59,"zipAvailable":60},[50,53,56],{"tool":51,"command":52},"npx","npx skills add diegopacheco\u002Fai-playground --skill \"AgentDB Vector Search\"",{"tool":54,"command":55},"bunx","bunx skills add diegopacheco\u002Fai-playground --skill \"AgentDB Vector Search\"",{"tool":57,"command":58},"pnpm","pnpm dlx skills add diegopacheco\u002Fai-playground --skill \"AgentDB Vector Search\"","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdiegopacheco\u002Fai-playground\u002Fblob\u002Fmain\u002Fpocs\u002Fclaude-flow-fun\u002F.claude\u002Fskills\u002Fagentdb-vector-search\u002FSKILL.md",true,[],[63,79,89,102,118,137],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":72,"publishedAt":34},"01M6WJ537DN520XY8MSW9ZV0RP","word-count","Counts the words, lines and characters of a text or a file.","https:\u002F\u002Fgithub.com\u002Fdiegopacheco\u002Fai-playground\u002Fblob\u002Fmain\u002Fpocs\u002Fskills-gateway-router\u002Fupstream-skills\u002Ftext-skills\u002Fword-count\u002FSKILL.md",[69],{"categoryNo":70,"categoryName":71,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000002","文档处理",[73,74,75,76,77,78],"count","word count","Word","characters","text","file",{"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":34},"01M6WJ4Y2GT5SECWAKKYHGES4F","slugify","Turns a title or a sentence into a URL slug, lowercase words joined by hyphens with accents removed.","https:\u002F\u002Fgithub.com\u002Fdiegopacheco\u002Fai-playground\u002Fblob\u002Fmain\u002Fpocs\u002Fskills-gateway-router\u002Fupstream-skills\u002Ftext-skills\u002Fslugify\u002FSKILL.md",[],[81,86,87,88],"title","with","URL",{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":34},"01M6WJ4V9CWHT9NVCD441VK5MH","json-format","Validates a JSON file and pretty prints it with two space indentation, or reports where the JSON is invalid.","https:\u002F\u002Fgithub.com\u002Fdiegopacheco\u002Fai-playground\u002Fblob\u002Fmain\u002Fpocs\u002Fskills-gateway-router\u002Fupstream-skills\u002Fdev-skills\u002Fjson-format\u002FSKILL.md",[],[96,97,98,78,99,100,101,87],"json","format","json format","reports","invalid","it",{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":34},"01M6WJ4QMRKW8EFP71F4KS2DHE","commit-message","Writes a conventional commit message for the staged git changes.","https:\u002F\u002Fgithub.com\u002Fdiegopacheco\u002Fai-playground\u002Fblob\u002Fmain\u002Fpocs\u002Fskills-gateway-router\u002Fupstream-skills\u002Fdev-skills\u002Fcommit-message\u002FSKILL.md",[],[109,110,111,112,113,114,115,116,117],"commit","commit message","message","git","conventional commit","for","changes","staged","conventional commit message",{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":124,"publishedAt":34},"01M6WJ4MAM2CJH0GWYXFBB9GQC","skills-gateway","Gateway and router to a catalog of skills that are not registered directly. Use it before any task a specialized skill could handle, such as text, JSON or git chores. It finds the right skill and loads its instructions.","https:\u002F\u002Fgithub.com\u002Fdiegopacheco\u002Fai-playground\u002Fblob\u002Fmain\u002Fpocs\u002Fskills-gateway-router\u002F.claude\u002Fskills\u002Fskills-gateway\u002FSKILL.md",[],[125,126,101,127,128,112,129,96,77,130,131,132,133,134,135,136],"skills gateway","gateway","task","loads","Bash","node","specialized","instructions","catalog","use","router","as",{"skillNo":138,"name":139,"nameZh":6,"description":140,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":141,"categories":142,"keywords":143,"publishedAt":34},"01M6M2PYJJQKMWGX7XT7ZJK0H3","decision-log","Record, list, show and supersede architecture decisions that persist across sessions in the shared agent infra state store. Use when the user says \"record this decision\", \"log an ADR\", \"what did we decide about\", \"list decisions\", or \"supersede decision\".","https:\u002F\u002Fgithub.com\u002Fdiegopacheco\u002Fai-playground\u002Fblob\u002Fmain\u002Fpocs\u002Fagent-skills-infra-poc\u002Fskills\u002Fdecision-log\u002FSKILL.md",[],[144,145,146,147,148,149,150,151,152,153,134,154,155,156,157,158,159,160,161,162],"decision log","log","decision","persist","architecture","state","adr","decide","decisions","list","show","infra","record","across","shared","store","about","supersede","sessions"]