[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BPANEXCVV2P9SJAQJ3CW9S":3,"skill-same:01M7BPANEXCVV2P9SJAQJ3CW9S":47},{"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},"01M7BPANEXCVV2P9SJAQJ3CW9S","ReasoningBank with AgentDB",null,"Implement ReasoningBank adaptive learning with AgentDB's 150x faster vector database. Includes trajectory tracking, verdict judgment, memory distillation, and pattern recognition. Use when building self-learning agents, optimizing decision-making, or implementing experience replay systems.","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-Agent-智能体\u002FYYC3-Agent-智能体-ruflo\u002Fv3\u002F@claude-flow\u002Fmcp\u002F.claude\u002Fskills\u002Freasoningbank-agentdb\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: \"ReasoningBank with AgentDB\"\ndescription: \"Implement ReasoningBank adaptive learning with AgentDB's 150x faster vector database. Includes trajectory tracking, verdict judgment, memory distillation, and pattern recognition. Use when building self-learning agents, optimizing decision-making, or implementing experience replay systems.\"\n---\n\n# ReasoningBank with AgentDB\n\n## What This Skill Does\n\nProvides ReasoningBank adaptive learning patterns using AgentDB's high-performance backend (150x-12,500x faster). Enables agents to learn from experiences, judge outcomes, distill memories, and improve decision-making over time with 100% backward compatibility.\n\n**Performance**: 150x faster pattern retrieval, 500x faster batch operations, \u003C1ms memory access.\n\n## Prerequisites\n\n- Node.js 18+\n- AgentDB v1.0.7+ (via agentic-flow)\n- Understanding of reinforcement learning concepts (optional)\n\n---\n\n## Quick Start with CLI\n\n### Initialize ReasoningBank Database\n\n```bash\n# Initialize AgentDB for ReasoningBank\nnpx agentdb@latest init .\u002F.agentdb\u002Freasoningbank.db --dimension 1536\n\n# Start MCP server for Claude Code integration\nnpx agentdb@latest mcp\nclaude mcp add agentdb npx agentdb@latest mcp\n```\n\n### Migrate from Legacy ReasoningBank\n\n```bash\n# Automatic migration with validation\nnpx agentdb@latest migrate --source .swarm\u002Fmemory.db\n\n# Verify migration\nnpx agentdb@latest stats .\u002F.agentdb\u002Freasoningbank.db\n```\n\n---\n\n## Quick Start with API\n\n```typescript\nimport { createAgentDBAdapter, computeEmbedding } from 'agentic-flow\u002Freasoningbank';\n\n\u002F\u002F Initialize ReasoningBank with AgentDB\nconst rb = await createAgentDBAdapter({\n  dbPath: '.agentdb\u002Freasoningbank.db',\n  enableLearning: true,      \u002F\u002F Enable learning plugins\n  enableReasoning: true,      \u002F\u002F Enable reasoning agents\n  cacheSize: 1000,            \u002F\u002F 1000 pattern cache\n});\n\n\u002F\u002F Store successful experience\nconst query = \"How to optimize database queries?\";\nconst embedding = await computeEmbedding(query);\n\nawait rb.insertPattern({\n  id: '',\n  type: 'experience',\n  domain: 'database-optimization',\n  pattern_data: JSON.stringify({\n    embedding,\n    pattern: {\n      query,\n      approach: 'indexing + query optimization',\n      outcome: 'success',\n      metrics: { latency_reduction: 0.85 }\n    }\n  }),\n  confidence: 0.95,\n  usage_count: 1,\n  success_count: 1,\n  created_at: Date.now(),\n  last_used: Date.now(),\n});\n\n\u002F\u002F Retrieve similar experiences with reasoning\nconst result = await rb.retrieveWithReasoning(embedding, {\n  domain: 'database-optimization',\n  k: 5,\n  useMMR: true,              \u002F\u002F Diverse results\n  synthesizeContext: true,    \u002F\u002F Rich context synthesis\n});\n\nconsole.log('Memories:', result.memories);\nconsole.log('Context:', result.context);\nconsole.log('Patterns:', result.patterns);\n```\n\n---\n\n## Core ReasoningBank Concepts\n\n### 1. Trajectory Tracking\n\nTrack agent execution paths and outcomes:\n\n```typescript\n\u002F\u002F Record trajectory (sequence of actions)\nconst trajectory = {\n  task: 'optimize-api-endpoint',\n  steps: [\n    { action: 'analyze-bottleneck', result: 'found N+1 query' },\n    { action: 'add-eager-loading', result: 'reduced queries' },\n    { action: 'add-caching', result: 'improved latency' }\n  ],\n  outcome: 'success',\n  metrics: { latency_before: 2500, latency_after: 150 }\n};\n\nconst embedding = await computeEmbedding(JSON.stringify(trajectory));\n\nawait rb.insertPattern({\n  id: '',\n  type: 'trajectory',\n  domain: 'api-optimization',\n  pattern_data: JSON.stringify({ embedding, pattern: trajectory }),\n  confidence: 0.9,\n  usage_count: 1,\n  success_count: 1,\n  created_at: Date.now(),\n  last_used: Date.now(),\n});\n```\n\n### 2. Verdict Judgment\n\nJudge whether a trajectory was successful:\n\n```typescript\n\u002F\u002F Retrieve similar past trajectories\nconst similar = await rb.retrieveWithReasoning(queryEmbedding, {\n  domain: 'api-optimization',\n  k: 10,\n});\n\n\u002F\u002F Judge based on similarity to successful patterns\nconst verdict = similar.memories.filter(m =>\n  m.pattern.outcome === 'success' &&\n  m.similarity > 0.8\n).length > 5 ? 'likely_success' : 'needs_review';\n\nconsole.log('Verdict:', verdict);\nconsole.log('Confidence:', similar.memories[0]?.similarity || 0);\n```\n\n### 3. Memory Distillation\n\nConsolidate similar experiences into patterns:\n\n```typescript\n\u002F\u002F Get all experiences in domain\nconst experiences = await rb.retrieveWithReasoning(embedding, {\n  domain: 'api-optimization',\n  k: 100,\n  optimizeMemory: true,  \u002F\u002F Automatic consolidation\n});\n\n\u002F\u002F Distill into high-level pattern\nconst distilledPattern = {\n  domain: 'api-optimization',\n  pattern: 'For N+1 queries: add eager loading, then cache',\n  success_rate: 0.92,\n  sample_size: experiences.memories.length,\n  confidence: 0.95\n};\n\nawait rb.insertPattern({\n  id: '',\n  type: 'distilled-pattern',\n  domain: 'api-optimization',\n  pattern_data: JSON.stringify({\n    embedding: await computeEmbedding(JSON.stringify(distilledPattern)),\n    pattern: distilledPattern\n  }),\n  confidence: 0.95,\n  usage_count: 0,\n  success_count: 0,\n  created_at: Date.now(),\n  last_used: Date.now(),\n});\n```\n\n---\n\n## Integration with Reasoning Agents\n\nAgentDB provides 4 reasoning modules that enhance ReasoningBank:\n\n### 1. PatternMatcher\n\nFind similar successful patterns:\n\n```typescript\nconst result = await rb.retrieveWithReasoning(queryEmbedding, {\n  domain: 'problem-solving',\n  k: 10,\n  useMMR: true,  \u002F\u002F Maximal Marginal Relevance for diversity\n});\n\n\u002F\u002F PatternMatcher returns diverse, relevant memories\nresult.memories.forEach(mem => {\n  console.log(`Pattern: ${mem.pattern.approach}`);\n  console.log(`Similarity: ${mem.similarity}`);\n  console.log(`Success Rate: ${mem.success_count \u002F mem.usage_count}`);\n});\n```\n\n### 2. ContextSynthesizer\n\nGenerate rich context from multiple memories:\n\n```typescript\nconst result = await rb.retrieveWithReasoning(queryEmbedding, {\n  domain: 'code-optimization',\n  synthesizeContext: true,  \u002F\u002F Enable context synthesis\n  k: 5,\n});\n\n\u002F\u002F ContextSynthesizer creates coherent narrative\nconsole.log('Synthesized Context:', result.context);\n\u002F\u002F \"Based on 5 similar optimizations, the most effective approach\n\u002F\u002F  involves profiling, identifying bottlenecks, and applying targeted\n\u002F\u002F  improvements. Success rate: 87%\"\n```\n\n### 3. MemoryOptimizer\n\nAutomatically consolidate and prune:\n\n```typescript\nconst result = await rb.retrieveWithReasoning(queryEmbedding, {\n  domain: 'testing',\n  optimizeMemory: true,  \u002F\u002F Enable automatic optimization\n});\n\n\u002F\u002F MemoryOptimizer consolidates similar patterns and prunes low-quality\nconsole.log('Optimizations:', result.optimizations);\n\u002F\u002F { consolidated: 15, pruned: 3, improved_quality: 0.12 }\n```\n\n### 4. ExperienceCurator\n\nFilter by quality and relevance:\n\n```typescript\nconst result = await rb.retrieveWithReasoning(queryEmbedding, {\n  domain: 'debugging',\n  k: 20,\n  minConfidence: 0.8,  \u002F\u002F Only high-confidence experiences\n});\n\n\u002F\u002F ExperienceCurator returns only quality experiences\nresult.memories.forEach(mem => {\n  console.log(`Confidence: ${mem.confidence}`);\n  console.log(`Success Rate: ${mem.success_count \u002F mem.usage_count}`);\n});\n```\n\n---\n\n## Legacy API Compatibility\n\nAgentDB maintains 100% backward compatibility with legacy ReasoningBank:\n\n```typescript\nimport {\n  retrieveMemories,\n  judgeTrajectory,\n  distillMemories\n} from 'agentic-flow\u002Freasoningbank';\n\n\u002F\u002F Legacy API works unchanged (uses AgentDB backend automatically)\nconst memories = await retrieveMemories(query, {\n  domain: 'code-generation',\n  agent: 'coder'\n});\n\nconst verdict = await judgeTrajectory(trajectory, query);\n\nconst newMemories = await distillMemories(\n  trajectory,\n  verdict,\n  query,\n  { domain: 'code-generation' }\n);\n```\n\n---\n\n## Performance Characteristics\n\n- **Pattern Search**: 150x faster (100µs vs 15ms)\n- **Memory Retrieval**: \u003C1ms (with cache)\n- **Batch Insert**: 500x faster (2ms vs 1s for 100 patterns)\n- **Trajectory Judgment**: \u003C5ms (including retrieval + analysis)\n- **Memory Distillation**: \u003C50ms (consolidate 100 patterns)\n\n---\n\n## Advanced Patterns\n\n### Hierarchical Memory\n\nOrganize memories by abstraction level:\n\n```typescript\n\u002F\u002F Low-level: Specific implementation\nawait rb.insertPattern({\n  type: 'concrete',\n  domain: 'debugging\u002Fnull-pointer',\n  pattern_data: JSON.stringify({\n    embedding,\n    pattern: { bug: 'NPE in UserService.getUser()', fix: 'Add null check' }\n  }),\n  confidence: 0.9,\n  \u002F\u002F ...\n});\n\n\u002F\u002F Mid-level: Pattern across similar cases\nawait rb.insertPattern({\n  type: 'pattern',\n  domain: 'debugging',\n  pattern_data: JSON.stringify({\n    embedding,\n    pattern: { category: 'null-pointer', approach: 'defensive-checks' }\n  }),\n  confidence: 0.85,\n  \u002F\u002F ...\n});\n\n\u002F\u002F High-level: General principle\nawait rb.insertPattern({\n  type: 'principle',\n  domain: 'software-engineering',\n  pattern_data: JSON.stringify({\n    embedding,\n    pattern: { principle: 'fail-fast with clear errors' }\n  }),\n  confidence: 0.95,\n  \u002F\u002F ...\n});\n```\n\n### Multi-Domain Learning\n\nTransfer learning across domains:\n\n```typescript\n\u002F\u002F Learn from backend optimization\nconst backendExperience = await rb.retrieveWithReasoning(embedding, {\n  domain: 'backend-optimization',\n  k: 10,\n});\n\n\u002F\u002F Apply to frontend optimization\nconst transferredKnowledge = backendExperience.memories.map(mem => ({\n  ...mem,\n  domain: 'frontend-optimization',\n  adapted: true,\n}));\n```\n\n---\n\n## CLI Operations\n\n### Database Management\n\n```bash\n# Export trajectories and patterns\nnpx agentdb@latest export .\u002F.agentdb\u002Freasoningbank.db .\u002Fbackup.json\n\n# Import experiences\nnpx agentdb@latest import .\u002Fexperiences.json\n\n# Get statistics\nnpx agentdb@latest stats .\u002F.agentdb\u002Freasoningbank.db\n# Shows: total patterns, domains, confidence distribution\n```\n\n### Migration\n\n```bash\n# Migrate from legacy ReasoningBank\nnpx agentdb@latest migrate --source .swarm\u002Fmemory.db --target .agentdb\u002Freasoningbank.db\n\n# Validate migration\nnpx agentdb@latest stats .agentdb\u002Freasoningbank.db\n```\n\n---\n\n## Troubleshooting\n\n### Issue: Migration fails\n```bash\n# Check source database exists\nls -la .swarm\u002Fmemory.db\n\n# Run with verbose logging\nDEBUG=agentdb:* npx agentdb@latest migrate --source .swarm\u002Fmemory.db\n```\n\n### Issue: Low confidence scores\n```typescript\n\u002F\u002F Enable context synthesis for better quality\nconst result = await rb.retrieveWithReasoning(embedding, {\n  synthesizeContext: true,\n  useMMR: true,\n  k: 10,\n});\n```\n\n### Issue: Memory growing too large\n```typescript\n\u002F\u002F Enable automatic optimization\nconst result = await rb.retrieveWithReasoning(embedding, {\n  optimizeMemory: true,  \u002F\u002F Consolidates similar patterns\n});\n\n\u002F\u002F Or manually optimize\nawait rb.optimize();\n```\n\n---\n\n## Learn More\n\n- **AgentDB Integration**: node_modules\u002Fagentic-flow\u002Fdocs\u002FAGENTDB_INTEGRATION.md\n- **GitHub**: https:\u002F\u002Fgithub.com\u002Fruvnet\u002Fagentic-flow\u002Ftree\u002Fmain\u002Fpackages\u002Fagentdb\n- **MCP Integration**: `npx agentdb@latest mcp`\n- **Website**: https:\u002F\u002Fagentdb.ruv.io\n\n---\n\n**Category**: Machine Learning \u002F Reinforcement Learning\n**Difficulty**: Intermediate\n**Estimated Time**: 20-30 minutes\n","# ReasoningBank with AgentDB\n\n## What This Skill Does\n\nProvides ReasoningBank adaptive learning patterns using AgentDB's high-performance backend (150x-12,500x faster). Enables agents to learn from experiences, judge outcomes, distill memories, and improve decision-making over time with 100% backward compatibility.\n\n**Performance**: 150x faster pattern retrieval, 500x faster batch operations, \u003C1ms memory access.\n\n## Prerequisites\n\n- Node.js 18+\n- AgentDB v1.0.7+ (via agentic-flow)\n- Understanding of reinforcement learning concepts (optional)\n\n---\n\n## Quick Start with CLI\n\n### Initialize ReasoningBank Database\n\n```bash\n# Initialize AgentDB for ReasoningBank\nnpx agentdb@latest init .\u002F.agentdb\u002Freasoningbank.db --dimension 1536\n\n# Start MCP server for Claude Code integration\nnpx agentdb@latest mcp\nclaude mcp add agentdb npx agentdb@latest mcp\n```\n\n### Migrate from Legacy ReasoningBank\n\n```bash\n# Automatic migration with validation\nnpx agentdb@latest migrate --source .swarm\u002Fmemory.db\n\n# Verify migration\nnpx agentdb@latest stats .\u002F.agentdb\u002Freasoningbank.db\n```\n\n---\n\n## Quick Start with API\n\n```typescript\nimport { createAgentDBAdapter, computeEmbedding } from 'agentic-flow\u002Freasoningbank';\n\n\u002F\u002F Initialize ReasoningBank with AgentDB\nconst rb = await createAgentDBAdapter({\n  dbPath: '.agentdb\u002Freasoningbank.db',\n  enableLearning: true,      \u002F\u002F Enable learning plugins\n  enableReasoning: true,      \u002F\u002F Enable reasoning agents\n  cacheSize: 1000,            \u002F\u002F 1000 pattern cache\n});\n\n\u002F\u002F Store successful experience\nconst query = \"How to optimize database queries?\";\nconst embedding = await computeEmbedding(query);\n\nawait rb.insertPattern({\n  id: '',\n  type: 'experience',\n  domain: 'database-optimization',\n  pattern_data: JSON.stringify({\n    embedding,\n    pattern: {\n      query,\n      approach: 'indexing + query optimization',\n      outcome: 'success',\n      metrics: { latency_reduction: 0.85 }\n    }\n  }),\n  confidence: 0.95,\n  usage_count: 1,\n  success_count: 1,\n  created_at: Date.now(),\n  last_used: Date.now(),\n});\n\n\u002F\u002F Retrieve similar experiences with reasoning\nconst result = await rb.retrieveWithReasoning(embedding, {\n  domain: 'database-optimization',\n  k: 5,\n  useMMR: true,              \u002F\u002F Diverse results\n  synthesizeContext: true,    \u002F\u002F Rich context synthesis\n});\n\nconsole.log('Memories:', result.memories);\nconsole.log('Context:', result.context);\nconsole.log('Patterns:', result.patterns);\n```\n\n---\n\n## Core ReasoningBank Concepts\n\n### 1. Trajectory Tracking\n\nTrack agent execution paths and outcomes:\n\n```typescript\n\u002F\u002F Record trajectory (sequence of actions)\nconst trajectory = {\n  task: 'optimize-api-endpoint',\n  steps: [\n    { action: 'analyze-bottleneck', result: 'found N+1 query' },\n    { action: 'add-eager-loading', result: 'reduced queries' },\n    { action: 'add-caching', result: 'improved latency' }\n  ],\n  outcome: 'success',\n  metrics: { latency_before: 2500, latency_after: 150 }\n};\n\nconst embedding = await computeEmbedding(JSON.stringify(trajectory));\n\nawait rb.insertPattern({\n  id: '',\n  type: 'trajectory',\n  domain: 'api-optimization',\n  pattern_data: JSON.stringify({ embedding, pattern: trajectory }),\n  confidence: 0.9,\n  usage_count: 1,\n  success_count: 1,\n  created_at: Date.now(),\n  last_used: Date.now(),\n});\n```\n\n### 2. Verdict Judgment\n\nJudge whether a trajectory was successful:\n\n```typescript\n\u002F\u002F Retrieve similar past trajectories\nconst similar = await rb.retrieveWithReasoning(queryEmbedding, {\n  domain: 'api-optimization',\n  k: 10,\n});\n\n\u002F\u002F Judge based on similarity to successful patterns\nconst verdict = similar.memories.filter(m =>\n  m.pattern.outcome === 'success' &&\n  m.similarity > 0.8\n).length > 5 ? 'likely_success' : 'needs_review';\n\nconsole.log('Verdict:', verdict);\nconsole.log('Confidence:', similar.memories[0]?.similarity || 0);\n```\n\n### 3. Memory Distillation\n\nConsolidate similar experiences into patterns:\n\n```typescript\n\u002F\u002F Get all experiences in domain\nconst experiences = await rb.retrieveWithReasoning(embedding, {\n  domain: 'api-optimization',\n  k: 100,\n  optimizeMemory: true,  \u002F\u002F Automatic consolidation\n});\n\n\u002F\u002F Distill into high-level pattern\nconst distilledPattern = {\n  domain: 'api-optimization',\n  pattern: 'For N+1 queries: add eager loading, then cache',\n  success_rate: 0.92,\n  sample_size: experiences.memories.length,\n  confidence: 0.95\n};\n\nawait rb.insertPattern({\n  id: '',\n  type: 'distilled-pattern',\n  domain: 'api-optimization',\n  pattern_data: JSON.stringify({\n    embedding: await computeEmbedding(JSON.stringify(distilledPattern)),\n    pattern: distilledPattern\n  }),\n  confidence: 0.95,\n  usage_count: 0,\n  success_count: 0,\n  created_at: Date.now(),\n  last_used: Date.now(),\n});\n```\n\n---\n\n## Integration with Reasoning Agents\n\nAgentDB provides 4 reasoning modules that enhance ReasoningBank:\n\n### 1. PatternMatcher\n\nFind similar successful patterns:\n\n```typescript\nconst result = await rb.retrieveWithReasoning(queryEmbedding, {\n  domain: 'problem-solving',\n  k: 10,\n  useMMR: true,  \u002F\u002F Maximal Marginal Relevance for diversity\n});\n\n\u002F\u002F PatternMatcher returns diverse, relevant memories\nresult.memories.forEach(mem => {\n  console.log(`Pattern: ${mem.pattern.approach}`);\n  console.log(`Similarity: ${mem.similarity}`);\n  console.log(`Success Rate: ${mem.success_count \u002F mem.usage_count}`);\n});\n```\n\n### 2. ContextSynthesizer\n\nGenerate rich context from multiple memories:\n\n```typescript\nconst result = await rb.retrieveWithReasoning(queryEmbedding, {\n  domain: 'code-optimization',\n  synthesizeContext: true,  \u002F\u002F Enable context synthesis\n  k: 5,\n});\n\n\u002F\u002F ContextSynthesizer creates coherent narrative\nconsole.log('Synthesized Context:', result.context);\n\u002F\u002F \"Based on 5 similar optimizations, the most effective approach\n\u002F\u002F  involves profiling, identifying bottlenecks, and applying targeted\n\u002F\u002F  improvements. Success rate: 87%\"\n```\n\n### 3. MemoryOptimizer\n\nAutomatically consolidate and prune:\n\n```typescript\nconst result = await rb.retrieveWithReasoning(queryEmbedding, {\n  domain: 'testing',\n  optimizeMemory: true,  \u002F\u002F Enable automatic optimization\n});\n\n\u002F\u002F MemoryOptimizer consolidates similar patterns and prunes low-quality\nconsole.log('Optimizations:', result.optimizations);\n\u002F\u002F { consolidated: 15, pruned: 3, improved_quality: 0.12 }\n```\n\n### 4. ExperienceCurator\n\nFilter by quality and relevance:\n\n```typescript\nconst result = await rb.retrieveWithReasoning(queryEmbedding, {\n  domain: 'debugging',\n  k: 20,\n  minConfidence: 0.8,  \u002F\u002F Only high-confidence experiences\n});\n\n\u002F\u002F ExperienceCurator returns only quality experiences\nresult.memories.forEach(mem => {\n  console.log(`Confidence: ${mem.confidence}`);\n  console.log(`Success Rate: ${mem.success_count \u002F mem.usage_count}`);\n});\n```\n\n---\n\n## Legacy API Compatibility\n\nAgentDB maintains 100% backward compatibility with legacy ReasoningBank:\n\n```typescript\nimport {\n  retrieveMemories,\n  judgeTrajectory,\n  distillMemories\n} from 'agentic-flow\u002Freasoningbank';\n\n\u002F\u002F Legacy API works unchanged (uses AgentDB backend automatically)\nconst memories = await retrieveMemories(query, {\n  domain: 'code-generation',\n  agent: 'coder'\n});\n\nconst verdict = await judgeTrajectory(trajectory, query);\n\nconst newMemories = await distillMemories(\n  trajectory,\n  verdict,\n  query,\n  { domain: 'code-generation' }\n);\n```\n\n---\n\n## Performance Characteristics\n\n- **Pattern Search**: 150x faster (100µs vs 15ms)\n- **Memory Retrieval**: \u003C1ms (with cache)\n- **Batch Insert**: 500x faster (2ms vs 1s for 100 patterns)\n- **Trajectory Judgment**: \u003C5ms (including retrieval + analysis)\n- **Memory Distillation**: \u003C50ms (consolidate 100 patterns)\n\n---\n\n## Advanced Patterns\n\n### Hierarchical Memory\n\nOrganize memories by abstraction level:\n\n```typescript\n\u002F\u002F Low-level: Specific implementation\nawait rb.insertPattern({\n  type: 'concrete',\n  domain: 'debugging\u002Fnull-pointer',\n  pattern_data: JSON.stringify({\n    embedding,\n    pattern: { bug: 'NPE in UserService.getUser()', fix: 'Add null check' }\n  }),\n  confidence: 0.9,\n  \u002F\u002F ...\n});\n\n\u002F\u002F Mid-level: Pattern across similar cases\nawait rb.insertPattern({\n  type: 'pattern',\n  domain: 'debugging',\n  pattern_data: JSON.stringify({\n    embedding,\n    pattern: { category: 'null-pointer', approach: 'defensive-checks' }\n  }),\n  confidence: 0.85,\n  \u002F\u002F ...\n});\n\n\u002F\u002F High-level: General principle\nawait rb.insertPattern({\n  type: 'principle',\n  domain: 'software-engineering',\n  pattern_data: JSON.stringify({\n    embedding,\n    pattern: { principle: 'fail-fast with clear errors' }\n  }),\n  confidence: 0.95,\n  \u002F\u002F ...\n});\n```\n\n### Multi-Domain Learning\n\nTransfer learning across domains:\n\n```typescript\n\u002F\u002F Learn from backend optimization\nconst backendExperience = await rb.retrieveWithReasoning(embedding, {\n  domain: 'backend-optimization',\n  k: 10,\n});\n\n\u002F\u002F Apply to frontend optimization\nconst transferredKnowledge = backendExperience.memories.map(mem => ({\n  ...mem,\n  domain: 'frontend-optimization',\n  adapted: true,\n}));\n```\n\n---\n\n## CLI Operations\n\n### Database Management\n\n```bash\n# Export trajectories and patterns\nnpx agentdb@latest export .\u002F.agentdb\u002Freasoningbank.db .\u002Fbackup.json\n\n# Import experiences\nnpx agentdb@latest import .\u002Fexperiences.json\n\n# Get statistics\nnpx agentdb@latest stats .\u002F.agentdb\u002Freasoningbank.db\n# Shows: total patterns, domains, confidence distribution\n```\n\n### Migration\n\n```bash\n# Migrate from legacy ReasoningBank\nnpx agentdb@latest migrate --source .swarm\u002Fmemory.db --target .agentdb\u002Freasoningbank.db\n\n# Validate migration\nnpx agentdb@latest stats .agentdb\u002Freasoningbank.db\n```\n\n---\n\n## Troubleshooting\n\n### Issue: Migration fails\n```bash\n# Check source database exists\nls -la .swarm\u002Fmemory.db\n\n# Run with verbose logging\nDEBUG=agentdb:* npx agentdb@latest migrate --source .swarm\u002Fmemory.db\n```\n\n### Issue: Low confidence scores\n```typescript\n\u002F\u002F Enable context synthesis for better quality\nconst result = await rb.retrieveWithReasoning(embedding, {\n  synthesizeContext: true,\n  useMMR: true,\n  k: 10,\n});\n```\n\n### Issue: Memory growing too large\n```typescript\n\u002F\u002F Enable automatic optimization\nconst result = await rb.retrieveWithReasoning(embedding, {\n  optimizeMemory: true,  \u002F\u002F Consolidates similar patterns\n});\n\n\u002F\u002F Or manually optimize\nawait rb.optimize();\n```\n\n---\n\n## Learn More\n\n- **AgentDB Integration**: node_modules\u002Fagentic-flow\u002Fdocs\u002FAGENTDB_INTEGRATION.md\n- **GitHub**: https:\u002F\u002Fgithub.com\u002Fruvnet\u002Fagentic-flow\u002Ftree\u002Fmain\u002Fpackages\u002Fagentdb\n- **MCP Integration**: `npx agentdb@latest mcp`\n- **Website**: https:\u002F\u002Fagentdb.ruv.io\n\n---\n\n**Category**: Machine Learning \u002F Reinforcement Learning\n**Difficulty**: Intermediate\n**Estimated Time**: 20-30 minutes\n",{"name":5,"description":7},"main","87afe6ce96220accf50a345dea46784c8c9f210e","YYC3-Agent-智能体\u002FYYC3-Agent-智能体-ruflo\u002Fv3\u002F@claude-flow\u002Fmcp\u002F.claude\u002Fskills\u002Freasoningbank-agentdb",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 \"ReasoningBank with AgentDB\"",{"tool":39,"command":40},"bunx","bunx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill \"ReasoningBank with AgentDB\"",{"tool":42,"command":43},"pnpm","pnpm dlx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill \"ReasoningBank with AgentDB\"","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Agent-智能体\u002FYYC3-Agent-智能体-ruflo\u002Fv3\u002F@claude-flow\u002Fmcp\u002F.claude\u002Fskills\u002Freasoningbank-agentdb\u002FSKILL.md",true,[],[48,55,62,69,76,83],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"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":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"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":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"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":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"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":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"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":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"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",[],[]]