[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M73BWTQQ3FA7Y1P29140GFVB":3,"skill-same:01M73BWTQQ3FA7Y1P29140GFVB":71},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":8,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":14,"categories":15,"keywords":16,"publishedAt":17,"linkOnly":18,"markdownContent":19,"markdownBody":20,"frontMatter":21,"refName":31,"commitSha":32,"skillDirectory":33,"forksCount":12,"repositoryHtmlUrl":34,"repositoryHomepageUrl":6,"ownerHtmlUrl":35,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":36,"install":37,"resources":50},"01M73BWTQQ3FA7Y1P29140GFVB","reasoningbank-intelligence",null,"ngdletrung\u002FJKAI-Zenith","ngdletrung","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F88302940?v=4","01M73BJVV5QJ87R3MC4BXJMWDN","01M73BJVWAAM03TM18QHKRDAMH",0,"MIT","https:\u002F\u002Fgithub.com\u002Fngdletrung\u002FJKAI-Zenith\u002Fblob\u002Fmain\u002Fintelligence\u002Fskills\u002FCORE\u002Freasoningbank-intelligence\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nid: reasoningbank-intelligence\nname_vn: '\"ReasoningBank Intelligence\"'\nversion: 1.0.0\nauthor: Zenith Legacy\ndomain: UNKNOWN\nintent_pairs: []\naliases_vn: []\nschema: {}\npriority: NORMAL\nrelated_skills: []\n\n---\n\n# \"ReasoningBank Intelligence\" (reasoningbank-intelligence)\n\n## 🌟 TỔNG QUAN\n---\nname: \"ReasoningBank Intelligence\"\ndescription: \"Implement adaptive learning with ReasoningBank for pattern recognition, strategy optimization, and continuous improvement. Use when building self-learning agents, optimizing workflows, or implementing meta-cognitive systems.\"\n---\n\n# ReasoningBank Intelligence\n\n## What This Skill Does\n\nImplements ReasoningBank's adaptive learning system for AI agents to learn from experience, recognize patterns, and optimize strategies over time. Enables meta-cognitive capabilities and continuous improvement.\n\n## Prerequisites\n\n- agentic-flow v1.5.11+\n- AgentDB v1.0.4+ (for persistence)\n- Node.js 18+\n\n## Quick Start\n\n```typescript\nimport { ReasoningBank } from 'agentic-flow$reasoningbank';\n\n\u002F\u002F Initialize ReasoningBank\nconst rb = new ReasoningBank({\n  persist: true,\n  learningRate: 0.1,\n  adapter: 'agentdb' \u002F\u002F Use AgentDB for storage\n});\n\n\u002F\u002F Record task outcome\nawait rb.recordExperience({\n  task: 'code_review',\n  approach: 'static_analysis_first',\n  outcome: {\n    success: true,\n    metrics: {\n      bugs_found: 5,\n      time_taken: 120,\n      false_positives: 1\n    }\n  },\n  context: {\n    language: 'typescript',\n    complexity: 'medium'\n  }\n});\n\n\u002F\u002F Get optimal strategy\nconst strategy = await rb.recommendStrategy('code_review', {\n  language: 'typescript',\n  complexity: 'high'\n});\n```\n\n## Core Features\n\n### 1. Pattern Recognition\n```typescript\n\u002F\u002F Learn patterns from data\nawait rb.learnPattern({\n  pattern: 'api_errors_increase_after_deploy',\n  triggers: ['deployment', 'traffic_spike'],\n  actions: ['rollback', 'scale_up'],\n  confidence: 0.85\n});\n\n\u002F\u002F Match patterns\nconst matches = await rb.matchPatterns(currentSituation);\n```\n\n### 2. Strategy Optimization\n```typescript\n\u002F\u002F Compare strategies\nconst comparison = await rb.compareStrategies('bug_fixing', [\n  'tdd_approach',\n  'debug_first',\n  'reproduce_then_fix'\n]);\n\n\u002F\u002F Get best strategy\nconst best = comparison.strategies[0];\nconsole.log(`Best: ${best.name} (score: ${best.score})`);\n```\n\n### 3. Continuous Learning\n```typescript\n\u002F\u002F Enable auto-learning from all tasks\nawait rb.enableAutoLearning({\n  threshold: 0.7,        \u002F\u002F Only learn from high-confidence outcomes\n  updateFrequency: 100   \u002F\u002F Update models every 100 experiences\n});\n```\n\n## Advanced Usage\n\n### Meta-Learning\n```typescript\n\u002F\u002F Learn about learning\nawait rb.metaLearn({\n  observation: 'parallel_execution_faster_for_independent_tasks',\n  confidence: 0.95,\n  applicability: {\n    task_types: ['batch_processing', 'data_transformation'],\n    conditions: ['tasks_independent', 'io_bound']\n  }\n});\n```\n\n### Transfer Learning\n```typescript\n\u002F\u002F Apply knowledge from one domain to another\nawait rb.transferKnowledge({\n  from: 'code_review_javascript',\n  to: 'code_review_typescript',\n  similarity: 0.8\n});\n```\n\n### Adaptive Agents\n```typescript\n\u002F\u002F Create self-improving agent\nclass AdaptiveAgent {\n  async execute(task: Task) {\n    \u002F\u002F Get optimal strategy\n    const strategy = await rb.recommendStrategy(task.type, task.context);\n\n    \u002F\u002F Execute with strategy\n    const result = await this.executeWithStrategy(task, strategy);\n\n    \u002F\u002F Learn from outcome\n    await rb.recordExperience({\n      task: task.type,\n      approach: strategy.name,\n      outcome: result,\n      context: task.context\n    });\n\n    return result;\n  }\n}\n```\n\n## Integration with AgentDB\n\n```typescript\n\u002F\u002F Persist ReasoningBank data\nawait rb.configure({\n  storage: {\n    type: 'agentdb',\n    options: {\n      database: '.$reasoning-bank.db',\n      enableVectorSearch: true\n    }\n  }\n});\n\n\u002F\u002F Query learned patterns\nconst patterns = await rb.query({\n  category: 'optimization',\n  minConfidence: 0.8,\n  timeRange: { last: '30d' }\n});\n```\n\n## Performance Metrics\n\n```typescript\n\u002F\u002F Track learning effectiveness\nconst metrics = await rb.getMetrics();\nconsole.log(`\n  Total Experiences: ${metrics.totalExperiences}\n  Patterns Learned: ${metrics.patternsLearned}\n  Strategy Success Rate: ${metrics.strategySuccessRate}\n  Improvement Over Time: ${metrics.improvement}\n`);\n```\n\n## Best Practices\n\n1. **Record consistently**: Log all task outcomes, not just successes\n2. **Provide context**: Rich context improves pattern matching\n3. **Set thresholds**: Filter low-confidence learnings\n4. **Review periodically**: Audit learned patterns for quality\n5. **Use vector search**: Enable semantic pattern matching\n\n## Troubleshooting\n\n### Issue: Poor recommendations\n**Solution**: Ensure sufficient training data (100+ experiences per task type)\n\n### Issue: Slow pattern matching\n**Solution**: Enable vector indexing in AgentDB\n\n### Issue: Memory growing large\n**Solution**: Set TTL for old experiences or enable pruning\n\n## Learn More\n\n- ReasoningBank Guide: agentic-flow$src$reasoningbank\u002FREADME.md\n- AgentDB Integration: packages$agentdb$docs$reasoningbank.md\n- Pattern Learning: docs$reasoning$patterns.md\n\n\n## 🛠️ PHÁC ĐỒ VẬN HÀNH (OPERATIONAL PROTOCOL)\n### 🔍 Phase 1: Investigation (Thẩm định)\n- Xác minh tham số đầu vào dựa trên Schema.\n- Kiểm tra bối cảnh hệ thống liên quan.\n\n### 🚀 Phase 2: Action (Thực thi)\n- Triệu hồi logic thực thi trong `logic.py`.\n- Trả về kết quả và chắt lọc kinh nghiệm.\n\n---\n## ⚠️ SAI LẦM THƯỜNG GẶP (COMMON PITFALLS)\n- Chưa ghi nhận.\n\n---\n*TRUNG THÀNH - CHÍNH XÁC - TỐI THƯỢNG* 💎🦾\n","# \"ReasoningBank Intelligence\" (reasoningbank-intelligence)\n\n## 🌟 TỔNG QUAN\n---\nname: \"ReasoningBank Intelligence\"\ndescription: \"Implement adaptive learning with ReasoningBank for pattern recognition, strategy optimization, and continuous improvement. Use when building self-learning agents, optimizing workflows, or implementing meta-cognitive systems.\"\n---\n\n# ReasoningBank Intelligence\n\n## What This Skill Does\n\nImplements ReasoningBank's adaptive learning system for AI agents to learn from experience, recognize patterns, and optimize strategies over time. Enables meta-cognitive capabilities and continuous improvement.\n\n## Prerequisites\n\n- agentic-flow v1.5.11+\n- AgentDB v1.0.4+ (for persistence)\n- Node.js 18+\n\n## Quick Start\n\n```typescript\nimport { ReasoningBank } from 'agentic-flow$reasoningbank';\n\n\u002F\u002F Initialize ReasoningBank\nconst rb = new ReasoningBank({\n  persist: true,\n  learningRate: 0.1,\n  adapter: 'agentdb' \u002F\u002F Use AgentDB for storage\n});\n\n\u002F\u002F Record task outcome\nawait rb.recordExperience({\n  task: 'code_review',\n  approach: 'static_analysis_first',\n  outcome: {\n    success: true,\n    metrics: {\n      bugs_found: 5,\n      time_taken: 120,\n      false_positives: 1\n    }\n  },\n  context: {\n    language: 'typescript',\n    complexity: 'medium'\n  }\n});\n\n\u002F\u002F Get optimal strategy\nconst strategy = await rb.recommendStrategy('code_review', {\n  language: 'typescript',\n  complexity: 'high'\n});\n```\n\n## Core Features\n\n### 1. Pattern Recognition\n```typescript\n\u002F\u002F Learn patterns from data\nawait rb.learnPattern({\n  pattern: 'api_errors_increase_after_deploy',\n  triggers: ['deployment', 'traffic_spike'],\n  actions: ['rollback', 'scale_up'],\n  confidence: 0.85\n});\n\n\u002F\u002F Match patterns\nconst matches = await rb.matchPatterns(currentSituation);\n```\n\n### 2. Strategy Optimization\n```typescript\n\u002F\u002F Compare strategies\nconst comparison = await rb.compareStrategies('bug_fixing', [\n  'tdd_approach',\n  'debug_first',\n  'reproduce_then_fix'\n]);\n\n\u002F\u002F Get best strategy\nconst best = comparison.strategies[0];\nconsole.log(`Best: ${best.name} (score: ${best.score})`);\n```\n\n### 3. Continuous Learning\n```typescript\n\u002F\u002F Enable auto-learning from all tasks\nawait rb.enableAutoLearning({\n  threshold: 0.7,        \u002F\u002F Only learn from high-confidence outcomes\n  updateFrequency: 100   \u002F\u002F Update models every 100 experiences\n});\n```\n\n## Advanced Usage\n\n### Meta-Learning\n```typescript\n\u002F\u002F Learn about learning\nawait rb.metaLearn({\n  observation: 'parallel_execution_faster_for_independent_tasks',\n  confidence: 0.95,\n  applicability: {\n    task_types: ['batch_processing', 'data_transformation'],\n    conditions: ['tasks_independent', 'io_bound']\n  }\n});\n```\n\n### Transfer Learning\n```typescript\n\u002F\u002F Apply knowledge from one domain to another\nawait rb.transferKnowledge({\n  from: 'code_review_javascript',\n  to: 'code_review_typescript',\n  similarity: 0.8\n});\n```\n\n### Adaptive Agents\n```typescript\n\u002F\u002F Create self-improving agent\nclass AdaptiveAgent {\n  async execute(task: Task) {\n    \u002F\u002F Get optimal strategy\n    const strategy = await rb.recommendStrategy(task.type, task.context);\n\n    \u002F\u002F Execute with strategy\n    const result = await this.executeWithStrategy(task, strategy);\n\n    \u002F\u002F Learn from outcome\n    await rb.recordExperience({\n      task: task.type,\n      approach: strategy.name,\n      outcome: result,\n      context: task.context\n    });\n\n    return result;\n  }\n}\n```\n\n## Integration with AgentDB\n\n```typescript\n\u002F\u002F Persist ReasoningBank data\nawait rb.configure({\n  storage: {\n    type: 'agentdb',\n    options: {\n      database: '.$reasoning-bank.db',\n      enableVectorSearch: true\n    }\n  }\n});\n\n\u002F\u002F Query learned patterns\nconst patterns = await rb.query({\n  category: 'optimization',\n  minConfidence: 0.8,\n  timeRange: { last: '30d' }\n});\n```\n\n## Performance Metrics\n\n```typescript\n\u002F\u002F Track learning effectiveness\nconst metrics = await rb.getMetrics();\nconsole.log(`\n  Total Experiences: ${metrics.totalExperiences}\n  Patterns Learned: ${metrics.patternsLearned}\n  Strategy Success Rate: ${metrics.strategySuccessRate}\n  Improvement Over Time: ${metrics.improvement}\n`);\n```\n\n## Best Practices\n\n1. **Record consistently**: Log all task outcomes, not just successes\n2. **Provide context**: Rich context improves pattern matching\n3. **Set thresholds**: Filter low-confidence learnings\n4. **Review periodically**: Audit learned patterns for quality\n5. **Use vector search**: Enable semantic pattern matching\n\n## Troubleshooting\n\n### Issue: Poor recommendations\n**Solution**: Ensure sufficient training data (100+ experiences per task type)\n\n### Issue: Slow pattern matching\n**Solution**: Enable vector indexing in AgentDB\n\n### Issue: Memory growing large\n**Solution**: Set TTL for old experiences or enable pruning\n\n## Learn More\n\n- ReasoningBank Guide: agentic-flow$src$reasoningbank\u002FREADME.md\n- AgentDB Integration: packages$agentdb$docs$reasoningbank.md\n- Pattern Learning: docs$reasoning$patterns.md\n\n\n## 🛠️ PHÁC ĐỒ VẬN HÀNH (OPERATIONAL PROTOCOL)\n### 🔍 Phase 1: Investigation (Thẩm định)\n- Xác minh tham số đầu vào dựa trên Schema.\n- Kiểm tra bối cảnh hệ thống liên quan.\n\n### 🚀 Phase 2: Action (Thực thi)\n- Triệu hồi logic thực thi trong `logic.py`.\n- Trả về kết quả và chắt lọc kinh nghiệm.\n\n---\n## ⚠️ SAI LẦM THƯỜNG GẶP (COMMON PITFALLS)\n- Chưa ghi nhận.\n\n---\n*TRUNG THÀNH - CHÍNH XÁC - TỐI THƯỢNG* 💎🦾\n",{"id":5,"author":22,"domain":23,"schema":24,"name_vn":25,"version":26,"priority":27,"aliases_vn":28,"intent_pairs":29,"related_skills":30},"Zenith Legacy","UNKNOWN",{},"\"ReasoningBank Intelligence\"","1.0.0","NORMAL",[],[],[],"main","571327a911ec45873180fd5628525b6d4504ed79","intelligence\u002Fskills\u002FCORE\u002Freasoningbank-intelligence","https:\u002F\u002Fgithub.com\u002Fngdletrung\u002FJKAI-Zenith","https:\u002F\u002Fgithub.com\u002Fngdletrung","2026-11-08 11:23:33",{"source":7,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add ngdletrung\u002FJKAI-Zenith --skill reasoningbank-intelligence",{"tool":43,"command":44},"bunx","bunx skills add ngdletrung\u002FJKAI-Zenith --skill reasoningbank-intelligence",{"tool":46,"command":47},"pnpm","pnpm dlx skills add ngdletrung\u002FJKAI-Zenith --skill reasoningbank-intelligence","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fngdletrung\u002FJKAI-Zenith\u002Fblob\u002Fmain\u002Fintelligence\u002Fskills\u002FCORE\u002Freasoningbank-intelligence\u002FSKILL.md",true,[51,57,63,67],{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},"__init__.py","SCRIPT","脚本",75,"https:\u002F\u002Fgithub.com\u002Fngdletrung\u002FJKAI-Zenith\u002Fblob\u002Fmain\u002Fintelligence\u002Fskills\u002FCORE\u002Freasoningbank-intelligence\u002F__init__.py",{"path":58,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":61,"sourceHtmlUrl":62},"dossier.md","REFERENCE","参考文档",2127,"https:\u002F\u002Fgithub.com\u002Fngdletrung\u002FJKAI-Zenith\u002Fblob\u002Fmain\u002Fintelligence\u002Fskills\u002FCORE\u002Freasoningbank-intelligence\u002Fdossier.md",{"path":64,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":65,"sourceHtmlUrl":66},"logic.py",434,"https:\u002F\u002Fgithub.com\u002Fngdletrung\u002FJKAI-Zenith\u002Fblob\u002Fmain\u002Fintelligence\u002Fskills\u002FCORE\u002Freasoningbank-intelligence\u002Flogic.py",{"path":68,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":69,"sourceHtmlUrl":70},"manifest.json",957,"https:\u002F\u002Fgithub.com\u002Fngdletrung\u002FJKAI-Zenith\u002Fblob\u002Fmain\u002Fintelligence\u002Fskills\u002FCORE\u002Freasoningbank-intelligence\u002Fmanifest.json",[72,79,85,92,98,104],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":8,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":17},"01M73C2NC1W5P3A0V3GQAJ0SJB","standard_plugin","Hướng dẫn kích hoạt và vận hành cho kỹ năng standard_plugin.","https:\u002F\u002Fgithub.com\u002Fngdletrung\u002FJKAI-Zenith\u002Fblob\u002Fmain\u002Fintelligence\u002Fskills\u002Ftemplates\u002Fstandard_plugin\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":8,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":17},"01M73C2KAN3Q7D5XEBKB3KZW1B","_STANDARD","https:\u002F\u002Fgithub.com\u002Fngdletrung\u002FJKAI-Zenith\u002Fblob\u002Fmain\u002Fintelligence\u002Fskills\u002F_STANDARD\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":8,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":17},"01M73C2HV7KDJQTA6ACCR10HZB","test_dynamic_audit","Thao tác kiểm toán động","https:\u002F\u002Fgithub.com\u002Fngdletrung\u002FJKAI-Zenith\u002Fblob\u002Fmain\u002Fintelligence\u002Fskills\u002FTEST\u002Ftest_dynamic_audit\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":8,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":17},"01M73C2FRG0JHZ6W155V1KCHRP","security-audit","https:\u002F\u002Fgithub.com\u002Fngdletrung\u002FJKAI-Zenith\u002Fblob\u002Fmain\u002Fintelligence\u002Fskills\u002FSECURITY\u002Fsecurity-audit\u002FSKILL.md",[],[],{"skillNo":99,"name":100,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":8,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":17},"01M73C2EMWYHFTAR9RSZ41TBGP","security-and-hardening","https:\u002F\u002Fgithub.com\u002Fngdletrung\u002FJKAI-Zenith\u002Fblob\u002Fmain\u002Fintelligence\u002Fskills\u002FSECURITY\u002Fsecurity-and-hardening\u002FSKILL.md",[],[],{"skillNo":105,"name":106,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":8,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":17},"01M73C2CV0BQ59NAEWXKBQ370Z","performance-optimization","https:\u002F\u002Fgithub.com\u002Fngdletrung\u002FJKAI-Zenith\u002Fblob\u002Fmain\u002Fintelligence\u002Fskills\u002FSECURITY\u002Fperformance-optimization\u002FSKILL.md",[],[]]