[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71S4AGW6TPQ0BM6A5BB7MGA":3,"skill-same:01M71S4AGW6TPQ0BM6A5BB7MGA":61},{"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":35,"linkOnly":36,"markdownContent":37,"markdownBody":38,"frontMatter":39,"refName":40,"commitSha":41,"skillDirectory":42,"forksCount":43,"repositoryHtmlUrl":44,"repositoryHomepageUrl":6,"ownerHtmlUrl":45,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":46,"install":47,"resources":60},"01M71S4AGW6TPQ0BM6A5BB7MGA","V3 Memory Unification",null,"Unify 6+ memory systems into AgentDB with HNSW indexing for 150x-12,500x search improvements. Implements ADR-006 (Unified Memory Service) and ADR-009 (Hybrid Memory Backend).","manykarim\u002Frobotframework-agentguard","manykarim","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F61293164?v=4","01M71S15ZAXR15JHKM1N7BHT21","Many Kasiriha","01M71S160CWQXETSCYWXDVNYJ2",1,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fmanykarim\u002Frobotframework-agentguard\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fv3-memory-unification\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34],"memory","v3","indexing","unified memory","hybrid","unify","for","with","systems","service","hybrid memory","backend","memory systems","adr","HNSW","search","2026-11-10 13:02:02",false,"---\nname: \"V3 Memory Unification\"\ndescription: \"Unify 6+ memory systems into AgentDB with HNSW indexing for 150x-12,500x search improvements. Implements ADR-006 (Unified Memory Service) and ADR-009 (Hybrid Memory Backend).\"\n---\n\n# V3 Memory Unification\n\n## What This Skill Does\n\nConsolidates disparate memory systems into unified AgentDB backend with HNSW vector search, achieving 150x-12,500x search performance improvements while maintaining backward compatibility.\n\n## Quick Start\n\n```bash\n# Initialize memory unification\nTask(\"Memory architecture\", \"Design AgentDB unification strategy\", \"v3-memory-specialist\")\n\n# AgentDB integration\nTask(\"AgentDB setup\", \"Configure HNSW indexing and vector search\", \"v3-memory-specialist\")\n\n# Data migration\nTask(\"Memory migration\", \"Migrate SQLite\u002FMarkdown to AgentDB\", \"v3-memory-specialist\")\n```\n\n## Systems to Unify\n\n### Legacy Systems → AgentDB\n```\n┌─────────────────────────────────────────┐\n│  • MemoryManager (basic operations)     │\n│  • DistributedMemorySystem (clustering) │\n│  • SwarmMemory (agent-specific)         │\n│  • AdvancedMemoryManager (features)     │\n│  • SQLiteBackend (structured)           │\n│  • MarkdownBackend (file-based)         │\n│  • HybridBackend (combination)          │\n└─────────────────────────────────────────┘\n                    ↓\n┌─────────────────────────────────────────┐\n│       🚀 AgentDB with HNSW             │\n│  • 150x-12,500x faster search          │\n│  • Unified query interface             │\n│  • Cross-agent memory sharing          │\n│  • SONA learning integration           │\n└─────────────────────────────────────────┘\n```\n\n## Implementation Architecture\n\n### Unified Memory Service\n```typescript\nclass UnifiedMemoryService implements IMemoryBackend {\n  constructor(\n    private agentdb: AgentDBAdapter,\n    private indexer: HNSWIndexer,\n    private migrator: DataMigrator\n  ) {}\n\n  async store(entry: MemoryEntry): Promise\u003Cvoid> {\n    await this.agentdb.store(entry);\n    await this.indexer.index(entry);\n  }\n\n  async query(query: MemoryQuery): Promise\u003CMemoryEntry[]> {\n    if (query.semantic) {\n      return this.indexer.search(query); \u002F\u002F 150x-12,500x faster\n    }\n    return this.agentdb.query(query);\n  }\n}\n```\n\n### HNSW Vector Search\n```typescript\nclass HNSWIndexer {\n  constructor(dimensions: number = 1536) {\n    this.index = new HNSWIndex({\n      dimensions,\n      efConstruction: 200,\n      M: 16,\n      speedupTarget: '150x-12500x'\n    });\n  }\n\n  async search(query: MemoryQuery): Promise\u003CMemoryEntry[]> {\n    const embedding = await this.embedContent(query.content);\n    const results = this.index.search(embedding, query.limit || 10);\n    return this.retrieveEntries(results);\n  }\n}\n```\n\n## Migration Strategy\n\n### Phase 1: Foundation\n```typescript\n\u002F\u002F AgentDB adapter setup\nconst agentdb = new AgentDBAdapter({\n  dimensions: 1536,\n  indexType: 'HNSW',\n  speedupTarget: '150x-12500x'\n});\n```\n\n### Phase 2: Data Migration\n```typescript\n\u002F\u002F SQLite → AgentDB\nconst migrateFromSQLite = async () => {\n  const entries = await sqlite.getAll();\n  for (const entry of entries) {\n    const embedding = await generateEmbedding(entry.content);\n    await agentdb.store({ ...entry, embedding });\n  }\n};\n\n\u002F\u002F Markdown → AgentDB\nconst migrateFromMarkdown = async () => {\n  const files = await glob('**\u002F*.md');\n  for (const file of files) {\n    const content = await fs.readFile(file, 'utf-8');\n    await agentdb.store({\n      id: generateId(),\n      content,\n      embedding: await generateEmbedding(content),\n      metadata: { originalFile: file }\n    });\n  }\n};\n```\n\n## SONA Integration\n\n### Learning Pattern Storage\n```typescript\nclass SONAMemoryIntegration {\n  async storePattern(pattern: LearningPattern): Promise\u003Cvoid> {\n    await this.memory.store({\n      id: pattern.id,\n      content: pattern.data,\n      metadata: {\n        sonaMode: pattern.mode,\n        reward: pattern.reward,\n        adaptationTime: pattern.adaptationTime\n      },\n      embedding: await this.generateEmbedding(pattern.data)\n    });\n  }\n\n  async retrieveSimilarPatterns(query: string): Promise\u003CLearningPattern[]> {\n    return this.memory.query({\n      type: 'semantic',\n      content: query,\n      filters: { type: 'learning_pattern' }\n    });\n  }\n}\n```\n\n## Performance Targets\n\n- **Search Speed**: 150x-12,500x improvement via HNSW\n- **Memory Usage**: 50-75% reduction through optimization\n- **Query Latency**: \u003C100ms for 1M+ entries\n- **Cross-Agent Sharing**: Real-time memory synchronization\n- **SONA Integration**: \u003C0.05ms adaptation time\n\n## Success Metrics\n\n- [ ] All 7 legacy memory systems migrated to AgentDB\n- [ ] 150x-12,500x search performance validated\n- [ ] 50-75% memory usage reduction achieved\n- [ ] Backward compatibility maintained\n- [ ] SONA learning patterns integrated\n- [ ] Cross-agent memory sharing operational","# V3 Memory Unification\n\n## What This Skill Does\n\nConsolidates disparate memory systems into unified AgentDB backend with HNSW vector search, achieving 150x-12,500x search performance improvements while maintaining backward compatibility.\n\n## Quick Start\n\n```bash\n# Initialize memory unification\nTask(\"Memory architecture\", \"Design AgentDB unification strategy\", \"v3-memory-specialist\")\n\n# AgentDB integration\nTask(\"AgentDB setup\", \"Configure HNSW indexing and vector search\", \"v3-memory-specialist\")\n\n# Data migration\nTask(\"Memory migration\", \"Migrate SQLite\u002FMarkdown to AgentDB\", \"v3-memory-specialist\")\n```\n\n## Systems to Unify\n\n### Legacy Systems → AgentDB\n```\n┌─────────────────────────────────────────┐\n│  • MemoryManager (basic operations)     │\n│  • DistributedMemorySystem (clustering) │\n│  • SwarmMemory (agent-specific)         │\n│  • AdvancedMemoryManager (features)     │\n│  • SQLiteBackend (structured)           │\n│  • MarkdownBackend (file-based)         │\n│  • HybridBackend (combination)          │\n└─────────────────────────────────────────┘\n                    ↓\n┌─────────────────────────────────────────┐\n│       🚀 AgentDB with HNSW             │\n│  • 150x-12,500x faster search          │\n│  • Unified query interface             │\n│  • Cross-agent memory sharing          │\n│  • SONA learning integration           │\n└─────────────────────────────────────────┘\n```\n\n## Implementation Architecture\n\n### Unified Memory Service\n```typescript\nclass UnifiedMemoryService implements IMemoryBackend {\n  constructor(\n    private agentdb: AgentDBAdapter,\n    private indexer: HNSWIndexer,\n    private migrator: DataMigrator\n  ) {}\n\n  async store(entry: MemoryEntry): Promise\u003Cvoid> {\n    await this.agentdb.store(entry);\n    await this.indexer.index(entry);\n  }\n\n  async query(query: MemoryQuery): Promise\u003CMemoryEntry[]> {\n    if (query.semantic) {\n      return this.indexer.search(query); \u002F\u002F 150x-12,500x faster\n    }\n    return this.agentdb.query(query);\n  }\n}\n```\n\n### HNSW Vector Search\n```typescript\nclass HNSWIndexer {\n  constructor(dimensions: number = 1536) {\n    this.index = new HNSWIndex({\n      dimensions,\n      efConstruction: 200,\n      M: 16,\n      speedupTarget: '150x-12500x'\n    });\n  }\n\n  async search(query: MemoryQuery): Promise\u003CMemoryEntry[]> {\n    const embedding = await this.embedContent(query.content);\n    const results = this.index.search(embedding, query.limit || 10);\n    return this.retrieveEntries(results);\n  }\n}\n```\n\n## Migration Strategy\n\n### Phase 1: Foundation\n```typescript\n\u002F\u002F AgentDB adapter setup\nconst agentdb = new AgentDBAdapter({\n  dimensions: 1536,\n  indexType: 'HNSW',\n  speedupTarget: '150x-12500x'\n});\n```\n\n### Phase 2: Data Migration\n```typescript\n\u002F\u002F SQLite → AgentDB\nconst migrateFromSQLite = async () => {\n  const entries = await sqlite.getAll();\n  for (const entry of entries) {\n    const embedding = await generateEmbedding(entry.content);\n    await agentdb.store({ ...entry, embedding });\n  }\n};\n\n\u002F\u002F Markdown → AgentDB\nconst migrateFromMarkdown = async () => {\n  const files = await glob('**\u002F*.md');\n  for (const file of files) {\n    const content = await fs.readFile(file, 'utf-8');\n    await agentdb.store({\n      id: generateId(),\n      content,\n      embedding: await generateEmbedding(content),\n      metadata: { originalFile: file }\n    });\n  }\n};\n```\n\n## SONA Integration\n\n### Learning Pattern Storage\n```typescript\nclass SONAMemoryIntegration {\n  async storePattern(pattern: LearningPattern): Promise\u003Cvoid> {\n    await this.memory.store({\n      id: pattern.id,\n      content: pattern.data,\n      metadata: {\n        sonaMode: pattern.mode,\n        reward: pattern.reward,\n        adaptationTime: pattern.adaptationTime\n      },\n      embedding: await this.generateEmbedding(pattern.data)\n    });\n  }\n\n  async retrieveSimilarPatterns(query: string): Promise\u003CLearningPattern[]> {\n    return this.memory.query({\n      type: 'semantic',\n      content: query,\n      filters: { type: 'learning_pattern' }\n    });\n  }\n}\n```\n\n## Performance Targets\n\n- **Search Speed**: 150x-12,500x improvement via HNSW\n- **Memory Usage**: 50-75% reduction through optimization\n- **Query Latency**: \u003C100ms for 1M+ entries\n- **Cross-Agent Sharing**: Real-time memory synchronization\n- **SONA Integration**: \u003C0.05ms adaptation time\n\n## Success Metrics\n\n- [ ] All 7 legacy memory systems migrated to AgentDB\n- [ ] 150x-12,500x search performance validated\n- [ ] 50-75% memory usage reduction achieved\n- [ ] Backward compatibility maintained\n- [ ] SONA learning patterns integrated\n- [ ] Cross-agent memory sharing operational",{"name":5,"description":7},"main","63caf799a0409377ce4fd434e24e9eac7c05c6fa",".claude\u002Fskills\u002Fv3-memory-unification",0,"https:\u002F\u002Fgithub.com\u002Fmanykarim\u002Frobotframework-agentguard","https:\u002F\u002Fgithub.com\u002Fmanykarim","2026-07-27 14:20:37",{"source":8,"skillName":5,"commands":48,"prompt":58,"zipAvailable":59},[49,52,55],{"tool":50,"command":51},"npx","npx skills add manykarim\u002Frobotframework-agentguard --skill \"V3 Memory Unification\"",{"tool":53,"command":54},"bunx","bunx skills add manykarim\u002Frobotframework-agentguard --skill \"V3 Memory Unification\"",{"tool":56,"command":57},"pnpm","pnpm dlx skills add manykarim\u002Frobotframework-agentguard --skill \"V3 Memory Unification\"","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmanykarim\u002Frobotframework-agentguard\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fv3-memory-unification\u002FSKILL.md",true,[],[62,84,92,110,124,140],{"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":73,"publishedAt":35},"01M71S584X6G22VN1KZ42DZ33K","good-example","Demonstrate a minimal valid Agent Skill used by AgentGuard's own tests.","https:\u002F\u002Fgithub.com\u002Fmanykarim\u002Frobotframework-agentguard\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskills\u002Fgood-skill\u002FSKILL.md",[68],{"categoryNo":69,"categoryName":70,"taxonomyType":71,"taxonomyTypeDesc":72},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[74,75,76,77,78,79,80,81,82,83],"good example","good","example","valid","agentguard","read","write","minimal","tests","agent skill",{"skillNo":85,"name":86,"nameZh":6,"description":6,"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":35},"01M71S55P2APRSAC0S9F5X556A","bad-example","https:\u002F\u002Fgithub.com\u002Fmanykarim\u002Frobotframework-agentguard\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskills\u002Fbad-skill\u002FSKILL.md",[],[90,76,91,79],"bad","bad example",{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":99,"publishedAt":35},"01M71S53FGWCB5XXX4QGW3RF4P","injection-skill","Demonstrates a prompt-injection payload embedded in the body.","https:\u002F\u002Fgithub.com\u002Fmanykarim\u002Frobotframework-agentguard\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fsecurity\u002Finjection-skill\u002FSKILL.md",[98],{"categoryNo":69,"categoryName":70,"taxonomyType":71,"taxonomyTypeDesc":72},[100,101,79,102,103,104,105,106,107,108,109],"injection skill","injection","payload","body","prompt","unknown","Bash","prompt-injection","author","embedded",{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":117,"publishedAt":35},"01M71S518MA1JN7F1DZ5XVRH06","curl-pipe-skill","Skill whose installer script demonstrates the `curl ... | sh` antipattern.","https:\u002F\u002Fgithub.com\u002Fmanykarim\u002Frobotframework-agentguard\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fsecurity\u002Fcurl-pipe-skill\u002FSKILL.md",[116],{"categoryNo":69,"categoryName":70,"taxonomyType":71,"taxonomyTypeDesc":72},[118,119,120,121,122,105,106,108,123],"curl","pipe","curl pipe skill","installer","antipattern","script",{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":131,"publishedAt":35},"01M71S4YYFE3HJKDEQR5Z944ZW","clean-skill","A minimal, well-formed skill used as the security-scanner happy path.","https:\u002F\u002Fgithub.com\u002Fmanykarim\u002Frobotframework-agentguard\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fsecurity\u002Fclean-skill\u002FSKILL.md",[130],{"categoryNo":69,"categoryName":70,"taxonomyType":71,"taxonomyTypeDesc":72},[132,133,78,134,81,135,136,137,138,79,139],"clean skill","clean","scanner","grep","true","as","security","path",{"skillNo":141,"name":142,"nameZh":6,"description":143,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":144,"categories":145,"keywords":146,"publishedAt":35},"01M71S4W60AZYGA57HJWYBQZMJ","rf-libdoc-search","Search Robot Framework library\u002Fresource\u002Fsuite documentation to find matching keywords for a use case. Use when asked to find keywords, search libdoc, match a use case to keywords, or scan multiple libraries\u002Fresources for relevant keywords.","https:\u002F\u002Fgithub.com\u002Fmanykarim\u002Frobotframework-agentguard\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fintegrations\u002Fskills\u002Frf-libdoc-search\u002FSKILL.md",[],[34,147,148,25,149,150,151,152,153,154,155,156,157,158,159,160,161,162],"rf libdoc search","case","resources","relevant","scan","libraries","documentation","robot","when","framework","use","match","library","suite","matching","find"]