[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M74AX4C5GS74F9S3ZTVRCEYD":3,"skill-same:01M74AX4C5GS74F9S3ZTVRCEYD":43},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":13,"repositoryHtmlUrl":26,"repositoryHomepageUrl":6,"ownerHtmlUrl":27,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":28,"install":29,"resources":42},"01M74AX4C5GS74F9S3ZTVRCEYD","agentdb-patterns",null,"Memory persistence, vector search, optimization, and learning patterns for AI agents.\nUse when implementing persistent memory, vector-based search, agent state management,\nor building learning systems that improve over time.","aicreator350\u002FaurionOFFICIELLE","aicreator350","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F217751428?v=4","01M731QVHB22WCM6PDX5VFN1RV","01M731QVJ0TAD058M1SW9MY548",0,"MIT","https:\u002F\u002Fgithub.com\u002Faicreator350\u002FaurionOFFICIELLE\u002Fblob\u002Fmain\u002F.claude\u002F_archive\u002Fskills\u002Fagentdb-patterns\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: agentdb-patterns\ndescription: |\n  Memory persistence, vector search, optimization, and learning patterns for AI agents.\n  Use when implementing persistent memory, vector-based search, agent state management,\n  or building learning systems that improve over time.\n---\n\n# AgentDB Patterns\n\nMemory persistence, vector search, optimization, and learning patterns for AI agent systems.\n\n## Memory Patterns\n\n### Memory Types\n- **Ephemeral** — Current session only, fast access (Zustand store)\n- **Persistent** — Survives sessions, database-backed (Supabase)\n- **Shared** — Accessible across agents (coordination memory)\n- **Private** — Agent-specific, isolated context\n\n### Memory Hierarchy\n```\nL1: In-memory cache (Zustand) — \u003C1ms access\nL2: Local storage\u002FIndexedDB — \u003C10ms access\nL3: Supabase PostgreSQL — \u003C50ms access\nL4: External APIs (OpenRouter context) — \u003C500ms access\n```\n\n### Memory Operations\n- **Store** — Save with key, value, type, optional TTL\n- **Retrieve** — Get by exact key\n- **Search** — Pattern-based search (prefix, regex)\n- **Associate** — Link related memories (e.g., \"auth\" ↔ \"jwt\" ↔ \"refresh-token\")\n- **Consolidate** — Merge duplicate\u002Frelated entries\n- **Prune** — Remove expired or low-value entries\n\n## Vector Search Patterns\n\n### Embedding-Based Search\nUse vector embeddings for semantic similarity:\n- Convert text to embeddings (OpenAI\u002FSupabase pgvector)\n- Store embeddings alongside content\n- Query with cosine similarity\n- Filter by metadata (type, date, confidence)\n\n### Search Strategies\n- **Exact Match** — Key-based lookup, fastest\n- **Prefix Search** — Namespace-based, good for hierarchical data\n- **Semantic Search** — Vector similarity, best for natural language queries\n- **Hybrid** — Combine exact + semantic for best results\n\n### Supabase pgvector Integration\n```sql\n-- Enable vector extension\nCREATE EXTENSION IF NOT EXISTS vector;\n\n-- Add embedding column\nALTER TABLE knowledge_base ADD COLUMN embedding vector(1536);\n\n-- Create index for fast similarity search\nCREATE INDEX ON knowledge_base USING ivfflat (embedding vector_cosine_ops);\n\n-- Query similar items\nSELECT *, 1 - (embedding \u003C=> query_embedding) as similarity\nFROM knowledge_base\nORDER BY embedding \u003C=> query_embedding\nLIMIT 10;\n```\n\n## Optimization Patterns\n\n### Cache Strategies\n- **LRU Cache** — Evict least recently used entries\n- **TTL Cache** — Time-based expiration\n- **Write-Through** — Update cache and database simultaneously\n- **Write-Behind** — Buffer writes, batch to database\n\n### Query Optimization\n- Prepared statements for common queries\n- Connection pooling for database access\n- Batch operations for bulk inserts\u002Fupdates\n- Pagination for large result sets\n\n### Memory Pressure Handling\n- Monitor memory usage thresholds\n- Auto-evict low-priority entries\n- Compress old data\n- Archive to cold storage\n\n## Learning Patterns\n\n### Trajectory-Based Learning\nRecord operations → Analyze outcomes → Discover patterns → Suggest improvements.\n\n### Feedback Loop\n```\nAction → Outcome → Score → Store → Analyze → Improve → Action (better)\n```\n\n### Knowledge Accumulation\n- Store successful patterns with confidence scores\n- Track failure modes and recovery strategies\n- Build knowledge graphs linking related concepts\n- Prune outdated or contradicted knowledge\n\n## Aurion AgentDB Integration\n\n### Credit System Memory\n```\nuser_credits table:\n  - balance (atomic deduction)\n  - monthly_allowance (plan-based)\n  - period_start\u002Fperiod_end (lazy reset)\n  - bonus_credits (one-time additions)\nMemory pattern: Cache user credits in React Query, invalidate on deduction\n```\n\n### Tool Session Memory\n```\nEach of 11 tools maintains session state:\n  - Chat history (chat tool)\n  - File tree (IDE, 1code)\n  - Canvas state (ai-marketing)\n  - Editor content (text-editor, code-editor)\nMemory pattern: Supabase Realtime for sync, local buffer for offline\n```\n\n### Research Memory\n```\nResearch results from Tavily\u002FExa\u002FBrave:\n  - Store in .research\u002Flatest.json\n  - TTL: 24 hours\n  - Key: topic + source hash\n  - Inject into LLM context automatically\n```\n\n## Best Practices\n\n1. Use appropriate memory tier for access pattern\n2. Set TTLs on all non-permanent entries\n3. Index frequently queried fields\n4. Batch writes to reduce database round-trips\n5. Monitor memory pressure and cache hit rates\n6. Prune old data regularly\n7. Use vector search for semantic queries, exact search for known keys\n","# AgentDB Patterns\n\nMemory persistence, vector search, optimization, and learning patterns for AI agent systems.\n\n## Memory Patterns\n\n### Memory Types\n- **Ephemeral** — Current session only, fast access (Zustand store)\n- **Persistent** — Survives sessions, database-backed (Supabase)\n- **Shared** — Accessible across agents (coordination memory)\n- **Private** — Agent-specific, isolated context\n\n### Memory Hierarchy\n```\nL1: In-memory cache (Zustand) — \u003C1ms access\nL2: Local storage\u002FIndexedDB — \u003C10ms access\nL3: Supabase PostgreSQL — \u003C50ms access\nL4: External APIs (OpenRouter context) — \u003C500ms access\n```\n\n### Memory Operations\n- **Store** — Save with key, value, type, optional TTL\n- **Retrieve** — Get by exact key\n- **Search** — Pattern-based search (prefix, regex)\n- **Associate** — Link related memories (e.g., \"auth\" ↔ \"jwt\" ↔ \"refresh-token\")\n- **Consolidate** — Merge duplicate\u002Frelated entries\n- **Prune** — Remove expired or low-value entries\n\n## Vector Search Patterns\n\n### Embedding-Based Search\nUse vector embeddings for semantic similarity:\n- Convert text to embeddings (OpenAI\u002FSupabase pgvector)\n- Store embeddings alongside content\n- Query with cosine similarity\n- Filter by metadata (type, date, confidence)\n\n### Search Strategies\n- **Exact Match** — Key-based lookup, fastest\n- **Prefix Search** — Namespace-based, good for hierarchical data\n- **Semantic Search** — Vector similarity, best for natural language queries\n- **Hybrid** — Combine exact + semantic for best results\n\n### Supabase pgvector Integration\n```sql\n-- Enable vector extension\nCREATE EXTENSION IF NOT EXISTS vector;\n\n-- Add embedding column\nALTER TABLE knowledge_base ADD COLUMN embedding vector(1536);\n\n-- Create index for fast similarity search\nCREATE INDEX ON knowledge_base USING ivfflat (embedding vector_cosine_ops);\n\n-- Query similar items\nSELECT *, 1 - (embedding \u003C=> query_embedding) as similarity\nFROM knowledge_base\nORDER BY embedding \u003C=> query_embedding\nLIMIT 10;\n```\n\n## Optimization Patterns\n\n### Cache Strategies\n- **LRU Cache** — Evict least recently used entries\n- **TTL Cache** — Time-based expiration\n- **Write-Through** — Update cache and database simultaneously\n- **Write-Behind** — Buffer writes, batch to database\n\n### Query Optimization\n- Prepared statements for common queries\n- Connection pooling for database access\n- Batch operations for bulk inserts\u002Fupdates\n- Pagination for large result sets\n\n### Memory Pressure Handling\n- Monitor memory usage thresholds\n- Auto-evict low-priority entries\n- Compress old data\n- Archive to cold storage\n\n## Learning Patterns\n\n### Trajectory-Based Learning\nRecord operations → Analyze outcomes → Discover patterns → Suggest improvements.\n\n### Feedback Loop\n```\nAction → Outcome → Score → Store → Analyze → Improve → Action (better)\n```\n\n### Knowledge Accumulation\n- Store successful patterns with confidence scores\n- Track failure modes and recovery strategies\n- Build knowledge graphs linking related concepts\n- Prune outdated or contradicted knowledge\n\n## Aurion AgentDB Integration\n\n### Credit System Memory\n```\nuser_credits table:\n  - balance (atomic deduction)\n  - monthly_allowance (plan-based)\n  - period_start\u002Fperiod_end (lazy reset)\n  - bonus_credits (one-time additions)\nMemory pattern: Cache user credits in React Query, invalidate on deduction\n```\n\n### Tool Session Memory\n```\nEach of 11 tools maintains session state:\n  - Chat history (chat tool)\n  - File tree (IDE, 1code)\n  - Canvas state (ai-marketing)\n  - Editor content (text-editor, code-editor)\nMemory pattern: Supabase Realtime for sync, local buffer for offline\n```\n\n### Research Memory\n```\nResearch results from Tavily\u002FExa\u002FBrave:\n  - Store in .research\u002Flatest.json\n  - TTL: 24 hours\n  - Key: topic + source hash\n  - Inject into LLM context automatically\n```\n\n## Best Practices\n\n1. Use appropriate memory tier for access pattern\n2. Set TTLs on all non-permanent entries\n3. Index frequently queried fields\n4. Batch writes to reduce database round-trips\n5. Monitor memory pressure and cache hit rates\n6. Prune old data regularly\n7. Use vector search for semantic queries, exact search for known keys\n",{"name":5,"description":7},"main","5593cf3c72898ea9fc67225d452fe38f866ba6dd",".claude\u002F_archive\u002Fskills\u002Fagentdb-patterns","https:\u002F\u002Fgithub.com\u002Faicreator350\u002FaurionOFFICIELLE","https:\u002F\u002Fgithub.com\u002Faicreator350","2026-05-18 03:39:30",{"source":8,"skillName":5,"commands":30,"prompt":40,"zipAvailable":41},[31,34,37],{"tool":32,"command":33},"npx","npx skills add aicreator350\u002FaurionOFFICIELLE --skill agentdb-patterns",{"tool":35,"command":36},"bunx","bunx skills add aicreator350\u002FaurionOFFICIELLE --skill agentdb-patterns",{"tool":38,"command":39},"pnpm","pnpm dlx skills add aicreator350\u002FaurionOFFICIELLE --skill agentdb-patterns","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Faicreator350\u002FaurionOFFICIELLE\u002Fblob\u002Fmain\u002F.claude\u002F_archive\u002Fskills\u002Fagentdb-patterns\u002FSKILL.md",true,[],[44,53,60,67,74,81],{"skillNo":45,"name":46,"nameZh":6,"description":47,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":48,"licenseFileUrl":49,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":18},"01M74CAJWR9WB6DX1HF2V461Y0","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Faicreator350\u002FaurionOFFICIELLE\u002Fblob\u002Fmain\u002Fskills\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Faicreator350\u002FaurionOFFICIELLE\u002Fblob\u002Fmain\u002Fskills\u002Fwebapp-testing\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":18},"01M74CAFWC2H75GJ81B39C9RSW","web-design-guidelines","Review UI code for Web Interface Guidelines compliance. Use when asked to \"review my UI\", \"check accessibility\", \"audit design\", \"review UX\", or \"check my site against best practices\".","https:\u002F\u002Fgithub.com\u002Faicreator350\u002FaurionOFFICIELLE\u002Fblob\u002Fmain\u002Fskills\u002Fweb-design-guidelines\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":18},"01M74CA9N2HTGCKJ93AE9NQMHA","vercel-react-view-transitions","Guide for implementing smooth, native-feeling animations using React's View Transition API (`\u003CViewTransition>` component, `addTransitionType`, and CSS view transition pseudo-elements). Use this skill whenever the user wants to add page transitions, animate route changes, create shared element animations, animate enter\u002Fexit of components, animate list reorder, implement directional (forward\u002Fback) navigation animations, or integrate view transitions in Next.js. Also use when the user mentions view transitions, `startViewTransition`, `ViewTransition`, transition types, or asks about animating between UI states in React without third-party animation libraries.","https:\u002F\u002Fgithub.com\u002Faicreator350\u002FaurionOFFICIELLE\u002Fblob\u002Fmain\u002Fskills\u002Fvercel-react-view-transitions\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":18},"01M74CA364D4EVDXZZQRVK1Z73","vercel-react-best-practices","React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React\u002FNext.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.","https:\u002F\u002Fgithub.com\u002Faicreator350\u002FaurionOFFICIELLE\u002Fblob\u002Fmain\u002Fskills\u002Fvercel-react-best-practices\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":18},"01M74C9YQZX1GVS18V0AYCYPZE","vercel-composition-patterns","React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.","https:\u002F\u002Fgithub.com\u002Faicreator350\u002FaurionOFFICIELLE\u002Fblob\u002Fmain\u002Fskills\u002Fvercel-composition-patterns\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":18},"01M74C9SEYD6F764Q1JACZX3A6","vercel-cli-with-tokens","Deploy and manage projects on Vercel using token-based authentication. Use when working with Vercel CLI using access tokens rather than interactive login — e.g. \"deploy to vercel\", \"set up vercel\", \"add environment variables to vercel\".","https:\u002F\u002Fgithub.com\u002Faicreator350\u002FaurionOFFICIELLE\u002Fblob\u002Fmain\u002Fskills\u002Fvercel-cli-with-tokens\u002FSKILL.md",[],[]]