[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71GZN5HA5VQ3TTHC3TSNJZ1":3,"skill-same:01M71GZN5HA5VQ3TTHC3TSNJZ1":58},{"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":25,"linkOnly":26,"markdownContent":27,"markdownBody":28,"frontMatter":29,"refName":31,"commitSha":32,"skillDirectory":33,"forksCount":34,"repositoryHtmlUrl":35,"repositoryHomepageUrl":6,"ownerHtmlUrl":36,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":37,"install":38,"resources":51},"01M71GZN5HA5VQ3TTHC3TSNJZ1","memory",null,"Persistent memory system for preferences, facts, and notes","JSGforever\u002Fskillguard","JSGforever","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F85541948?v=4","01M71FQD3E132VMR5F4TAYX3YS","01M71FQD4DYW0XJ4XQ4YQH75Y9",2,"GPL-3.0","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__alsk1992--memory\u002FSKILL.md",[],[5,18,19,20,21,22,23,24],"for","system","memory system","preferences","facts","notes","persistent memory","2026-11-10 10:12:30",false,"---\nname: memory\ndescription: \"Persistent memory system for preferences, facts, and notes\"\nemoji: \"🧠\"\n---\n\n# Memory - Complete API Reference\n\nStore and recall user preferences, facts, and notes across conversations. Semantic search powered by vector embeddings.\n\n---\n\n## Chat Commands\n\n### Store Memories\n\n```\n\u002Fremember preference risk=conservative      Save trading preference\n\u002Fremember fact BTC halving is in April 2028 Store a fact\n\u002Fremember note Check ETH before market open Save a note\n\u002Fremember rule Never trade during FOMC      Store trading rule\n```\n\n### Recall Memories\n\n```\n\u002Fmemory                                     View all memories\n\u002Fmemory preferences                         View preferences only\n\u002Fmemory facts                               View facts only\n\u002Fmemory notes                               View notes only\n\u002Fmemory rules                               View trading rules\n\u002Fmemory search \"bitcoin\"                    Search memories\n```\n\n### Forget Memories\n\n```\n\u002Fforget \u003Ckey>                               Delete specific memory\n\u002Fforget all preferences                     Clear all preferences\n\u002Fforget all                                 Clear everything (careful!)\n```\n\n---\n\n## TypeScript API Reference\n\n### Create Memory Service\n\n```typescript\nimport { createMemoryService } from 'clodds\u002Fmemory';\n\nconst memory = createMemoryService({\n  \u002F\u002F Storage backend\n  backend: 'lancedb',  \u002F\u002F 'lancedb' | 'sqlite' | 'postgres'\n\n  \u002F\u002F Embedding model\n  embeddings: {\n    provider: 'openai',\n    model: 'text-embedding-3-small',\n  },\n\n  \u002F\u002F Options\n  encryptionKey: process.env.MEMORY_ENCRYPTION_KEY,\n});\n```\n\n### Remember (Store)\n\n```typescript\n\u002F\u002F Store a preference\nawait memory.remember({\n  userId: 'user-123',\n  type: 'preference',\n  key: 'risk_tolerance',\n  value: 'conservative',\n});\n\n\u002F\u002F Store a fact\nawait memory.remember({\n  userId: 'user-123',\n  type: 'fact',\n  content: 'BTC halving occurs approximately every 4 years',\n  metadata: { topic: 'crypto', confidence: 0.95 },\n});\n\n\u002F\u002F Store a note\nawait memory.remember({\n  userId: 'user-123',\n  type: 'note',\n  content: 'Check Polymarket for election markets before Tuesday',\n  metadata: { priority: 'high' },\n});\n\n\u002F\u002F Store a trading rule\nawait memory.remember({\n  userId: 'user-123',\n  type: 'rule',\n  content: 'Never trade more than 5% of portfolio on single position',\n});\n```\n\n### Recall (Retrieve)\n\n```typescript\n\u002F\u002F Get all memories for user\nconst all = await memory.recall({ userId: 'user-123' });\n\n\u002F\u002F Get by type\nconst preferences = await memory.recall({\n  userId: 'user-123',\n  type: 'preference',\n});\n\n\u002F\u002F Get specific key\nconst risk = await memory.recall({\n  userId: 'user-123',\n  type: 'preference',\n  key: 'risk_tolerance',\n});\n```\n\n### Semantic Search\n\n```typescript\n\u002F\u002F Search by meaning (not just keywords)\nconst results = await memory.semanticSearch({\n  userId: 'user-123',\n  query: 'what is my risk appetite?',\n  limit: 5,\n  threshold: 0.7,  \u002F\u002F Similarity threshold\n});\n\nfor (const result of results) {\n  console.log(`${result.type}: ${result.content}`);\n  console.log(`  Similarity: ${result.score}`);\n}\n```\n\n### Forget (Delete)\n\n```typescript\n\u002F\u002F Delete specific memory\nawait memory.forget({\n  userId: 'user-123',\n  type: 'preference',\n  key: 'risk_tolerance',\n});\n\n\u002F\u002F Delete all of a type\nawait memory.forgetByType({\n  userId: 'user-123',\n  type: 'note',\n});\n\n\u002F\u002F Delete all memories\nawait memory.forgetAll({ userId: 'user-123' });\n```\n\n### Daily Journal\n\n```typescript\n\u002F\u002F Log daily activity\nawait memory.logDaily({\n  userId: 'user-123',\n  date: new Date(),\n  trades: 5,\n  pnl: 123.45,\n  notes: 'Good day, caught BTC rally',\n});\n\n\u002F\u002F Get journal entries\nconst journal = await memory.getDailyLogs({\n  userId: 'user-123',\n  from: '2024-01-01',\n  to: '2024-01-31',\n});\n```\n\n---\n\n## Memory Types\n\n| Type | Purpose | Example |\n|------|---------|---------|\n| **preference** | User settings | `risk=conservative` |\n| **fact** | Stored knowledge | \"ETH gas is cheaper on weekends\" |\n| **note** | Reminders\u002Ftodos | \"Check election markets\" |\n| **rule** | Trading rules | \"Max 5% per position\" |\n| **context** | Conversation context | Auto-saved by system |\n\n---\n\n## Storage Backends\n\n| Backend | Description | Best For |\n|---------|-------------|----------|\n| **LanceDB** | Vector DB with hybrid search | Production, semantic search |\n| **SQLite** | Local file-based | Development, single user |\n| **PostgreSQL** | Distributed with pgvector | Multi-user, production |\n\n---\n\n## Best Practices\n\n1. **Be specific with keys** — `max_position_size` not just `size`\n2. **Use types correctly** — Preferences for settings, rules for constraints\n3. **Semantic search** — Ask questions naturally, embeddings will match\n4. **Regular cleanup** — Delete outdated notes and facts\n5. **Backup memories** — Export before major changes\n","# Memory - Complete API Reference\n\nStore and recall user preferences, facts, and notes across conversations. Semantic search powered by vector embeddings.\n\n---\n\n## Chat Commands\n\n### Store Memories\n\n```\n\u002Fremember preference risk=conservative      Save trading preference\n\u002Fremember fact BTC halving is in April 2028 Store a fact\n\u002Fremember note Check ETH before market open Save a note\n\u002Fremember rule Never trade during FOMC      Store trading rule\n```\n\n### Recall Memories\n\n```\n\u002Fmemory                                     View all memories\n\u002Fmemory preferences                         View preferences only\n\u002Fmemory facts                               View facts only\n\u002Fmemory notes                               View notes only\n\u002Fmemory rules                               View trading rules\n\u002Fmemory search \"bitcoin\"                    Search memories\n```\n\n### Forget Memories\n\n```\n\u002Fforget \u003Ckey>                               Delete specific memory\n\u002Fforget all preferences                     Clear all preferences\n\u002Fforget all                                 Clear everything (careful!)\n```\n\n---\n\n## TypeScript API Reference\n\n### Create Memory Service\n\n```typescript\nimport { createMemoryService } from 'clodds\u002Fmemory';\n\nconst memory = createMemoryService({\n  \u002F\u002F Storage backend\n  backend: 'lancedb',  \u002F\u002F 'lancedb' | 'sqlite' | 'postgres'\n\n  \u002F\u002F Embedding model\n  embeddings: {\n    provider: 'openai',\n    model: 'text-embedding-3-small',\n  },\n\n  \u002F\u002F Options\n  encryptionKey: process.env.MEMORY_ENCRYPTION_KEY,\n});\n```\n\n### Remember (Store)\n\n```typescript\n\u002F\u002F Store a preference\nawait memory.remember({\n  userId: 'user-123',\n  type: 'preference',\n  key: 'risk_tolerance',\n  value: 'conservative',\n});\n\n\u002F\u002F Store a fact\nawait memory.remember({\n  userId: 'user-123',\n  type: 'fact',\n  content: 'BTC halving occurs approximately every 4 years',\n  metadata: { topic: 'crypto', confidence: 0.95 },\n});\n\n\u002F\u002F Store a note\nawait memory.remember({\n  userId: 'user-123',\n  type: 'note',\n  content: 'Check Polymarket for election markets before Tuesday',\n  metadata: { priority: 'high' },\n});\n\n\u002F\u002F Store a trading rule\nawait memory.remember({\n  userId: 'user-123',\n  type: 'rule',\n  content: 'Never trade more than 5% of portfolio on single position',\n});\n```\n\n### Recall (Retrieve)\n\n```typescript\n\u002F\u002F Get all memories for user\nconst all = await memory.recall({ userId: 'user-123' });\n\n\u002F\u002F Get by type\nconst preferences = await memory.recall({\n  userId: 'user-123',\n  type: 'preference',\n});\n\n\u002F\u002F Get specific key\nconst risk = await memory.recall({\n  userId: 'user-123',\n  type: 'preference',\n  key: 'risk_tolerance',\n});\n```\n\n### Semantic Search\n\n```typescript\n\u002F\u002F Search by meaning (not just keywords)\nconst results = await memory.semanticSearch({\n  userId: 'user-123',\n  query: 'what is my risk appetite?',\n  limit: 5,\n  threshold: 0.7,  \u002F\u002F Similarity threshold\n});\n\nfor (const result of results) {\n  console.log(`${result.type}: ${result.content}`);\n  console.log(`  Similarity: ${result.score}`);\n}\n```\n\n### Forget (Delete)\n\n```typescript\n\u002F\u002F Delete specific memory\nawait memory.forget({\n  userId: 'user-123',\n  type: 'preference',\n  key: 'risk_tolerance',\n});\n\n\u002F\u002F Delete all of a type\nawait memory.forgetByType({\n  userId: 'user-123',\n  type: 'note',\n});\n\n\u002F\u002F Delete all memories\nawait memory.forgetAll({ userId: 'user-123' });\n```\n\n### Daily Journal\n\n```typescript\n\u002F\u002F Log daily activity\nawait memory.logDaily({\n  userId: 'user-123',\n  date: new Date(),\n  trades: 5,\n  pnl: 123.45,\n  notes: 'Good day, caught BTC rally',\n});\n\n\u002F\u002F Get journal entries\nconst journal = await memory.getDailyLogs({\n  userId: 'user-123',\n  from: '2024-01-01',\n  to: '2024-01-31',\n});\n```\n\n---\n\n## Memory Types\n\n| Type | Purpose | Example |\n|------|---------|---------|\n| **preference** | User settings | `risk=conservative` |\n| **fact** | Stored knowledge | \"ETH gas is cheaper on weekends\" |\n| **note** | Reminders\u002Ftodos | \"Check election markets\" |\n| **rule** | Trading rules | \"Max 5% per position\" |\n| **context** | Conversation context | Auto-saved by system |\n\n---\n\n## Storage Backends\n\n| Backend | Description | Best For |\n|---------|-------------|----------|\n| **LanceDB** | Vector DB with hybrid search | Production, semantic search |\n| **SQLite** | Local file-based | Development, single user |\n| **PostgreSQL** | Distributed with pgvector | Multi-user, production |\n\n---\n\n## Best Practices\n\n1. **Be specific with keys** — `max_position_size` not just `size`\n2. **Use types correctly** — Preferences for settings, rules for constraints\n3. **Semantic search** — Ask questions naturally, embeddings will match\n4. **Regular cleanup** — Delete outdated notes and facts\n5. **Backup memories** — Export before major changes\n",{"name":5,"emoji":30,"description":7},"🧠","main","f2ec4b3b9133d34eeaf9b38e4b0a97e8e5705a7f","benchmarks\u002Ffinal\u002Fskills\u002Fasset1__alsk1992--memory",0,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard","https:\u002F\u002Fgithub.com\u002FJSGforever","2026-08-29 18:27:56",{"source":8,"skillName":5,"commands":39,"prompt":49,"zipAvailable":50},[40,43,46],{"tool":41,"command":42},"npx","npx skills add JSGforever\u002Fskillguard --skill memory",{"tool":44,"command":45},"bunx","bunx skills add JSGforever\u002Fskillguard --skill memory",{"tool":47,"command":48},"pnpm","pnpm dlx skills add JSGforever\u002Fskillguard --skill memory","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__alsk1992--memory\u002FSKILL.md",true,[52],{"path":53,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":57},"index.ts","SCRIPT","脚本",7220,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__alsk1992--memory\u002Findex.ts",[59,91,107,134,156,177],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":70,"publishedAt":25},"01M71HY2SNXBA9Q00WZDTZQ31Z","skillguard-codex-scanner","Hybrid deterministic+LLM agent-skill security scanner. Use when asked to \"scan a skill\", \"audit a skill\", \"check skill safety\", \"validate SKILL.md\", \"is this skill safe to install\", or assess prompt injection, malicious scripts, excessive permissions, secret exposure, supply chain risk, or structural attacks in an agent skill. Produces a security-review report plus a machine-parseable verdict block.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fsrc\u002Fskillguard\u002Fstatic_scanner\u002Fskillguard-codex-scanner\u002FSKILL.md",[65],{"categoryNo":66,"categoryName":67,"taxonomyType":68,"taxonomyTypeDesc":69},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90],"scanner","skillguard codex scanner","skillguard","codex","chain","skill security","security-review","review report","structural","secret","prompt injection","security scanner","when","review","malicious","permissions","exposure","audit","scripts","safe",{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":95,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":103,"publishedAt":25},"01M71HY0SPKTT3S27BC2HPAC5M","data-exfiltrator","Analyzes data files","MIT","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Fsmoke-one-skill\u002Fasset1__cisco-ai-defense--data-exfiltrator\u002FSKILL.md",[98],{"categoryNo":99,"categoryName":100,"taxonomyType":101,"taxonomyTypeDesc":102},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[104,105,106],"data","data exfiltrator","files",{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":25},"01M71HXVS9EMN44BGDW215FZ72","real-time-collaboration-engine","Build real-time collaborative editing with WebSockets, OT\u002FCRDT conflict resolution, and presence awareness. Implements cursor tracking, optimistic updates, and offline sync. Use for collaborative editors, whiteboards, video editing. Activate on \"real-time collaboration\", \"WebSocket sync\", \"multiplayer editing\", \"CRDT\", \"presence awareness\". NOT for simple chat, request-response APIs, or single-user apps.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--real-time-collaboration-engine\u002FSKILL.md",[],[114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133],"time","real time collaboration engine","real time collaboration","collaboration","engine","real time","Video","reliability","video editing","performance","conflict resolution","presence","access","apps","updates","Bash","activate","optimizer","react","streaming",{"skillNo":135,"name":136,"nameZh":6,"description":137,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":138,"categories":139,"keywords":143,"publishedAt":25},"01M71HXP6CTY4KFN0QVMMN0V7J","react-performance-optimizer","Optimize React apps for 60fps performance. Implements memoization, virtualization, code splitting, bundle optimization. Use for slow renders, large lists, bundle bloat. Activate on \"React performance\", \"slow render\", \"useMemo\", \"bundle size\", \"virtualization\". NOT for backend optimization, non-React frameworks, or premature optimization.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--react-performance-optimizer\u002FSKILL.md",[140],{"categoryNo":141,"categoryName":142,"taxonomyType":68,"taxonomyTypeDesc":69},"01JBSEEDCAT000000000000009","前端开发",[123,144,131,132,145,146,147,148,149,150,114,151,152,127,129,153,130,133,154,155],"react performance optimizer","react performance","performance optimizer","app","nextjs","expert","re","render","2025","code","router","strategies",{"skillNo":157,"name":158,"nameZh":6,"description":159,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":160,"categories":161,"keywords":163,"publishedAt":25},"01M71HXH7QXSQB4QTDZ7SP7YXQ","llm-streaming-response-handler","Build production LLM streaming UIs with Server-Sent Events, real-time token display, cancellation, error recovery. Handles OpenAI\u002FAnthropic\u002FClaude streaming APIs. Use for chatbots, AI assistants, real-time text generation. Activate on \"LLM streaming\", \"SSE\", \"token stream\", \"chat UI\", \"real-time AI\". NOT for batch processing, non-streaming APIs, or WebSocket bidirectional chat.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--llm-streaming-response-handler\u002FSKILL.md",[162],{"categoryNo":141,"categoryName":142,"taxonomyType":68,"taxonomyTypeDesc":69},[164,133,165,166,167,168,123,114,169,170,171,129,130,131,172,132,173,174,175,176],"llm streaming response handler","handler","error","processing","retry","chat ui","error recovery","critical","batch","display","text","server","read",{"skillNo":178,"name":179,"nameZh":6,"description":180,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":181,"categories":182,"keywords":190,"publishedAt":25},"01M71HXCB0E1YRKYW1Y8T0Y106","github-actions-pipeline-builder","Build production CI\u002FCD pipelines with GitHub Actions. Implements matrix builds, caching, deployments, testing, security scanning. Use for automated testing, deployments, release workflows. Activate on \"GitHub Actions\", \"CI\u002FCD\", \"workflow\", \"deployment pipeline\", \"automated testing\". NOT for Jenkins\u002FCircleCI, manual deployments, or non-GitHub repositories.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--github-actions-pipeline-builder\u002FSKILL.md",[183,186,189],{"categoryNo":184,"categoryName":185,"taxonomyType":68,"taxonomyTypeDesc":69},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":187,"categoryName":188,"taxonomyType":68,"taxonomyTypeDesc":69},"01JBSEEDCAT000000000000011","运维与部署",{"categoryNo":66,"categoryName":67,"taxonomyType":68,"taxonomyTypeDesc":69},[191,192,193,194,195,196,197,121,149,198,199,200,130,155,201,176,202,203,204,205],"github actions pipeline builder","actions","github actions","pipeline builder","github","builder","pipeline","testing","ci","workflows","run","release","write","edit","git"]