[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EWJ4XNJVPXSHHEKA698KSW":3,"skill-same:01M7EWJ4XNJVPXSHHEKA698KSW":46},{"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":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M7EWJ4XNJVPXSHHEKA698KSW","AgentDB Memory Patterns",null,"Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use when building stateful agents, chat systems, or intelligent assistants.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fagentdb-memory-patterns-ruflo\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: \"AgentDB Memory Patterns\"\ndescription: \"Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use when building stateful agents, chat systems, or intelligent assistants.\"\n---\n\n# AgentDB Memory Patterns\n\n## What This Skill Does\n\nProvides memory management patterns for AI agents using AgentDB's persistent storage and ReasoningBank integration. Enables agents to remember conversations, learn from interactions, and maintain context across sessions.\n\n**Performance**: 150x-12,500x faster than traditional solutions with 100% backward compatibility.\n\n## Prerequisites\n\n- Node.js 18+\n- AgentDB v1.0.7+ (via agentic-flow or standalone)\n- Understanding of agent architectures\n\n## Quick Start with CLI\n\n### Initialize AgentDB\n\n```bash\n# Initialize vector database\nnpx agentdb@latest init .$agents.db\n\n# Or with custom dimensions\nnpx agentdb@latest init .$agents.db --dimension 768\n\n# Use preset configurations\nnpx agentdb@latest init .$agents.db --preset large\n\n# In-memory database for testing\nnpx agentdb@latest init .$memory.db --in-memory\n```\n\n### Start MCP Server for Claude Code\n\n```bash\n# Start MCP server (integrates with Claude Code)\nnpx agentdb@latest mcp\n\n# Add to Claude Code (one-time setup)\nclaude mcp add agentdb npx agentdb@latest mcp\n```\n\n### Create Learning Plugin\n\n```bash\n# Interactive plugin wizard\nnpx agentdb@latest create-plugin\n\n# Use template directly\nnpx agentdb@latest create-plugin -t decision-transformer -n my-agent\n\n# Available templates:\n# - decision-transformer (sequence modeling RL)\n# - q-learning (value-based learning)\n# - sarsa (on-policy TD learning)\n# - actor-critic (policy gradient)\n# - curiosity-driven (exploration-based)\n```\n\n## Quick Start with API\n\n```typescript\nimport { createAgentDBAdapter } from 'agentic-flow$reasoningbank';\n\n\u002F\u002F Initialize with default configuration\nconst adapter = await createAgentDBAdapter({\n  dbPath: '.agentdb$reasoningbank.db',\n  enableLearning: true,      \u002F\u002F Enable learning plugins\n  enableReasoning: true,      \u002F\u002F Enable reasoning agents\n  quantizationType: 'scalar', \u002F\u002F binary | scalar | product | none\n  cacheSize: 1000,            \u002F\u002F In-memory cache\n});\n\n\u002F\u002F Store interaction memory\nconst patternId = await adapter.insertPattern({\n  id: '',\n  type: 'pattern',\n  domain: 'conversation',\n  pattern_data: JSON.stringify({\n    embedding: await computeEmbedding('What is the capital of France?'),\n    pattern: {\n      user: 'What is the capital of France?',\n      assistant: 'The capital of France is Paris.',\n      timestamp: Date.now()\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 context with reasoning\nconst context = await adapter.retrieveWithReasoning(queryEmbedding, {\n  domain: 'conversation',\n  k: 10,\n  useMMR: true,              \u002F\u002F Maximal Marginal Relevance\n  synthesizeContext: true,    \u002F\u002F Generate rich context\n});\n```\n\n## Memory Patterns\n\n### 1. Session Memory\n```typescript\nclass SessionMemory {\n  async storeMessage(role: string, content: string) {\n    return await db.storeMemory({\n      sessionId: this.sessionId,\n      role,\n      content,\n      timestamp: Date.now()\n    });\n  }\n\n  async getSessionHistory(limit = 20) {\n    return await db.query({\n      filters: { sessionId: this.sessionId },\n      orderBy: 'timestamp',\n      limit\n    });\n  }\n}\n```\n\n### 2. Long-Term Memory\n```typescript\n\u002F\u002F Store important facts\nawait db.storeFact({\n  category: 'user_preference',\n  key: 'language',\n  value: 'English',\n  confidence: 1.0,\n  source: 'explicit'\n});\n\n\u002F\u002F Retrieve facts\nconst prefs = await db.getFacts({\n  category: 'user_preference'\n});\n```\n\n### 3. Pattern Learning\n```typescript\n\u002F\u002F Learn from successful interactions\nawait db.storePattern({\n  trigger: 'user_asks_time',\n  response: 'provide_formatted_time',\n  success: true,\n  context: { timezone: 'UTC' }\n});\n\n\u002F\u002F Apply learned patterns\nconst pattern = await db.matchPattern(currentContext);\n```\n\n## Advanced Patterns\n\n### Hierarchical Memory\n```typescript\n\u002F\u002F Organize memory in hierarchy\nawait memory.organize({\n  immediate: recentMessages,    \u002F\u002F Last 10 messages\n  shortTerm: sessionContext,    \u002F\u002F Current session\n  longTerm: importantFacts,     \u002F\u002F Persistent facts\n  semantic: embeddedKnowledge   \u002F\u002F Vector search\n});\n```\n\n### Memory Consolidation\n```typescript\n\u002F\u002F Periodically consolidate memories\nawait memory.consolidate({\n  strategy: 'importance',       \u002F\u002F Keep important memories\n  maxSize: 10000,              \u002F\u002F Size limit\n  minScore: 0.5                \u002F\u002F Relevance threshold\n});\n```\n\n## CLI Operations\n\n### Query Database\n\n```bash\n# Query with vector embedding\nnpx agentdb@latest query .$agents.db \"[0.1,0.2,0.3,...]\"\n\n# Top-k results\nnpx agentdb@latest query .$agents.db \"[0.1,0.2,0.3]\" -k 10\n\n# With similarity threshold\nnpx agentdb@latest query .$agents.db \"0.1 0.2 0.3\" -t 0.75\n\n# JSON output\nnpx agentdb@latest query .$agents.db \"[...]\" -f json\n```\n\n### Import\u002FExport Data\n\n```bash\n# Export vectors to file\nnpx agentdb@latest export .$agents.db .$backup.json\n\n# Import vectors from file\nnpx agentdb@latest import .$backup.json\n\n# Get database statistics\nnpx agentdb@latest stats .$agents.db\n```\n\n### Performance Benchmarks\n\n```bash\n# Run performance benchmarks\nnpx agentdb@latest benchmark\n\n# Results show:\n# - Pattern Search: 150x faster (100µs vs 15ms)\n# - Batch Insert: 500x faster (2ms vs 1s)\n# - Large-scale Query: 12,500x faster (8ms vs 100s)\n```\n\n## Integration with ReasoningBank\n\n```typescript\nimport { createAgentDBAdapter, migrateToAgentDB } from 'agentic-flow$reasoningbank';\n\n\u002F\u002F Migrate from legacy ReasoningBank\nconst result = await migrateToAgentDB(\n  '.swarm$memory.db',           \u002F\u002F Source (legacy)\n  '.agentdb$reasoningbank.db'   \u002F\u002F Destination (AgentDB)\n);\n\nconsole.log(`✅ Migrated ${result.patternsMigrated} patterns`);\n\n\u002F\u002F Train learning model\nconst adapter = await createAgentDBAdapter({\n  enableLearning: true,\n});\n\nawait adapter.train({\n  epochs: 50,\n  batchSize: 32,\n});\n\n\u002F\u002F Get optimal strategy with reasoning\nconst result = await adapter.retrieveWithReasoning(queryEmbedding, {\n  domain: 'task-planning',\n  synthesizeContext: true,\n  optimizeMemory: true,\n});\n```\n\n## Learning Plugins\n\n### Available Algorithms (9 Total)\n\n1. **Decision Transformer** - Sequence modeling RL (recommended)\n2. **Q-Learning** - Value-based learning\n3. **SARSA** - On-policy TD learning\n4. **Actor-Critic** - Policy gradient with baseline\n5. **Active Learning** - Query selection\n6. **Adversarial Training** - Robustness\n7. **Curriculum Learning** - Progressive difficulty\n8. **Federated Learning** - Distributed learning\n9. **Multi-task Learning** - Transfer learning\n\n### List and Manage Plugins\n\n```bash\n# List available plugins\nnpx agentdb@latest list-plugins\n\n# List plugin templates\nnpx agentdb@latest list-templates\n\n# Get plugin info\nnpx agentdb@latest plugin-info \u003Cname>\n```\n\n## Reasoning Agents (4 Modules)\n\n1. **PatternMatcher** - Find similar patterns with HNSW indexing\n2. **ContextSynthesizer** - Generate rich context from multiple sources\n3. **MemoryOptimizer** - Consolidate similar patterns, prune low-quality\n4. **ExperienceCurator** - Quality-based experience filtering\n\n## Best Practices\n\n1. **Enable quantization**: Use scalar$binary for 4-32x memory reduction\n2. **Use caching**: 1000 pattern cache for \u003C1ms retrieval\n3. **Batch operations**: 500x faster than individual inserts\n4. **Train regularly**: Update learning models with new experiences\n5. **Enable reasoning**: Automatic context synthesis and optimization\n6. **Monitor metrics**: Use `stats` command to track performance\n\n## Troubleshooting\n\n### Issue: Memory growing too large\n```bash\n# Check database size\nnpx agentdb@latest stats .$agents.db\n\n# Enable quantization\n# Use 'binary' (32x smaller) or 'scalar' (4x smaller)\n```\n\n### Issue: Slow search performance\n```bash\n# Enable HNSW indexing and caching\n# Results: \u003C100µs search time\n```\n\n### Issue: Migration from legacy ReasoningBank\n```bash\n# Automatic migration with validation\nnpx agentdb@latest migrate --source .swarm$memory.db\n```\n\n## Performance Characteristics\n\n- **Vector Search**: \u003C100µs (HNSW indexing)\n- **Pattern Retrieval**: \u003C1ms (with cache)\n- **Batch Insert**: 2ms for 100 patterns\n- **Memory Efficiency**: 4-32x reduction with quantization\n- **Backward Compatibility**: 100% compatible with ReasoningBank API\n\n## Learn More\n\n- GitHub: https:\u002F$github.com$ruvnet$agentic-flow$tree$main$packages$agentdb\n- Documentation: node_modules$agentic-flow\u002Fdocs\u002FAGENTDB_INTEGRATION.md\n- MCP Integration: `npx agentdb@latest mcp` for Claude Code\n- Website: https:\u002F$agentdb.ruv.io\n","# AgentDB Memory Patterns\n\n## What This Skill Does\n\nProvides memory management patterns for AI agents using AgentDB's persistent storage and ReasoningBank integration. Enables agents to remember conversations, learn from interactions, and maintain context across sessions.\n\n**Performance**: 150x-12,500x faster than traditional solutions with 100% backward compatibility.\n\n## Prerequisites\n\n- Node.js 18+\n- AgentDB v1.0.7+ (via agentic-flow or standalone)\n- Understanding of agent architectures\n\n## Quick Start with CLI\n\n### Initialize AgentDB\n\n```bash\n# Initialize vector database\nnpx agentdb@latest init .$agents.db\n\n# Or with custom dimensions\nnpx agentdb@latest init .$agents.db --dimension 768\n\n# Use preset configurations\nnpx agentdb@latest init .$agents.db --preset large\n\n# In-memory database for testing\nnpx agentdb@latest init .$memory.db --in-memory\n```\n\n### Start MCP Server for Claude Code\n\n```bash\n# Start MCP server (integrates with Claude Code)\nnpx agentdb@latest mcp\n\n# Add to Claude Code (one-time setup)\nclaude mcp add agentdb npx agentdb@latest mcp\n```\n\n### Create Learning Plugin\n\n```bash\n# Interactive plugin wizard\nnpx agentdb@latest create-plugin\n\n# Use template directly\nnpx agentdb@latest create-plugin -t decision-transformer -n my-agent\n\n# Available templates:\n# - decision-transformer (sequence modeling RL)\n# - q-learning (value-based learning)\n# - sarsa (on-policy TD learning)\n# - actor-critic (policy gradient)\n# - curiosity-driven (exploration-based)\n```\n\n## Quick Start with API\n\n```typescript\nimport { createAgentDBAdapter } from 'agentic-flow$reasoningbank';\n\n\u002F\u002F Initialize with default configuration\nconst adapter = await createAgentDBAdapter({\n  dbPath: '.agentdb$reasoningbank.db',\n  enableLearning: true,      \u002F\u002F Enable learning plugins\n  enableReasoning: true,      \u002F\u002F Enable reasoning agents\n  quantizationType: 'scalar', \u002F\u002F binary | scalar | product | none\n  cacheSize: 1000,            \u002F\u002F In-memory cache\n});\n\n\u002F\u002F Store interaction memory\nconst patternId = await adapter.insertPattern({\n  id: '',\n  type: 'pattern',\n  domain: 'conversation',\n  pattern_data: JSON.stringify({\n    embedding: await computeEmbedding('What is the capital of France?'),\n    pattern: {\n      user: 'What is the capital of France?',\n      assistant: 'The capital of France is Paris.',\n      timestamp: Date.now()\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 context with reasoning\nconst context = await adapter.retrieveWithReasoning(queryEmbedding, {\n  domain: 'conversation',\n  k: 10,\n  useMMR: true,              \u002F\u002F Maximal Marginal Relevance\n  synthesizeContext: true,    \u002F\u002F Generate rich context\n});\n```\n\n## Memory Patterns\n\n### 1. Session Memory\n```typescript\nclass SessionMemory {\n  async storeMessage(role: string, content: string) {\n    return await db.storeMemory({\n      sessionId: this.sessionId,\n      role,\n      content,\n      timestamp: Date.now()\n    });\n  }\n\n  async getSessionHistory(limit = 20) {\n    return await db.query({\n      filters: { sessionId: this.sessionId },\n      orderBy: 'timestamp',\n      limit\n    });\n  }\n}\n```\n\n### 2. Long-Term Memory\n```typescript\n\u002F\u002F Store important facts\nawait db.storeFact({\n  category: 'user_preference',\n  key: 'language',\n  value: 'English',\n  confidence: 1.0,\n  source: 'explicit'\n});\n\n\u002F\u002F Retrieve facts\nconst prefs = await db.getFacts({\n  category: 'user_preference'\n});\n```\n\n### 3. Pattern Learning\n```typescript\n\u002F\u002F Learn from successful interactions\nawait db.storePattern({\n  trigger: 'user_asks_time',\n  response: 'provide_formatted_time',\n  success: true,\n  context: { timezone: 'UTC' }\n});\n\n\u002F\u002F Apply learned patterns\nconst pattern = await db.matchPattern(currentContext);\n```\n\n## Advanced Patterns\n\n### Hierarchical Memory\n```typescript\n\u002F\u002F Organize memory in hierarchy\nawait memory.organize({\n  immediate: recentMessages,    \u002F\u002F Last 10 messages\n  shortTerm: sessionContext,    \u002F\u002F Current session\n  longTerm: importantFacts,     \u002F\u002F Persistent facts\n  semantic: embeddedKnowledge   \u002F\u002F Vector search\n});\n```\n\n### Memory Consolidation\n```typescript\n\u002F\u002F Periodically consolidate memories\nawait memory.consolidate({\n  strategy: 'importance',       \u002F\u002F Keep important memories\n  maxSize: 10000,              \u002F\u002F Size limit\n  minScore: 0.5                \u002F\u002F Relevance threshold\n});\n```\n\n## CLI Operations\n\n### Query Database\n\n```bash\n# Query with vector embedding\nnpx agentdb@latest query .$agents.db \"[0.1,0.2,0.3,...]\"\n\n# Top-k results\nnpx agentdb@latest query .$agents.db \"[0.1,0.2,0.3]\" -k 10\n\n# With similarity threshold\nnpx agentdb@latest query .$agents.db \"0.1 0.2 0.3\" -t 0.75\n\n# JSON output\nnpx agentdb@latest query .$agents.db \"[...]\" -f json\n```\n\n### Import\u002FExport Data\n\n```bash\n# Export vectors to file\nnpx agentdb@latest export .$agents.db .$backup.json\n\n# Import vectors from file\nnpx agentdb@latest import .$backup.json\n\n# Get database statistics\nnpx agentdb@latest stats .$agents.db\n```\n\n### Performance Benchmarks\n\n```bash\n# Run performance benchmarks\nnpx agentdb@latest benchmark\n\n# Results show:\n# - Pattern Search: 150x faster (100µs vs 15ms)\n# - Batch Insert: 500x faster (2ms vs 1s)\n# - Large-scale Query: 12,500x faster (8ms vs 100s)\n```\n\n## Integration with ReasoningBank\n\n```typescript\nimport { createAgentDBAdapter, migrateToAgentDB } from 'agentic-flow$reasoningbank';\n\n\u002F\u002F Migrate from legacy ReasoningBank\nconst result = await migrateToAgentDB(\n  '.swarm$memory.db',           \u002F\u002F Source (legacy)\n  '.agentdb$reasoningbank.db'   \u002F\u002F Destination (AgentDB)\n);\n\nconsole.log(`✅ Migrated ${result.patternsMigrated} patterns`);\n\n\u002F\u002F Train learning model\nconst adapter = await createAgentDBAdapter({\n  enableLearning: true,\n});\n\nawait adapter.train({\n  epochs: 50,\n  batchSize: 32,\n});\n\n\u002F\u002F Get optimal strategy with reasoning\nconst result = await adapter.retrieveWithReasoning(queryEmbedding, {\n  domain: 'task-planning',\n  synthesizeContext: true,\n  optimizeMemory: true,\n});\n```\n\n## Learning Plugins\n\n### Available Algorithms (9 Total)\n\n1. **Decision Transformer** - Sequence modeling RL (recommended)\n2. **Q-Learning** - Value-based learning\n3. **SARSA** - On-policy TD learning\n4. **Actor-Critic** - Policy gradient with baseline\n5. **Active Learning** - Query selection\n6. **Adversarial Training** - Robustness\n7. **Curriculum Learning** - Progressive difficulty\n8. **Federated Learning** - Distributed learning\n9. **Multi-task Learning** - Transfer learning\n\n### List and Manage Plugins\n\n```bash\n# List available plugins\nnpx agentdb@latest list-plugins\n\n# List plugin templates\nnpx agentdb@latest list-templates\n\n# Get plugin info\nnpx agentdb@latest plugin-info \u003Cname>\n```\n\n## Reasoning Agents (4 Modules)\n\n1. **PatternMatcher** - Find similar patterns with HNSW indexing\n2. **ContextSynthesizer** - Generate rich context from multiple sources\n3. **MemoryOptimizer** - Consolidate similar patterns, prune low-quality\n4. **ExperienceCurator** - Quality-based experience filtering\n\n## Best Practices\n\n1. **Enable quantization**: Use scalar$binary for 4-32x memory reduction\n2. **Use caching**: 1000 pattern cache for \u003C1ms retrieval\n3. **Batch operations**: 500x faster than individual inserts\n4. **Train regularly**: Update learning models with new experiences\n5. **Enable reasoning**: Automatic context synthesis and optimization\n6. **Monitor metrics**: Use `stats` command to track performance\n\n## Troubleshooting\n\n### Issue: Memory growing too large\n```bash\n# Check database size\nnpx agentdb@latest stats .$agents.db\n\n# Enable quantization\n# Use 'binary' (32x smaller) or 'scalar' (4x smaller)\n```\n\n### Issue: Slow search performance\n```bash\n# Enable HNSW indexing and caching\n# Results: \u003C100µs search time\n```\n\n### Issue: Migration from legacy ReasoningBank\n```bash\n# Automatic migration with validation\nnpx agentdb@latest migrate --source .swarm$memory.db\n```\n\n## Performance Characteristics\n\n- **Vector Search**: \u003C100µs (HNSW indexing)\n- **Pattern Retrieval**: \u003C1ms (with cache)\n- **Batch Insert**: 2ms for 100 patterns\n- **Memory Efficiency**: 4-32x reduction with quantization\n- **Backward Compatibility**: 100% compatible with ReasoningBank API\n\n## Learn More\n\n- GitHub: https:\u002F$github.com$ruvnet$agentic-flow$tree$main$packages$agentdb\n- Documentation: node_modules$agentic-flow\u002Fdocs\u002FAGENTDB_INTEGRATION.md\n- MCP Integration: `npx agentdb@latest mcp` for Claude Code\n- Website: https:\u002F$agentdb.ruv.io\n",{"name":5,"description":7},"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","05-技能与代理开发\u002Fagentdb-memory-patterns-ruflo",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill \"AgentDB Memory Patterns\"",{"tool":38,"command":39},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill \"AgentDB Memory Patterns\"",{"tool":41,"command":42},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill \"AgentDB Memory Patterns\"","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fagentdb-memory-patterns-ruflo\u002FSKILL.md",true,[],[47,55,60,67,74,81],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":54},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],"2026-11-16 10:05:34",{"skillNo":56,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":54},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":54},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":54},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":54},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":54},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]