[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6J6P9TPC5R24Z1Z9VXCAPQW":3,"skill-same:01M6J6P9TPC5R24Z1Z9VXCAPQW":121},{"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":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":14,"repositoryHtmlUrl":52,"repositoryHomepageUrl":6,"ownerHtmlUrl":53,"ownerBlogUrl":54,"ownerDescription":55,"updatedAt":56,"install":57,"resources":70},"01M6J6P9TPC5R24Z1Z9VXCAPQW","mcp-management",null,"Manage Model Context Protocol (MCP) servers - discover, analyze, and execute tools\u002Fprompts\u002Fresources from configured MCP servers. Use when working with MCP integrations, need to discover available MCP capabilities, filter MCP tools for specific tasks, execute MCP tools programmatically, access MCP prompts\u002Fresources, or implement MCP client functionality. Supports intelligent tool selection, multi-server management, and context-efficient capability discovery.","ldanh270\u002Fcreate-skills-kit","ldanh270","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F117491247?v=4","01M6J6JM6HXDA2QYTMNGQC3QBV","Lê Đức Anh","01M6J6JMAM2DEECQ418M736HRV",0,"MIT","https:\u002F\u002Fgithub.com\u002Fldanh270\u002Fcreate-skills-kit\u002Fblob\u002Fmain\u002Fsource\u002F.agent\u002Fskills\u002Fmcp-management\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"management","mcp management","MCP","integrations","for","resources","filter","discover","with mcp","selection","context","model","analyze","access","discovery","Tools","server","capabilities","tasks","model context protocol","2026-11-10 10:12:30",false,"---\nname: mcp-management\ndescription: Manage Model Context Protocol (MCP) servers - discover, analyze, and execute tools\u002Fprompts\u002Fresources from configured MCP servers. Use when working with MCP integrations, need to discover available MCP capabilities, filter MCP tools for specific tasks, execute MCP tools programmatically, access MCP prompts\u002Fresources, or implement MCP client functionality. Supports intelligent tool selection, multi-server management, and context-efficient capability discovery.\n---\n\n# MCP Management\n\nSkill for managing and interacting with Model Context Protocol (MCP) servers.\n\n## Overview\n\nMCP is an open protocol enabling AI agents to connect to external tools and data sources. This skill provides scripts and utilities to discover, analyze, and execute MCP capabilities from configured servers without polluting the main context window.\n\n**Key Benefits**:\n- Progressive disclosure of MCP capabilities (load only what's needed)\n- Intelligent tool\u002Fprompt\u002Fresource selection based on task requirements\n- Multi-server management from single config file\n- Context-efficient: subagents handle MCP discovery and execution\n- Persistent tool catalog: automatically saves discovered tools to JSON for fast reference\n\n## When to Use This Skill\n\nUse this skill when:\n1. **Discovering MCP Capabilities**: Need to list available tools\u002Fprompts\u002Fresources from configured servers\n2. **Task-Based Tool Selection**: Analyzing which MCP tools are relevant for a specific task\n3. **Executing MCP Tools**: Calling MCP tools programmatically with proper parameter handling\n4. **MCP Integration**: Building or debugging MCP client implementations\n5. **Context Management**: Avoiding context pollution by delegating MCP operations to subagents\n\n## Core Capabilities\n\n### 1. Configuration Management\n\nMCP servers configured in `.claude\u002F.mcp.json`.\n\n**Gemini CLI Integration** (recommended): Create symlink to `.gemini\u002Fsettings.json`:\n```bash\nmkdir -p .gemini && ln -sf .claude\u002F.mcp.json .gemini\u002Fsettings.json\n```\n\nSee [references\u002Fconfiguration.md](references\u002Fconfiguration.md) and [references\u002Fgemini-cli-integration.md](references\u002Fgemini-cli-integration.md).\n\n**GEMINI.md Response Format**: Project root contains `GEMINI.md` that Gemini CLI auto-loads, enforcing structured JSON responses:\n```json\n{\"server\":\"name\",\"tool\":\"name\",\"success\":true,\"result\":\u003Cdata>,\"error\":null}\n```\n\nThis ensures parseable, consistent output instead of unpredictable natural language. The file defines:\n- Mandatory JSON-only response format (no markdown, no explanations)\n- Maximum 500 character responses\n- Error handling structure\n- Available MCP servers reference\n\n**Benefits**: Programmatically parseable output, consistent error reporting, DRY configuration (format defined once), context-efficient (auto-loaded by Gemini CLI).\n\n### 2. Capability Discovery\n\n```bash\nnpx tsx scripts\u002Fcli.ts list-tools  # Saves to assets\u002Ftools.json\nnpx tsx scripts\u002Fcli.ts list-prompts\nnpx tsx scripts\u002Fcli.ts list-resources\n```\n\nAggregates capabilities from multiple servers with server identification.\n\n### 3. Intelligent Tool Analysis\n\nLLM analyzes `assets\u002Ftools.json` directly - better than keyword matching algorithms.\n\n### 4. Tool Execution\n\n**Primary: Gemini CLI** (if available)\n```bash\n# IMPORTANT: Use stdin piping, NOT -p flag (deprecated, skips MCP init)\necho \"Take a screenshot of https:\u002F\u002Fexample.com\" | gemini -y -m gemini-2.5-flash\n```\n\n**Secondary: Direct Scripts**\n```bash\nnpx tsx scripts\u002Fcli.ts call-tool memory create_entities '{\"entities\":[...]}'\n```\n\n**Fallback: mcp-manager Subagent**\n\nSee [references\u002Fgemini-cli-integration.md](references\u002Fgemini-cli-integration.md) for complete examples.\n\n## Implementation Patterns\n\n### Pattern 1: Gemini CLI Auto-Execution (Primary)\n\nUse Gemini CLI for automatic tool discovery and execution. Gemini CLI auto-loads `GEMINI.md` from project root to enforce structured JSON responses.\n\n**Quick Example**:\n```bash\n# IMPORTANT: Use stdin piping, NOT -p flag (deprecated, skips MCP init)\n# Add \"Return JSON only per GEMINI.md instructions\" to enforce structured output\necho \"Take a screenshot of https:\u002F\u002Fexample.com. Return JSON only per GEMINI.md instructions.\" | gemini -y -m gemini-2.5-flash\n```\n\n**Expected Output**:\n```json\n{\"server\":\"puppeteer\",\"tool\":\"screenshot\",\"success\":true,\"result\":\"screenshot.png\",\"error\":null}\n```\n\n**Benefits**:\n- Automatic tool discovery\n- Structured JSON responses (parseable by Claude)\n- GEMINI.md auto-loaded for consistent formatting\n- Faster than subagent orchestration\n- No natural language ambiguity\n\nSee [references\u002Fgemini-cli-integration.md](references\u002Fgemini-cli-integration.md) for complete guide.\n\n### Pattern 2: Subagent-Based Execution (Fallback)\n\nUse `mcp-manager` agent when Gemini CLI unavailable. Subagent discovers tools, selects relevant ones, executes tasks, reports back.\n\n**Benefit**: Main context stays clean, only relevant tool definitions loaded when needed.\n\n### Pattern 3: LLM-Driven Tool Selection\n\nLLM reads `assets\u002Ftools.json`, intelligently selects relevant tools using context understanding, synonyms, and intent recognition.\n\n### Pattern 4: Multi-Server Orchestration\n\nCoordinate tools across multiple servers. Each tool knows its source server for proper routing.\n\n## Scripts Reference\n\n### scripts\u002Fmcp-client.ts\n\nCore MCP client manager class. Handles:\n- Config loading from `.claude\u002F.mcp.json`\n- Connecting to multiple MCP servers\n- Listing tools\u002Fprompts\u002Fresources across all servers\n- Executing tools with proper error handling\n- Connection lifecycle management\n\n### scripts\u002Fcli.ts\n\nCommand-line interface for MCP operations. Commands:\n- `list-tools` - Display all tools and save to `assets\u002Ftools.json`\n- `list-prompts` - Display all prompts\n- `list-resources` - Display all resources\n- `call-tool \u003Cserver> \u003Ctool> \u003Cjson>` - Execute a tool\n\n**Note**: `list-tools` persists complete tool catalog to `assets\u002Ftools.json` with full schemas for fast reference, offline browsing, and version control.\n\n## Quick Start\n\n**Method 1: Gemini CLI** (recommended)\n```bash\nnpm install -g gemini-cli\nmkdir -p .gemini && ln -sf .claude\u002F.mcp.json .gemini\u002Fsettings.json\n# IMPORTANT: Use stdin piping, NOT -p flag (deprecated, skips MCP init)\n# GEMINI.md auto-loads to enforce JSON responses\necho \"Take a screenshot of https:\u002F\u002Fexample.com. Return JSON only per GEMINI.md instructions.\" | gemini -y -m gemini-2.5-flash\n```\n\nReturns structured JSON: `{\"server\":\"puppeteer\",\"tool\":\"screenshot\",\"success\":true,\"result\":\"screenshot.png\",\"error\":null}`\n\n**Method 2: Scripts**\n```bash\ncd .claude\u002Fskills\u002Fmcp-management\u002Fscripts && npm install\nnpx tsx cli.ts list-tools  # Saves to assets\u002Ftools.json\nnpx tsx cli.ts call-tool memory create_entities '{\"entities\":[...]}'\n```\n\n**Method 3: mcp-manager Subagent**\n\nSee [references\u002Fgemini-cli-integration.md](references\u002Fgemini-cli-integration.md) for complete guide.\n\n## Technical Details\n\nSee [references\u002Fmcp-protocol.md](references\u002Fmcp-protocol.md) for:\n- JSON-RPC protocol details\n- Message types and formats\n- Error codes and handling\n- Transport mechanisms (stdio, HTTP+SSE)\n- Best practices\n\n## Integration Strategy\n\n### Execution Priority\n\n1. **Gemini CLI** (Primary): Fast, automatic, intelligent tool selection\n   - Check: `command -v gemini`\n   - Execute: `echo \"\u003Ctask>\" | gemini -y -m gemini-2.5-flash`\n   - **IMPORTANT**: Use stdin piping, NOT `-p` flag (deprecated, skips MCP init)\n   - Best for: All tasks when available\n\n2. **Direct CLI Scripts** (Secondary): Manual tool specification\n   - Use when: Need specific tool\u002Fserver control\n   - Execute: `npx tsx scripts\u002Fcli.ts call-tool \u003Cserver> \u003Ctool> \u003Cargs>`\n\n3. **mcp-manager Subagent** (Fallback): Context-efficient delegation\n   - Use when: Gemini unavailable or failed\n   - Keeps main context clean\n\n### Integration with Agents\n\nThe `mcp-manager` agent uses this skill to:\n- Check Gemini CLI availability first\n- Execute via `gemini` command if available\n- Fallback to direct script execution\n- Discover MCP capabilities without loading into main context\n- Report results back to main agent\n\nThis keeps main agent context clean and enables efficient MCP integration.","# MCP Management\n\nSkill for managing and interacting with Model Context Protocol (MCP) servers.\n\n## Overview\n\nMCP is an open protocol enabling AI agents to connect to external tools and data sources. This skill provides scripts and utilities to discover, analyze, and execute MCP capabilities from configured servers without polluting the main context window.\n\n**Key Benefits**:\n- Progressive disclosure of MCP capabilities (load only what's needed)\n- Intelligent tool\u002Fprompt\u002Fresource selection based on task requirements\n- Multi-server management from single config file\n- Context-efficient: subagents handle MCP discovery and execution\n- Persistent tool catalog: automatically saves discovered tools to JSON for fast reference\n\n## When to Use This Skill\n\nUse this skill when:\n1. **Discovering MCP Capabilities**: Need to list available tools\u002Fprompts\u002Fresources from configured servers\n2. **Task-Based Tool Selection**: Analyzing which MCP tools are relevant for a specific task\n3. **Executing MCP Tools**: Calling MCP tools programmatically with proper parameter handling\n4. **MCP Integration**: Building or debugging MCP client implementations\n5. **Context Management**: Avoiding context pollution by delegating MCP operations to subagents\n\n## Core Capabilities\n\n### 1. Configuration Management\n\nMCP servers configured in `.claude\u002F.mcp.json`.\n\n**Gemini CLI Integration** (recommended): Create symlink to `.gemini\u002Fsettings.json`:\n```bash\nmkdir -p .gemini && ln -sf .claude\u002F.mcp.json .gemini\u002Fsettings.json\n```\n\nSee [references\u002Fconfiguration.md](references\u002Fconfiguration.md) and [references\u002Fgemini-cli-integration.md](references\u002Fgemini-cli-integration.md).\n\n**GEMINI.md Response Format**: Project root contains `GEMINI.md` that Gemini CLI auto-loads, enforcing structured JSON responses:\n```json\n{\"server\":\"name\",\"tool\":\"name\",\"success\":true,\"result\":\u003Cdata>,\"error\":null}\n```\n\nThis ensures parseable, consistent output instead of unpredictable natural language. The file defines:\n- Mandatory JSON-only response format (no markdown, no explanations)\n- Maximum 500 character responses\n- Error handling structure\n- Available MCP servers reference\n\n**Benefits**: Programmatically parseable output, consistent error reporting, DRY configuration (format defined once), context-efficient (auto-loaded by Gemini CLI).\n\n### 2. Capability Discovery\n\n```bash\nnpx tsx scripts\u002Fcli.ts list-tools  # Saves to assets\u002Ftools.json\nnpx tsx scripts\u002Fcli.ts list-prompts\nnpx tsx scripts\u002Fcli.ts list-resources\n```\n\nAggregates capabilities from multiple servers with server identification.\n\n### 3. Intelligent Tool Analysis\n\nLLM analyzes `assets\u002Ftools.json` directly - better than keyword matching algorithms.\n\n### 4. Tool Execution\n\n**Primary: Gemini CLI** (if available)\n```bash\n# IMPORTANT: Use stdin piping, NOT -p flag (deprecated, skips MCP init)\necho \"Take a screenshot of https:\u002F\u002Fexample.com\" | gemini -y -m gemini-2.5-flash\n```\n\n**Secondary: Direct Scripts**\n```bash\nnpx tsx scripts\u002Fcli.ts call-tool memory create_entities '{\"entities\":[...]}'\n```\n\n**Fallback: mcp-manager Subagent**\n\nSee [references\u002Fgemini-cli-integration.md](references\u002Fgemini-cli-integration.md) for complete examples.\n\n## Implementation Patterns\n\n### Pattern 1: Gemini CLI Auto-Execution (Primary)\n\nUse Gemini CLI for automatic tool discovery and execution. Gemini CLI auto-loads `GEMINI.md` from project root to enforce structured JSON responses.\n\n**Quick Example**:\n```bash\n# IMPORTANT: Use stdin piping, NOT -p flag (deprecated, skips MCP init)\n# Add \"Return JSON only per GEMINI.md instructions\" to enforce structured output\necho \"Take a screenshot of https:\u002F\u002Fexample.com. Return JSON only per GEMINI.md instructions.\" | gemini -y -m gemini-2.5-flash\n```\n\n**Expected Output**:\n```json\n{\"server\":\"puppeteer\",\"tool\":\"screenshot\",\"success\":true,\"result\":\"screenshot.png\",\"error\":null}\n```\n\n**Benefits**:\n- Automatic tool discovery\n- Structured JSON responses (parseable by Claude)\n- GEMINI.md auto-loaded for consistent formatting\n- Faster than subagent orchestration\n- No natural language ambiguity\n\nSee [references\u002Fgemini-cli-integration.md](references\u002Fgemini-cli-integration.md) for complete guide.\n\n### Pattern 2: Subagent-Based Execution (Fallback)\n\nUse `mcp-manager` agent when Gemini CLI unavailable. Subagent discovers tools, selects relevant ones, executes tasks, reports back.\n\n**Benefit**: Main context stays clean, only relevant tool definitions loaded when needed.\n\n### Pattern 3: LLM-Driven Tool Selection\n\nLLM reads `assets\u002Ftools.json`, intelligently selects relevant tools using context understanding, synonyms, and intent recognition.\n\n### Pattern 4: Multi-Server Orchestration\n\nCoordinate tools across multiple servers. Each tool knows its source server for proper routing.\n\n## Scripts Reference\n\n### scripts\u002Fmcp-client.ts\n\nCore MCP client manager class. Handles:\n- Config loading from `.claude\u002F.mcp.json`\n- Connecting to multiple MCP servers\n- Listing tools\u002Fprompts\u002Fresources across all servers\n- Executing tools with proper error handling\n- Connection lifecycle management\n\n### scripts\u002Fcli.ts\n\nCommand-line interface for MCP operations. Commands:\n- `list-tools` - Display all tools and save to `assets\u002Ftools.json`\n- `list-prompts` - Display all prompts\n- `list-resources` - Display all resources\n- `call-tool \u003Cserver> \u003Ctool> \u003Cjson>` - Execute a tool\n\n**Note**: `list-tools` persists complete tool catalog to `assets\u002Ftools.json` with full schemas for fast reference, offline browsing, and version control.\n\n## Quick Start\n\n**Method 1: Gemini CLI** (recommended)\n```bash\nnpm install -g gemini-cli\nmkdir -p .gemini && ln -sf .claude\u002F.mcp.json .gemini\u002Fsettings.json\n# IMPORTANT: Use stdin piping, NOT -p flag (deprecated, skips MCP init)\n# GEMINI.md auto-loads to enforce JSON responses\necho \"Take a screenshot of https:\u002F\u002Fexample.com. Return JSON only per GEMINI.md instructions.\" | gemini -y -m gemini-2.5-flash\n```\n\nReturns structured JSON: `{\"server\":\"puppeteer\",\"tool\":\"screenshot\",\"success\":true,\"result\":\"screenshot.png\",\"error\":null}`\n\n**Method 2: Scripts**\n```bash\ncd .claude\u002Fskills\u002Fmcp-management\u002Fscripts && npm install\nnpx tsx cli.ts list-tools  # Saves to assets\u002Ftools.json\nnpx tsx cli.ts call-tool memory create_entities '{\"entities\":[...]}'\n```\n\n**Method 3: mcp-manager Subagent**\n\nSee [references\u002Fgemini-cli-integration.md](references\u002Fgemini-cli-integration.md) for complete guide.\n\n## Technical Details\n\nSee [references\u002Fmcp-protocol.md](references\u002Fmcp-protocol.md) for:\n- JSON-RPC protocol details\n- Message types and formats\n- Error codes and handling\n- Transport mechanisms (stdio, HTTP+SSE)\n- Best practices\n\n## Integration Strategy\n\n### Execution Priority\n\n1. **Gemini CLI** (Primary): Fast, automatic, intelligent tool selection\n   - Check: `command -v gemini`\n   - Execute: `echo \"\u003Ctask>\" | gemini -y -m gemini-2.5-flash`\n   - **IMPORTANT**: Use stdin piping, NOT `-p` flag (deprecated, skips MCP init)\n   - Best for: All tasks when available\n\n2. **Direct CLI Scripts** (Secondary): Manual tool specification\n   - Use when: Need specific tool\u002Fserver control\n   - Execute: `npx tsx scripts\u002Fcli.ts call-tool \u003Cserver> \u003Ctool> \u003Cargs>`\n\n3. **mcp-manager Subagent** (Fallback): Context-efficient delegation\n   - Use when: Gemini unavailable or failed\n   - Keeps main context clean\n\n### Integration with Agents\n\nThe `mcp-manager` agent uses this skill to:\n- Check Gemini CLI availability first\n- Execute via `gemini` command if available\n- Fallback to direct script execution\n- Discover MCP capabilities without loading into main context\n- Report results back to main agent\n\nThis keeps main agent context clean and enables efficient MCP integration.",{"name":5,"description":7},"main","b0fa28db5a831028e418b3335a5654dd75fcb95b","source\u002F.agent\u002Fskills\u002Fmcp-management","https:\u002F\u002Fgithub.com\u002Fldanh270\u002Fcreate-skills-kit","https:\u002F\u002Fgithub.com\u002Fldanh270","https:\u002F\u002Fldanh270.vercel.app\u002F","Software engineer with an algorithmic foundation, focused on building scalable, performant, and impactful web applications.","2026-03-26 11:23:48",{"source":8,"skillName":5,"commands":58,"prompt":68,"zipAvailable":69},[59,62,65],{"tool":60,"command":61},"npx","npx skills add ldanh270\u002Fcreate-skills-kit --skill mcp-management",{"tool":63,"command":64},"bunx","bunx skills add ldanh270\u002Fcreate-skills-kit --skill mcp-management",{"tool":66,"command":67},"pnpm","pnpm dlx skills add ldanh270\u002Fcreate-skills-kit --skill mcp-management","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fldanh270\u002Fcreate-skills-kit\u002Fblob\u002Fmain\u002Fsource\u002F.agent\u002Fskills\u002Fmcp-management\u002FSKILL.md",true,[71,77,83,87,91,95,101,105,109,113,117],{"path":72,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":75,"sourceHtmlUrl":76},"assets\u002Ftools.json","ASSET","资产文件",91862,"https:\u002F\u002Fgithub.com\u002Fldanh270\u002Fcreate-skills-kit\u002Fblob\u002Fmain\u002Fsource\u002F.agent\u002Fskills\u002Fmcp-management\u002Fassets\u002Ftools.json",{"path":78,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":81,"sourceHtmlUrl":82},"README.md","REFERENCE","参考文档",5747,"https:\u002F\u002Fgithub.com\u002Fldanh270\u002Fcreate-skills-kit\u002Fblob\u002Fmain\u002Fsource\u002F.agent\u002Fskills\u002Fmcp-management\u002FREADME.md",{"path":84,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":85,"sourceHtmlUrl":86},"references\u002Fconfiguration.md",1742,"https:\u002F\u002Fgithub.com\u002Fldanh270\u002Fcreate-skills-kit\u002Fblob\u002Fmain\u002Fsource\u002F.agent\u002Fskills\u002Fmcp-management\u002Freferences\u002Fconfiguration.md",{"path":88,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":89,"sourceHtmlUrl":90},"references\u002Fgemini-cli-integration.md",4945,"https:\u002F\u002Fgithub.com\u002Fldanh270\u002Fcreate-skills-kit\u002Fblob\u002Fmain\u002Fsource\u002F.agent\u002Fskills\u002Fmcp-management\u002Freferences\u002Fgemini-cli-integration.md",{"path":92,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":93,"sourceHtmlUrl":94},"references\u002Fmcp-protocol.md",2207,"https:\u002F\u002Fgithub.com\u002Fldanh270\u002Fcreate-skills-kit\u002Fblob\u002Fmain\u002Fsource\u002F.agent\u002Fskills\u002Fmcp-management\u002Freferences\u002Fmcp-protocol.md",{"path":96,"resourceType":97,"resourceTypeDesc":98,"sizeBytes":99,"sourceHtmlUrl":100},"scripts\u002F.env.example","SCRIPT","脚本",281,"https:\u002F\u002Fgithub.com\u002Fldanh270\u002Fcreate-skills-kit\u002Fblob\u002Fmain\u002Fsource\u002F.agent\u002Fskills\u002Fmcp-management\u002Fscripts\u002F.env.example",{"path":102,"resourceType":97,"resourceTypeDesc":98,"sizeBytes":103,"sourceHtmlUrl":104},"scripts\u002F.gitignore",801,"https:\u002F\u002Fgithub.com\u002Fldanh270\u002Fcreate-skills-kit\u002Fblob\u002Fmain\u002Fsource\u002F.agent\u002Fskills\u002Fmcp-management\u002Fscripts\u002F.gitignore",{"path":106,"resourceType":97,"resourceTypeDesc":98,"sizeBytes":107,"sourceHtmlUrl":108},"scripts\u002Fcli.ts",5393,"https:\u002F\u002Fgithub.com\u002Fldanh270\u002Fcreate-skills-kit\u002Fblob\u002Fmain\u002Fsource\u002F.agent\u002Fskills\u002Fmcp-management\u002Fscripts\u002Fcli.ts",{"path":110,"resourceType":97,"resourceTypeDesc":98,"sizeBytes":111,"sourceHtmlUrl":112},"scripts\u002Fmcp-client.ts",6888,"https:\u002F\u002Fgithub.com\u002Fldanh270\u002Fcreate-skills-kit\u002Fblob\u002Fmain\u002Fsource\u002F.agent\u002Fskills\u002Fmcp-management\u002Fscripts\u002Fmcp-client.ts",{"path":114,"resourceType":97,"resourceTypeDesc":98,"sizeBytes":115,"sourceHtmlUrl":116},"scripts\u002Fpackage.json",459,"https:\u002F\u002Fgithub.com\u002Fldanh270\u002Fcreate-skills-kit\u002Fblob\u002Fmain\u002Fsource\u002F.agent\u002Fskills\u002Fmcp-management\u002Fscripts\u002Fpackage.json",{"path":118,"resourceType":97,"resourceTypeDesc":98,"sizeBytes":119,"sourceHtmlUrl":120},"scripts\u002Ftsconfig.json",329,"https:\u002F\u002Fgithub.com\u002Fldanh270\u002Fcreate-skills-kit\u002Fblob\u002Fmain\u002Fsource\u002F.agent\u002Fskills\u002Fmcp-management\u002Fscripts\u002Ftsconfig.json",[122,148,181,207,220,237],{"skillNo":123,"name":124,"nameZh":6,"description":125,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":126,"categories":127,"keywords":128,"publishedAt":44},"01M6J6RSG4FR9B5FG3R8BGM9YH","web-frameworks","Build modern full-stack web applications with Next.js (App Router, Server Components, RSC, PPR, SSR, SSG, ISR), Turborepo (monorepo management, task pipelines, remote caching, parallel execution), and RemixIcon (3100+ SVG icons in outlined\u002Ffilled styles). Use when creating React applications, implementing server-side rendering, setting up monorepos with multiple packages, optimizing build performance and caching strategies, adding icon libraries, managing shared dependencies, or working with TypeScript full-stack projects.","https:\u002F\u002Fgithub.com\u002Fldanh270\u002Fcreate-skills-kit\u002Fblob\u002Fmain\u002Fsource\u002F.agent\u002Fskills\u002Fweb-frameworks\u002FSKILL.md",[],[129,130,131,132,133,134,135,136,40,137,138,139,140,141,142,143,144,145,146,147],"web","web frameworks","frameworks","performance","components","react","libraries","packages","projects","monorepo","router","up","caching","strategies","shared","app","remote","Server Components","implementing",{"skillNo":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":162,"publishedAt":44},"01M6J6RDB5RPFA1C39JC4XHSS7","ui-styling","Create beautiful, accessible user interfaces with shadcn\u002Fui components (built on Radix UI + Tailwind), Tailwind CSS utility-first styling, and canvas-based visual designs. Use when building user interfaces, implementing design systems, creating responsive layouts, adding accessible components (dialogs, dropdowns, forms, tables), customizing themes and colors, implementing dark mode, generating visual designs and posters, or establishing consistent styling patterns across applications.","https:\u002F\u002Fgithub.com\u002Fldanh270\u002Fcreate-skills-kit\u002Fblob\u002Fmain\u002Fsource\u002F.agent\u002Fskills\u002Fui-styling\u002FSKILL.md",[154,157],{"categoryNo":155,"categoryName":156,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":158,"categoryName":159,"taxonomyType":160,"taxonomyTypeDesc":161},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[163,164,165,166,167,168,133,169,170,171,172,173,174,175,176,177,178,179,180,147],"ui styling","ui","styling","design","css","canvas","create","design systems","shadcn","Tailwind","patterns","forms","across","responsive","themes","utility","tables","mode",{"skillNo":182,"name":183,"nameZh":6,"description":184,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":185,"categories":186,"keywords":187,"publishedAt":44},"01M6J6R697SCC1P1AFRZ0KZJ72","threejs","Build immersive 3D web experiences with Three.js - WebGL\u002FWebGPU library for scenes, cameras, geometries, materials, lights, animations, loaders, post-processing, shaders (including node-based TSL), compute, physics, VR\u002FXR, and advanced rendering. Use when creating 3D visualizations, games, interactive graphics, data viz, product configurators, architectural walkthroughs, or WebGL\u002FWebGPU applications. Covers OrbitControls, GLTF\u002FFBX loading, PBR materials, shadow mapping, post-processing effects (bloom, SSAO, SSR), custom shaders, instancing, LOD, animation systems, and WebXR.","https:\u002F\u002Fgithub.com\u002Fldanh270\u002Fcreate-skills-kit\u002Fblob\u002Fmain\u002Fsource\u002F.agent\u002Fskills\u002Fthreejs\u002FSKILL.md",[],[183,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,204,205,206],"webgpu","ssr","shaders","product","library","data","Animation","3D","node","data viz","physics","animation systems","mapping","processing","rendering","loading","advanced","post-processing","bloom",{"skillNo":208,"name":209,"nameZh":6,"description":210,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":211,"categories":212,"keywords":214,"publishedAt":44},"01M6J6R2Z8VBZ6NV4341JZZNQC","template-skill","Replace with description of the skill and when Claude should use it.","https:\u002F\u002Fgithub.com\u002Fldanh270\u002Fcreate-skills-kit\u002Fblob\u002Fmain\u002Fsource\u002F.agent\u002Fskills\u002Ftemplate-skill\u002FSKILL.md",[213],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[215,216,217,218,219],"template skill","template","use","it","with",{"skillNo":221,"name":222,"nameZh":6,"description":223,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":224,"categories":225,"keywords":226,"publishedAt":44},"01M6J6QSDZX70HMYCYEW7A2AHF","shopify","Build Shopify applications, extensions, and themes using GraphQL\u002FREST APIs, Shopify CLI, Polaris UI components, and Liquid templating. Capabilities include app development with OAuth authentication, checkout UI extensions for customizing checkout flow, admin UI extensions for dashboard integration, POS extensions for retail, theme development with Liquid, webhook management, billing API integration, product\u002Forder\u002Fcustomer management. Use when building Shopify apps, implementing checkout customizations, creating admin interfaces, developing themes, integrating payment processing, managing store data via APIs, or extending Shopify functionality.","https:\u002F\u002Fgithub.com\u002Fldanh270\u002Fcreate-skills-kit\u002Fblob\u002Fmain\u002Fsource\u002F.agent\u002Fskills\u002Fshopify\u002FSKILL.md",[],[222,227,228,229,133,230,41,191,164,231,193,232,233,144,234,235,177,201,236,147],"cli","dashboard","customer","authentication","flow","api","webhook","apps","checkout","billing",{"skillNo":238,"name":239,"nameZh":6,"description":240,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":241,"categories":242,"keywords":243,"publishedAt":44},"01M6J6QKMCVT5VJE498JZ3WQKZ","sequential-thinking","Apply structured, reflective problem-solving for complex tasks requiring multi-step analysis, revision capability, and hypothesis verification. Use for complex problem decomposition, adaptive planning, analysis needing course correction, problems with unclear scope, multi-step solutions, and hypothesis-driven work.","https:\u002F\u002Fgithub.com\u002Fldanh270\u002Fcreate-skills-kit\u002Fblob\u002Fmain\u002Fsource\u002F.agent\u002Fskills\u002Fsequential-thinking\u002FSKILL.md",[],[244,245,42,246,247,248,249,250,217,251,252,253,254,255,256,257,219,258,259,28],"sequential thinking","thinking","planning","verification","hypothesis","analysis","work","problem-solving","structured","decomposition","driven","scope","problem","multi","course","revision"]