[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6C32MACSHCJK49X53CTZJ04":3,"skill-same:01M6C32MACSHCJK49X53CTZJ04":91},{"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":26,"publishedAt":47,"linkOnly":48,"markdownContent":49,"markdownBody":50,"frontMatter":51,"refName":52,"commitSha":53,"skillDirectory":54,"forksCount":55,"repositoryHtmlUrl":56,"repositoryHomepageUrl":6,"ownerHtmlUrl":57,"ownerBlogUrl":58,"ownerDescription":59,"updatedAt":60,"install":61,"resources":74},"01M6C32MACSHCJK49X53CTZJ04","mcp-server",null,"Build production MCP (Model Context Protocol) servers that let AI clients call your tools and read your data. Covers tool registration with Zod validation, resource handlers, prompt templates, stdio and HTTP transports, session management, error handling, testing, and deployment. Use when building MCP servers or tools for AI integration.","RaheesAhmed\u002FSajiCode","RaheesAhmed","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F48914925?v=4","01M6C31VY6EJ4N8QS30J585H9H","Rahees Ahmed","01M6C31W21ET706B6XTWHS52VC",68,"MIT","https:\u002F\u002Fgithub.com\u002FRaheesAhmed\u002FSajiCode\u002Fblob\u002Fmain\u002Fskills\u002Fmcp-server\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46],"MCP","mcp server","server","use","testing","session","read","prompt","zod","model","tool","templates","integration","protocol","validation","error handling","deployment","prompt templates","http","model context protocol","2026-11-10 10:12:30",false,"---\nname: mcp-server\ndescription: Build production MCP (Model Context Protocol) servers that let AI clients call your tools and read your data. Covers tool registration with Zod validation, resource handlers, prompt templates, stdio and HTTP transports, session management, error handling, testing, and deployment. Use when building MCP servers or tools for AI integration.\n---\n\n# MCP Server Mastery\n\n## Project Setup\n\n```bash\nmkdir my-mcp-server && cd my-mcp-server\nnpm init -y\nnpm install @modelcontextprotocol\u002Fserver zod\nnpm install -D typescript @types\u002Fnode\n```\n\n### package.json\n```json\n{\n  \"type\": \"module\",\n  \"bin\": { \"my-mcp-server\": \"dist\u002Findex.js\" },\n  \"scripts\": { \"build\": \"tsc\", \"start\": \"node dist\u002Findex.js\" }\n}\n```\n\n### tsconfig.json\n```json\n{\n  \"compilerOptions\": {\n    \"target\": \"ES2022\", \"module\": \"NodeNext\", \"moduleResolution\": \"NodeNext\",\n    \"outDir\": \"dist\", \"strict\": true, \"esModuleInterop\": true, \"skipLibCheck\": true\n  },\n  \"include\": [\"src\"]\n}\n```\n\n## Server Architecture\n\n```\nsrc\u002F\n├── index.ts           # Entry point, server + transport setup\n├── tools\u002F             # Tool handler files\n│   ├── search.ts\n│   └── compute.ts\n├── resources\u002F         # Resource handlers\n│   └── config.ts\n└── utils\u002F             # Shared utilities\n    └── errors.ts\n```\n\n## Tool Patterns\n\n### Tool with Structured Output\n```ts\nimport { McpServer } from \"@modelcontextprotocol\u002Fserver\u002Fmcp.js\";\nimport { z } from \"zod\";\n\nconst server = new McpServer({ name: \"my-server\", version: \"1.0.0\" });\n\nserver.registerTool(\"calculate-bmi\", {\n  title: \"BMI Calculator\",\n  description: \"Calculate Body Mass Index from weight and height\",\n  inputSchema: z.object({\n    weightKg: z.number().positive(),\n    heightM: z.number().positive(),\n  }),\n  outputSchema: z.object({ bmi: z.number(), category: z.string() }),\n}, async ({ weightKg, heightM }) => {\n  const bmi = weightKg \u002F (heightM * heightM);\n  const category = bmi \u003C 18.5 ? \"underweight\" : bmi \u003C 25 ? \"normal\" : bmi \u003C 30 ? \"overweight\" : \"obese\";\n  return {\n    content: [{ type: \"text\", text: `BMI: ${bmi.toFixed(1)} (${category})` }],\n    structuredContent: { bmi: Number(bmi.toFixed(1)), category },\n  };\n});\n```\n\n### Tool with Error Handling\n```ts\nserver.registerTool(\"fetch-url\", {\n  title: \"Fetch URL\",\n  description: \"Fetch content from a URL and return as text\",\n  inputSchema: z.object({\n    url: z.string().url(),\n    timeout: z.number().optional().default(10000),\n  }),\n}, async ({ url, timeout }) => {\n  try {\n    const controller = new AbortController();\n    const timer = setTimeout(() => controller.abort(), timeout);\n    const response = await fetch(url, { signal: controller.signal });\n    clearTimeout(timer);\n\n    if (!response.ok) {\n      return { content: [{ type: \"text\", text: `HTTP ${response.status}: ${response.statusText}` }], isError: true };\n    }\n\n    const text = await response.text();\n    return { content: [{ type: \"text\", text: text.slice(0, 50000) }] };\n  } catch (error) {\n    const message = error instanceof Error ? error.message : \"Unknown error\";\n    return { content: [{ type: \"text\", text: `Fetch failed: ${message}` }], isError: true };\n  }\n});\n```\n\n### Tool with Annotations\n```ts\nserver.registerTool(\"read-file\", {\n  title: \"Read File\",\n  description: \"Read a file from disk\",\n  inputSchema: z.object({ path: z.string() }),\n  annotations: { readOnlyHint: true, openWorldHint: false },\n}, async ({ path }) => {\n  const content = await fs.readFile(path, \"utf-8\");\n  return { content: [{ type: \"text\", text: content }] };\n});\n```\n\n## Resource Patterns\n\n### Static Resource\n```ts\nserver.registerResource(\"config\", \"config:\u002F\u002Fapp\", {\n  title: \"App Configuration\",\n  description: \"Current application configuration\",\n  mimeType: \"application\u002Fjson\",\n}, async (uri) => ({\n  contents: [{ uri: uri.href, text: JSON.stringify(getConfig(), null, 2) }],\n}));\n```\n\n### Dynamic Resource with Template\n```ts\nimport { ResourceTemplate } from \"@modelcontextprotocol\u002Fserver\u002Fmcp.js\";\n\nserver.registerResource(\"user-profile\",\n  new ResourceTemplate(\"user:\u002F\u002F{userId}\u002Fprofile\", {\n    list: async () => ({\n      resources: users.map((u) => ({ uri: `user:\u002F\u002F${u.id}\u002Fprofile`, name: u.name })),\n    }),\n  }),\n  { title: \"User Profile\", mimeType: \"application\u002Fjson\" },\n  async (uri, { userId }) => ({\n    contents: [{ uri: uri.href, text: JSON.stringify(await getUser(userId)) }],\n  })\n);\n```\n\n## Transport Setup\n\n### Stdio (local CLI tools)\n```ts\nimport { StdioServerTransport } from \"@modelcontextprotocol\u002Fserver\u002Fstdio.js\";\nconst transport = new StdioServerTransport();\nawait server.connect(transport);\n```\n\n### HTTP (remote services)\n```ts\nimport express from \"express\";\nimport { NodeStreamableHTTPServerTransport } from \"@modelcontextprotocol\u002Fserver\u002FstreamableHttp.js\";\n\nconst app = express();\napp.use(express.json());\n\napp.post(\"\u002Fmcp\", async (req, res) => {\n  const transport = new NodeStreamableHTTPServerTransport({ sessionIdGenerator: undefined });\n  await server.connect(transport);\n  await transport.handleRequest(req, res, req.body);\n});\n\napp.listen(3000, \"127.0.0.1\");\n```\n\n## Client Configuration\n\n### Claude Desktop \u002F Cursor \u002F VS Code\n```json\n{\n  \"mcpServers\": {\n    \"my-server\": {\n      \"command\": \"node\",\n      \"args\": [\"path\u002Fto\u002Fdist\u002Findex.js\"],\n      \"env\": { \"API_KEY\": \"...\" }\n    }\n  }\n}\n```\n\n## Best Practices\n- Use Zod schemas for ALL input\u002Foutput validation\n- Keep tools focused — one action per tool\n- Return `isError: true` on failures — never throw unhandled\n- Log to stderr (`console.error`) — stdout is used by stdio transport\n- Add `#!\u002Fusr\u002Fbin\u002Fenv node` shebang for CLI distribution\n- Resources are read-only — no mutations\n- Use `outputSchema` when tools return structured data\n- Set timeouts on all external calls\n","# MCP Server Mastery\n\n## Project Setup\n\n```bash\nmkdir my-mcp-server && cd my-mcp-server\nnpm init -y\nnpm install @modelcontextprotocol\u002Fserver zod\nnpm install -D typescript @types\u002Fnode\n```\n\n### package.json\n```json\n{\n  \"type\": \"module\",\n  \"bin\": { \"my-mcp-server\": \"dist\u002Findex.js\" },\n  \"scripts\": { \"build\": \"tsc\", \"start\": \"node dist\u002Findex.js\" }\n}\n```\n\n### tsconfig.json\n```json\n{\n  \"compilerOptions\": {\n    \"target\": \"ES2022\", \"module\": \"NodeNext\", \"moduleResolution\": \"NodeNext\",\n    \"outDir\": \"dist\", \"strict\": true, \"esModuleInterop\": true, \"skipLibCheck\": true\n  },\n  \"include\": [\"src\"]\n}\n```\n\n## Server Architecture\n\n```\nsrc\u002F\n├── index.ts           # Entry point, server + transport setup\n├── tools\u002F             # Tool handler files\n│   ├── search.ts\n│   └── compute.ts\n├── resources\u002F         # Resource handlers\n│   └── config.ts\n└── utils\u002F             # Shared utilities\n    └── errors.ts\n```\n\n## Tool Patterns\n\n### Tool with Structured Output\n```ts\nimport { McpServer } from \"@modelcontextprotocol\u002Fserver\u002Fmcp.js\";\nimport { z } from \"zod\";\n\nconst server = new McpServer({ name: \"my-server\", version: \"1.0.0\" });\n\nserver.registerTool(\"calculate-bmi\", {\n  title: \"BMI Calculator\",\n  description: \"Calculate Body Mass Index from weight and height\",\n  inputSchema: z.object({\n    weightKg: z.number().positive(),\n    heightM: z.number().positive(),\n  }),\n  outputSchema: z.object({ bmi: z.number(), category: z.string() }),\n}, async ({ weightKg, heightM }) => {\n  const bmi = weightKg \u002F (heightM * heightM);\n  const category = bmi \u003C 18.5 ? \"underweight\" : bmi \u003C 25 ? \"normal\" : bmi \u003C 30 ? \"overweight\" : \"obese\";\n  return {\n    content: [{ type: \"text\", text: `BMI: ${bmi.toFixed(1)} (${category})` }],\n    structuredContent: { bmi: Number(bmi.toFixed(1)), category },\n  };\n});\n```\n\n### Tool with Error Handling\n```ts\nserver.registerTool(\"fetch-url\", {\n  title: \"Fetch URL\",\n  description: \"Fetch content from a URL and return as text\",\n  inputSchema: z.object({\n    url: z.string().url(),\n    timeout: z.number().optional().default(10000),\n  }),\n}, async ({ url, timeout }) => {\n  try {\n    const controller = new AbortController();\n    const timer = setTimeout(() => controller.abort(), timeout);\n    const response = await fetch(url, { signal: controller.signal });\n    clearTimeout(timer);\n\n    if (!response.ok) {\n      return { content: [{ type: \"text\", text: `HTTP ${response.status}: ${response.statusText}` }], isError: true };\n    }\n\n    const text = await response.text();\n    return { content: [{ type: \"text\", text: text.slice(0, 50000) }] };\n  } catch (error) {\n    const message = error instanceof Error ? error.message : \"Unknown error\";\n    return { content: [{ type: \"text\", text: `Fetch failed: ${message}` }], isError: true };\n  }\n});\n```\n\n### Tool with Annotations\n```ts\nserver.registerTool(\"read-file\", {\n  title: \"Read File\",\n  description: \"Read a file from disk\",\n  inputSchema: z.object({ path: z.string() }),\n  annotations: { readOnlyHint: true, openWorldHint: false },\n}, async ({ path }) => {\n  const content = await fs.readFile(path, \"utf-8\");\n  return { content: [{ type: \"text\", text: content }] };\n});\n```\n\n## Resource Patterns\n\n### Static Resource\n```ts\nserver.registerResource(\"config\", \"config:\u002F\u002Fapp\", {\n  title: \"App Configuration\",\n  description: \"Current application configuration\",\n  mimeType: \"application\u002Fjson\",\n}, async (uri) => ({\n  contents: [{ uri: uri.href, text: JSON.stringify(getConfig(), null, 2) }],\n}));\n```\n\n### Dynamic Resource with Template\n```ts\nimport { ResourceTemplate } from \"@modelcontextprotocol\u002Fserver\u002Fmcp.js\";\n\nserver.registerResource(\"user-profile\",\n  new ResourceTemplate(\"user:\u002F\u002F{userId}\u002Fprofile\", {\n    list: async () => ({\n      resources: users.map((u) => ({ uri: `user:\u002F\u002F${u.id}\u002Fprofile`, name: u.name })),\n    }),\n  }),\n  { title: \"User Profile\", mimeType: \"application\u002Fjson\" },\n  async (uri, { userId }) => ({\n    contents: [{ uri: uri.href, text: JSON.stringify(await getUser(userId)) }],\n  })\n);\n```\n\n## Transport Setup\n\n### Stdio (local CLI tools)\n```ts\nimport { StdioServerTransport } from \"@modelcontextprotocol\u002Fserver\u002Fstdio.js\";\nconst transport = new StdioServerTransport();\nawait server.connect(transport);\n```\n\n### HTTP (remote services)\n```ts\nimport express from \"express\";\nimport { NodeStreamableHTTPServerTransport } from \"@modelcontextprotocol\u002Fserver\u002FstreamableHttp.js\";\n\nconst app = express();\napp.use(express.json());\n\napp.post(\"\u002Fmcp\", async (req, res) => {\n  const transport = new NodeStreamableHTTPServerTransport({ sessionIdGenerator: undefined });\n  await server.connect(transport);\n  await transport.handleRequest(req, res, req.body);\n});\n\napp.listen(3000, \"127.0.0.1\");\n```\n\n## Client Configuration\n\n### Claude Desktop \u002F Cursor \u002F VS Code\n```json\n{\n  \"mcpServers\": {\n    \"my-server\": {\n      \"command\": \"node\",\n      \"args\": [\"path\u002Fto\u002Fdist\u002Findex.js\"],\n      \"env\": { \"API_KEY\": \"...\" }\n    }\n  }\n}\n```\n\n## Best Practices\n- Use Zod schemas for ALL input\u002Foutput validation\n- Keep tools focused — one action per tool\n- Return `isError: true` on failures — never throw unhandled\n- Log to stderr (`console.error`) — stdout is used by stdio transport\n- Add `#!\u002Fusr\u002Fbin\u002Fenv node` shebang for CLI distribution\n- Resources are read-only — no mutations\n- Use `outputSchema` when tools return structured data\n- Set timeouts on all external calls\n",{"name":5,"description":7},"main","791249e54ef4db28bf9af93993479d2e0c6a8a9d","skills\u002Fmcp-server",15,"https:\u002F\u002Fgithub.com\u002FRaheesAhmed\u002FSajiCode","https:\u002F\u002Fgithub.com\u002FRaheesAhmed","https:\u002F\u002Fraheesahmed.vercel.app\u002F","Forward Deployed AI Engineer | AI Agents, MCP Servers & Business Automation","2026-09-14 17:21:11",{"source":8,"skillName":5,"commands":62,"prompt":72,"zipAvailable":73},[63,66,69],{"tool":64,"command":65},"npx","npx skills add RaheesAhmed\u002FSajiCode --skill mcp-server",{"tool":67,"command":68},"bunx","bunx skills add RaheesAhmed\u002FSajiCode --skill mcp-server",{"tool":70,"command":71},"pnpm","pnpm dlx skills add RaheesAhmed\u002FSajiCode --skill mcp-server","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FRaheesAhmed\u002FSajiCode\u002Fblob\u002Fmain\u002Fskills\u002Fmcp-server\u002FSKILL.md",true,[75,81,87],{"path":76,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":79,"sourceHtmlUrl":80},"references\u002Ffontes.md","REFERENCE","参考文档",701,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-leiloeiro-ia\u002Freferences\u002Ffontes.md",{"path":82,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":85,"sourceHtmlUrl":86},"scripts\u002Fgovernance.py","SCRIPT","脚本",3838,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-leiloeiro-ia\u002Fscripts\u002Fgovernance.py",{"path":88,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":89,"sourceHtmlUrl":90},"scripts\u002Frequirements.txt",42,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-leiloeiro-ia\u002Fscripts\u002Frequirements.txt",[92,103,115,138,162,184],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":99,"publishedAt":47},"01M6C33MP48R5GWR13P2VFHWB0","demo-skill","Demo plugin skill for tests.","https:\u002F\u002Fgithub.com\u002FRaheesAhmed\u002FSajiCode\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fdemo-plugin\u002Fskills\u002Fdemo-skill\u002FSKILL.md",[98],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[100,101,102],"demo skill","demo","plugin",{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":110,"publishedAt":47},"01M6C33JV7RMPM5AVS7SCCGDR8","write-a-skill","Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.","https:\u002F\u002Fgithub.com\u002FRaheesAhmed\u002FSajiCode\u002Fblob\u002Fmain\u002Fskills\u002Fwrite-a-skill\u002FSKILL.MD",[109],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[111,112,113,114,30],"write","write a skill","create","user",{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":124,"publishedAt":47},"01M6C33G0SX1683HER40XB8047","web-research","Deep web research and data extraction skill. Systematically research ANY topic by fetching URLs, reading documentation, crawling API docs, evaluating npm\u002Fpypi packages, comparing technologies, and synthesizing findings into actionable recommendations. Use when researching libraries, frameworks, APIs, solutions, or any topic requiring web investigation.","https:\u002F\u002Fgithub.com\u002FRaheesAhmed\u002FSajiCode\u002Fblob\u002Fmain\u002Fskills\u002Fweb-research\u002FSKILL.md",[121],{"categoryNo":122,"categoryName":123,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究",[125,126,127,128,129,130,131,132,133,134,135,136,137,30],"research","web","web research","docs","documentation","libraries","packages","npm","extraction","pypi","data","investigation","api",{"skillNo":139,"name":31,"nameZh":6,"description":140,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":141,"categories":142,"keywords":146,"publishedAt":47},"01M6C33CRE3D30CHTTV1ZVR1ZM","Design and implement comprehensive test suites. Covers unit testing, integration testing, E2E testing with Playwright, API testing, mocking strategies, test data factories, TDD workflow, snapshot testing, coverage targets, and CI integration. Use when writing tests, designing test architecture, or debugging test failures.","https:\u002F\u002Fgithub.com\u002FRaheesAhmed\u002FSajiCode\u002Fblob\u002Fmain\u002Fskills\u002Ftesting\u002FSKILL.md",[143],{"categoryNo":144,"categoryName":145,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[31,147,30,148,149,150,137,151,135,152,39,153,154,155,156,157,158,159,160,161],"ci","playwright","snapshot","coverage","e2e","tdd","test","architecture","writing tests","debugging","workflow","implement","writing","design","e2e testing",{"skillNo":163,"name":164,"nameZh":6,"description":165,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":166,"categories":167,"keywords":168,"publishedAt":47},"01M6C33AER10BH236SAP89GJP6","superpowers","Core engineering workflow that activates on EVERY task. Enforces systematic plan-before-code methodology, multi-file refactoring safety, dependency-aware changes, pre-flight verification, and zero-placeholder quality standards. Use PROACTIVELY on all coding tasks.","https:\u002F\u002Fgithub.com\u002FRaheesAhmed\u002FSajiCode\u002Fblob\u002Fmain\u002Fskills\u002Fsuperpowers\u002FSKILL.md",[],[164,169,170,171,157,172,173,174,30,175,176,177,178,179,180,181,182,183],"core","tasks","placeholder","code","coding","dependency","quality","refactoring","plan","Safety","methodology","ZeRO","engineering","file","verification",{"skillNo":185,"name":186,"nameZh":6,"description":187,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":188,"categories":189,"keywords":193,"publishedAt":47},"01M6C3380VVQHM6CCC843MH5S3","styling","Implement production styling systems with Tailwind CSS, vanilla CSS, or CSS-in-JS. Covers CSS architecture (BEM, utility-first, modules), design tokens, responsive patterns, animation systems, dark mode, container queries, print styles, and performance optimization. Use when implementing designs or building CSS architectures.","https:\u002F\u002Fgithub.com\u002FRaheesAhmed\u002FSajiCode\u002Fblob\u002Fmain\u002Fskills\u002Fstyling\u002FSKILL.md",[190],{"categoryNo":191,"categoryName":192,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",[186,194,195,30,196,197,198,199,200,201,154,158,202,203,160],"Tailwind","container","performance optimization","js","Animation","first","Production","Optimization","performance","css"]