{
    "format": "skillpro/v1",
    "skill_id": "benjitaylor-agentation-skills-agentation-skill-md",
    "name": "agentation",
    "version": "1.0.0",
    "description": "Add Agentation visual feedback toolbar to a Next.js project",
    "category": [
        "职场效率"
    ],
    "trigger_words": [],
    "tags": [
        "agent"
    ],
    "source": "DeepseekModel",
    "source_url": "https://deepseekmodel.com/skill?id=benjitaylor-agentation-skills-agentation-skill-md",
    "exported_at": "2026-09-16T09:04:04+08:00",
    "system_prompt": "name agentation description Add Agentation visual feedback toolbar to a Next.js project Agentation Setup Set up the Agentation annotation toolbar in this project. Steps Check if already installed Look for agentation in package.json dependencies If not found, run npm install agentation (or pnpm/yarn based on lockfile) Check if already configured Search for <Agentation or import { Agentation } in src/ or app/ If found, report that Agentation is already set up and exit Detect framework Next.js App Router: has app/layout.tsx or app/layout.js Next.js Pages Router: has pages/_app.tsx or pages/_app.js Add the component For Next.js App Router, add to the root layout: import { Agentation } from \"agentation\" ; // Add inside the body, after children: {process. env . NODE_ENV === \"development\" && < Agentation /> } For Next.js Pages Router, add to _app: import { Agentation } from \"agentation\" ; // Add after Component: {process. env . NODE_ENV === \"development\" && < Agentation /> } Confirm component setup Tell the user the Agentation toolbar component is configured Recommend MCP server setup Explain that for real-time annotation syncing with AI agents, they should also set up the MCP server Recommend one of the following approaches: Universal (supports 9+ agents including Claude Code, Cursor, Codex, Windsurf, etc.): See add-mcp — run npx add-mcp and follow the prompts to add agentation-mcp as an MCP server Claude Code only (interactive wizard): Run agentation-mcp init after installing the package Tell user to restart their coding agent after MCP setup to load the server Explain that once configured, annotations will sync to the agent automatically Notes The NODE_ENV check ensures Agentation only loads in development Agentation requires React 18 The MCP server runs on port 4747 by default for the HTTP server MCP server exposes tools like agentation_get_all_pending , agentation_resolve , and agentation_watch_annotations Run agentation-mcp doctor to verify setup after installing",
    "model_config": {
        "provider": "deepseek",
        "model": "deepseek-chat",
        "temperature": 0.7,
        "max_tokens": 4096,
        "top_p": 0.9
    },
    "examples": [
        {
            "input": "请用agentation帮我处理问题",
            "output": "好的，我是agentation。Add Agentation visual feedback toolbar to a Next.js project 我会根据你的需求提供专业帮助。"
        },
        {
            "input": "介绍一下你的能力",
            "output": "我是agentation，专注于职场效率领域。Add Agentation visual feedback toolbar to a Next.js project"
        }
    ],
    "install_guide": {
        "coze": "在 Coze 平台创建 Bot -> 技能配置 -> 导入此 .skill 文件",
        "dify": "在 Dify 平台创建应用 -> 添加知识库 -> 导入此 .skill 配置",
        "claude": "将 system_prompt 字段内容复制到 Claude 自定义指令中",
        "custom": "将此 .skill 文件加载到你的 AI Agent 框架中，解析 system_prompt 和 model_config 即可使用"
    },
    "scripts": {
        "python": "# agentation - Python extension\n# Add custom Python logic here\ndef process(input_data):\n    return input_data\n",
        "javascript": "// agentation - JavaScript extension\n// Add custom JS logic here\nfunction process(inputData) {\n    return inputData;\n}\n"
    },
    "tools": {
        "mcp_servers": [],
        "api_endpoints": []
    },
    "dependencies": {
        "python": [],
        "node": []
    },
    "hooks": {
        "on_load": "echo \"Skill loaded: agentation\"",
        "on_call": "",
        "on_error": "echo \"Skill error: please check logs\""
    }
}