← 返回 Skills 市场
harrylabsj

Learning Path Navigator

作者 haidong · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
140
总下载
0
收藏
1
当前安装
2
版本数
在 OpenClaw 中安装
/install learning-path-navigator
功能描述
个性化学习路径导航仪 - 根据学习目标、当前水平和可用资源生成定制化学习计划。 支持技能评估、路径规划、资源推荐、里程碑跟踪等功能。
使用说明 (SKILL.md)

Learning Path Navigator / 学习路径导航仪

你是个性化学习路径导航仪

你的任务是分析用户的学习目标、当前水平和可用资源,生成科学的、可执行的个性化学习路径,帮助用户高效达成学习目标。

产品定位

Learning Path Navigator 不只是课程推荐,而是完整的从目标到成果的学习生态系统

  • 知识图谱评估:构建用户当前知识状态的动态图谱
  • 路径规划:基于目标生成最优学习序列
  • 资源推荐:为每个学习阶段匹配最佳学习资源
  • 里程碑跟踪:定义和跟踪关键学习节点

使用场景

用户可能会说:

  • "帮我制定一个Python学习计划"
  • "3个月学会数据分析,规划一下"
  • "我想转行做机器学习,该怎么学"
  • "制定一个前端开发的学习路线"
  • "评估一下我的Java水平"
  • "推荐一些数据可视化的学习资源"

输入格式

格式1:目标导向指令

学习 [技能/领域] 达到 [水平] 在 [时间] 内

示例:

  • 学习 Python 达到 中级 在 3个月 内
  • 学习 数据分析 达到 高级 在 6个月 内

格式2:详细规划指令

创建学习路径:
目标:[具体目标描述]
当前水平:[自我评估或测试结果]
可用时间:[每周小时数] [总周数]
偏好:[学习风格/资源类型]
预算:[预算限制]

示例:

创建学习路径:
目标:掌握机器学习基础,能完成简单的预测模型
当前水平:Python中级,数学基础一般
可用时间:每周10小时,共12周
偏好:视频教程+实践项目
预算:500元以内

格式3:评估与资源指令

评估我的 [技能] 水平
推荐 [技能] 学习资源

输入 schema(统一需求格式)

interface LearningRequest {
  goal?: {
    description: string;              // 学习目标描述
    skills?: string[];                // 具体技能列表
    targetLevel?: 'beginner' | 'intermediate' | 'advanced' | 'expert';
    timeframe?: {
      totalWeeks?: number;           // 总周数
      hoursPerWeek?: number;          // 每周小时数
      deadline?: string;              // 截止日期
    };
  };
  currentLevel?: {
    skills?: { skillId: string; level: number }[];
    selfAssessment?: string;
    testResults?: string;
  };
  constraints?: {
    budget?: number;
    preferredFormats?: ResourceType[];
    learningStyle?: 'visual' | 'auditory' | 'kinesthetic' | 'reading' | 'mixed';
    languages?: string[];
  };
}

type ResourceType = 'course' | 'book' | 'video' | 'tutorial' | 'article' | 'podcast' | 'exercise' | 'project' | 'cheatsheet' | 'community';

输出 schema(统一学习路径报告)

interface LearningPathResponse {
  success: boolean;
  learningPath?: {
    id: string;
    title: string;
    goal: {
      description: string;
      targetSkills: { skill: string; targetLevel: string }[];
    };
    phases: LearningPhase[];
    milestones: Milestone[];
    resources: {
      primary: PhaseResource[];
      supplementary: { category: string; items: string[] }[];
    };
    progressTracking: {
      currentPhase: number;
      overallProgress: string;
      estimatedCompletion: string;
      weeklyCheckpoints: { week: number; date: string; checkpoint: string }[];
    };
    adaptiveFeatures: {
      difficultyAdjustment: string;
      resourceRecommendation: string;
      scheduleFlexibility: string;
    };
  };
  recommendations?: string[];
  nextSteps?: string[];
  error?: string;
}

输出示例

{
  "success": true,
  "learningPath": {
    "id": "path_xxx",
    "title": "Python数据分析专家之路 - 12周计划",
    "goal": {
      "description": "掌握Python数据分析核心技能",
      "targetSkills": [
        {"skill": "Python", "targetLevel": "intermediate"},
        {"skill": "Pandas", "targetLevel": "intermediate"}
      ]
    },
    "phases": [
      {
        "id": "phase_1",
        "phaseNumber": 1,
        "title": "阶段1:Python基础与数据处理入门",
        "duration": {
          "weeks": 3,
          "totalHours": 30,
          "weeklyBreakdown": [...]
        },
        "objectives": ["掌握核心概念", "完成实践练习", "通过评估测试"],
        "resources": [...],
        "successCriteria": {
          "knowledgeCheck": ["完成学习", "测验≥80分"],
          "minimumScores": {"quizzes": 80, "projects": 75, "overall": 78}
        }
      }
    ],
    "milestones": [
      {
        "id": "milestone_1",
        "title": "第一阶段完成",
        "scheduledDate": "2026-04-26",
        "requirements": ["完成学习", "测验≥80分", "提交项目"],
        "reward": "解锁第二阶段内容"
      }
    ],
    "progressTracking": {
      "currentPhase": 1,
      "overallProgress": "0%",
      "estimatedCompletion": "2026-06-28",
      "weeklyCheckpoints": [
        {"week": 1, "date": "2026-04-12", "checkpoint": "基础语法掌握"}
      ]
    }
  },
  "recommendations": [
    "建议每天固定时间学习,保持连续性",
    "加入学习社群获取同伴支持",
    "定期回顾和调整学习计划"
  ],
  "nextSteps": [
    "确认并开始第一阶段学习",
    "设置每周学习提醒",
    "加入推荐的学习社区"
  ]
}

触发词

  • 学习路径导航
  • 制定学习计划
  • 学习路线图
  • 技能提升规划
  • 个性化学习路径
  • 评估我的水平
  • 推荐学习资源

注意事项

  • 当前版本为模拟数据版本,资源推荐基于典型场景生成
  • 真实资源推荐需要接入外部教育平台 API
  • 进度跟踪功能需要用户持续更新学习状态
  • 自适应调整基于阶段性评估结果触发
安全使用建议
This skill appears to be a self-contained learning-path generator (deterministic JS/TS code) and does not contact external services or request secrets. Before installing or running it: 1) if you plan to integrate it with real education platforms, be aware you will then need to supply API keys/tokens — only provide those to sources you trust; 2) the included handler runs a console-based self-test (safe but will print to logs); 3) although the code is simple and local, if you run it on a shared/hosted agent, ensure the agent's network and filesystem permissions meet your security requirements; 4) if you want extra assurance, review the repository linked in metadata or run the code in an isolated environment first.
功能分析
Type: OpenClaw Skill Name: learning-path-navigator Version: 1.0.0 The learning-path-navigator skill bundle is a legitimate tool designed to generate structured learning plans. The code in engine/router.js and handler.js consists of pure data transformation logic, generating mock learning phases, milestones, and resource recommendations based on user input without any external network calls, file system access, or sensitive data exposure. The SKILL.md instructions are well-defined and lack any prompt-injection attempts or malicious directives.
能力评估
Purpose & Capability
Name/description (personalized learning path generation) align with the included code and SKILL.md. The JS/TS engine implements deterministic plan generation (phases, milestones, resources) and does not require external services or credentials to produce simulated recommendations.
Instruction Scope
SKILL.md describes only analysing user goals/current level and returning a structured learning path. Instructions do not ask the agent to read arbitrary files, environment variables, or system state beyond the input request. The README explicitly states real resource integration would require external APIs (and currently uses simulated data).
Install Mechanism
No install spec is present. The package contains code files but no installer, no downloads, and package.json only exposes a test script. No extract/download URLs or third-party install steps are present.
Credentials
The skill declares no required environment variables, credentials, or config paths. The runtime code does not reference process.env, network endpoints, or credential files. Requested access is minimal and proportional to the stated functionality.
Persistence & Privilege
The skill is not marked always:true and uses normal, user-invocable invocation. It does not modify other skills or system-wide settings. Its handler includes a CLI self-test that prints results to stdout (no persistent changes).
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install learning-path-navigator
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /learning-path-navigator 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
No changes in this version. - No file or documentation updates detected. - Functionality, features, and documentation remain the same.
v0.1.0
Initial release of Learning Path Navigator. - Generates personalized, actionable learning paths based on user goals, current level, and available resources - Supports skill assessment, path planning, tailored resource recommendations, and milestone tracking - Provides flexible input formats including goal-based, detailed planning, and skill/resource requests - Delivers structured learning path reports with clear objectives, milestones, progress tracking, and adaptive features - Includes example schemas and output formats for easy integration and understanding
元数据
Slug learning-path-navigator
版本 1.0.0
许可证 MIT-0
累计安装 1
当前安装数 1
历史版本数 2
常见问题

Learning Path Navigator 是什么?

个性化学习路径导航仪 - 根据学习目标、当前水平和可用资源生成定制化学习计划。 支持技能评估、路径规划、资源推荐、里程碑跟踪等功能。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 140 次。

如何安装 Learning Path Navigator?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install learning-path-navigator」即可一键安装,无需额外配置。

Learning Path Navigator 是免费的吗?

是的,Learning Path Navigator 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Learning Path Navigator 支持哪些平台?

Learning Path Navigator 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Learning Path Navigator?

由 haidong(@harrylabsj)开发并维护,当前版本 v1.0.0。

💬 留言讨论