用AI教AI写代码，让开发者通过实战项目快速掌握Claude Code工具。
Agentic Education: Using Claude Code to Teach Claude Code
- 设计渐进式教学角色，从引导到放手，逐步提升学习自主性。
- 实测显示10项技能自信心显著提升，高级功能掌握效果尤佳。
- 课程自动更新，适配工具变化，适合想高效上手AI编程的开发者。
AI编程助手迅速普及，但系统化的学习框架仍稀缺。开发者常面临文档与实践之间的鸿沟，依赖零散资源如博客、视频和试错。我们提出cc-self-train，一个模块化交互式课程，通过动手项目教授Claude Code——一种智能体式AI编程工具。系统包含五大贡献：（1）角色渐进模型，分四个阶段（引导者、合作者、同行、启动者）调整教学语气，实现AI辅助教学的责任渐移；（2）自适应学习系统，通过钩子启发式方法监测参与质量，在短期（连续完成检测）和长期（模块间）两个时间尺度调整支持；（3）跨领域统一课程，五个项目领域共享相同特征序列，促进迁移学习；（4）步调控制机制，引入显式暂停原语，防止信息过载；（5）自动更新课程设计，入门代理可检测上游工具变更，并在教学前更新教学材料。参数化测试套件确保50个模块的结构一致性，作为教学恒定性的代理。27名参与者的小规模评估显示，所有10项技能领域自信心均显著提升（p < 0.001），尤其在钩子和自定义技能等高级功能上效果突出。讨论了自更新教育系统的设计意义。
原文摘要 · Abstract (English)
AI coding assistants have proliferated rapidly, yet structured pedagogical frameworks for learning these tools remain scarce. Developers face a gap between tool documentation and practical mastery, relying on fragmented resources such as blog posts, video tutorials, and trial-and-error. We present cc-self-train, a modular interactive curriculum for learning Claude Code, an agentic AI coding tool, through hands-on project construction. The system introduces five contributions: (1) a persona progression model that adapts instructor tone across four stages (Guide, Collaborator, Peer, Launcher), operationalizing Gradual Release of Responsibility for AI-mediated instruction; (2) an adaptive learning system that observes engagement quality through hook-based heuristics and adjusts scaffolding at two timescales, using streak detection for mid-module intervention and aggregate metrics for module-boundary persona changes; (3) a cross-domain unified curriculum in which five distinct project domains share identical feature sequencing, enabling transfer learning; (4) a step-pacing mechanism with explicit pause primitives to manage information overload in an AI-as-instructor context; and (5) an auto-updating curriculum design in which the onboarding agent detects upstream tool changes and updates teaching materials before instruction begins. A parametrized test suite enforces structural consistency as a proxy for pedagogical invariants across all 50 modules. A pilot evaluation with 27 participants shows statistically significant reported self-efficacy gains across all 10 assessed skill areas (p < 0.001), with the largest effects on advanced features such as hooks and custom skills. We discuss implications for the design of auto-updating educational systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。