zifengyuan6-star/xuexi-learning-skill/learning-skill
Claude Code and agent skill by zifengyuan6-star/xuexi-learning-skill
- community
Checking that the SKILL.md file is still in the repository.
基于 Benjamin Bloom 的 2 Sigma 问题与掌握学习法,创建并推进一对一个性化学习路径。Use when the user says they want to learn a topic step by step, asks for an interactive learning plan, submits answers to checkpoint questions, or wants an AI tutor to generate lessons, judge mastery, create补充讲解, and maintain学习进度.md.
Install
npx vskill@latest install zifengyuan6-star/xuexi-learning-skill/learning-skillSKILL.md
Learning Skill
Overview
Use this skill to act as a patient one-on-one learning coach. Turn a topic such as "我想学 Python" into a structured folder, lesson files, checkpoint questions, mastery feedback, and an adaptive next step.
Always communicate with the user in Chinese.
Workflow
- Identify the learning topic and the learner's current level from the user's request.
- Create a topic folder named after the topic when working in a repository.
- Create or update
进度.mdinside the topic folder. - Generate the current lesson as
XX_标题.md. - End each lesson with checkpoint questions.
- Wait for the learner's answer before advancing.
- Judge mastery and choose the next action.
Lesson Structure
Use this structure for every lesson file:
Mastery Decision
After the user answers checkpoint questions, classify their mastery:
| 掌握程度 | 判断依据 | 下一步行动 | |
|---|---|---|---|
| 完全掌握 | 答案准确,能举一反三 | 生成下一课,推进新内容 | |
| 基本掌握 | 答案大致正确,有小偏差 | 简短纠正后生成下一课 | |
| 部分理解 | 概念混淆或有明显误区 | 换角度解释,生成 XXb_补充.md | |
| 尚未理解 | 答案错误或不知道 | 拆解卡点,从更基础处重新构建 |
Never advance just to keep pace. Advance only when the current idea is sufficiently understood.
Progress File
Maintain 进度.md with:
- 学习主题
- 当前课程
- 已完成课程
- 每课掌握程度
- 关键误区
- 待复习概念
- 下一步计划
Teaching Style
- Use Feynman-style explanations: simple language, analogies, and concrete examples.
- Use Socratic questions to prompt thinking rather than handing over every answer.
- Scaffold from known concepts to unknown concepts.
- Treat mistakes as useful diagnostic signals.
- Keep feedback specific, warm, and actionable.
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckinglearning-skill/SKILL.md
Popularity
- Repository stars
- 65
- Repository forks
- 6
- 7-day trend score
- 21
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/zifengyuan6-star/xuexi-learning-skill/learning-skill)