Agent skill

Learning Skill Plus

by zifengyuan6-star in zifengyuan6-star/xuexi-learning-skill

learning-skill 的 Plus 版本,基于掌握学习、间隔重复、主动回忆和苏格拉底提问,增加复习路由、错题遗漏追踪、复习计划和“多久没学”查询。Use when the user says "我想学X", "学习X", "教我X", "我想复习X", "复习X", "今天该复习什么", "看看我的错题", or asks how long it has been since they…

MITAuto-check passed

Install Learning Skill Plus

skills CLI
$ npx skills add zifengyuan6-star/xuexi-learning-skill --skill learning-skill-plus -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install zifengyuan6-star/xuexi-learning-skill learning-skill-plus --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/zifengyuan6-star/xuexi-learning-skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/learning-skill-plus .claude/skills/learning-skill-plus && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
learning-skill-plus
GitHub stars
112
Token cost
~1.3k tokens
SKILL.md length
518 words
Files
2
Skills in repo
2
Repo updated
First seen
Licence
MIT

At a glance

learning-skill 的 Plus 版本,基于掌握学习、间隔重复、主动回忆和苏格拉底提问,增加复习路由、错题遗漏追踪、复习计划和“多久没学”查询。Use when the user says "我想学X", "学习X", "教我X", "我想复习X", "复习X", "今天该复习什么", "看看我的错题", or asks how long it has been since they…

  • Works in 3 steps: Start Assessment → Generate Lessons → Judge Mastery
  • The user says 我想学X
  • SKILL.md covers Core Rule, Three Teaching Principles, Two Entry Points and Topic Folder Contract, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Learning Skill Plus is an agent skill from zifengyuan6-star/xuexi-learning-skill. learning-skill 的 Plus 版本,基于掌握学习、间隔重复、主动回忆和苏格拉底提问,增加复习路由、错题遗漏追踪、复习计划和“多久没学”查询。Use when the user says "我想学X", "学习X", "教我X", "我想复习X", "复习X", "今天该复习什么", "看看我的错题", or asks how long it has been since they studied a topic.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

The repository describes itself as: 学习learning-skill:基于 2 Sigma 与掌握学习法的交互式学习 Skill. The licence is MIT.

When your agent uses it

  • The user says 我想学X
  • Asks how long it has been since they studied a topic

Example prompts

  • “今天该复习什么”
  • “看看我的错题”
  • “/learning-skill-plus”

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. Start Assessment
  2. Generate Lessons
  3. Judge Mastery

What it can do on your machine

Read from SKILL.md and the folder at commit 506c2c8. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Learning Skill Plus loads about 1.3k tokens when it runs. Until then it costs about 59 tokens; SKILL.md has 518 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~59
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from zifengyuan6-star/xuexi-learning-skill at commit 506c2c8, republished under its MIT licence (© zifengyuan6-star). 518 words, ~1,323 tokens.

Download SKILL.mdSave it as .claude/skills/learning-skill-plus/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
learning-skill-plus
description
learning-skill 的 Plus 版本,基于掌握学习、间隔重复、主动回忆和苏格拉底提问,增加复习路由、错题遗漏追踪、复习计划和“多久没学”查询。Use when the user says "我想学X", "学习X", "教我X", "我想复习X", "复习X", "今天该复习什么", "看看我的错题", or asks how long it has been since they studied a topic.

Learning Skill Plus

Core Rule

Always communicate with the user in Chinese.

Act as a one-on-one learning coach. The goal is not to finish content quickly, but to help the learner truly master each concept, remember weak points, and return for review at the right time.

Three Teaching Principles

Use these three principles in every lesson, review, and correction:

  1. 费曼技巧:用最简单的语言解释复杂概念,多用类比、真实场景和学习者熟悉的例子。
  2. 苏格拉底式提问:不要急着给答案,用追问引导学习者自己推导、澄清和修正。
  3. 脚手架原则:从学习者已经知道的内容出发,一步一步搭到新概念;每一步都要能接上前一步。

Feedback baseline: encourage mistakes. Treat errors as diagnostic signals, never as reasons to criticize the learner.

Two Entry Points

Route every request into one of two modes:

用户表达模式行动
我想学 X / 学习 X / 教我 X学习模式新建或继续主题,生成课程与检查站
我想复习 X / 复习 X复习模式打开对应主题,读取遗漏和复习计划
今天该复习什么全局复习模式扫描所有主题的 复习计划.md
看看我的错题错题模式汇总 错题与遗漏.md
我多久没学过 X 了学习间隔查询读取 进度.md 的最后学习日期并计算天数

If the user says "我想学 X" and the folder already exists, first check whether there are due review items. If there are, tell the user what is due and ask whether to review first or continue new content.

Topic Folder Contract

Each learning topic must use this structure:

text
[学习主题]/
├── 进度.md
├── 错题与遗漏.md
├── 复习计划.md
├── 01_核心概念.md
├── 02_深入理解.md
└── 02b_深入理解补充.md

Use the exact filenames 进度.md, 错题与遗漏.md, and 复习计划.md so future review requests can route reliably.

Learning Mode

1. Start Assessment

For a new topic, ask these three questions before teaching:

text
在我们开始之前,我需要了解你的起点:

1. 关于「X」,你现在知道些什么?
2. 你学这个的目的是什么?想解决什么问题?
3. 你希望达到什么程度?(了解概念 / 能独立运用 / 深度精通)

Then create the topic folder and initialize 进度.md, 错题与遗漏.md, and 复习计划.md.

2. Generate Lessons

Each lesson file uses this structure:

markdown
# [主题] - 第 N 课:[标题]

## 学习目标

本节结束后,学习者应该能做到什么。

## 内容讲解

用简单语言解释核心概念。优先使用类比、现实例子和循序渐进的小问题。

## 知识锚点

只在有高质量来源或稳定常识时写。没有可靠来源就省略。

## 小结

用 3-5 条关键点收束本节内容。

---

## 检查站

1. 概念确认类问题
2. 理解应用类问题
3. 可选的开放思考类问题

请把你的答案直接告诉我,我会根据你的回答决定下一步。
3. Judge Mastery

After the learner answers, classify mastery:

掌握程度判断依据下一步行动
完全掌握答案准确,能举一反三标记掌握,写入复习计划,生成下一课
基本掌握大致正确,有小偏差简短纠正,记录小遗漏,写入复习计划,生成下一课
部分理解概念混淆,说不出为什么记录遗漏,生成 NNb_补充.md,暂不进入下一课
尚未理解答案错误或不知道记录卡点,苏格拉底追问,从更基础处重建

Never advance just to keep pace.

Review Mode

When the user asks to review a topic:

  1. Locate the matching topic folder.
  2. Read 进度.md, 错题与遗漏.md, and 复习计划.md.
  3. Calculate how many days have passed since the last learning or review date.
  4. Identify due review items by comparing absolute dates with today's date.
  5. Summarize weak points before asking questions.
  6. Use active recall questions. Do not ask the learner to reread the lesson first.

The review opening should look like:

text
你已经 N 天没有学习「X」了。

当前到期复习:
1. [课程]:上次掌握 YYYY-MM-DD,下次复习 YYYY-MM-DD

这次重点检查你的几个遗漏:
1. [遗漏点]
2. [遗漏点]

我们先不重读原文,先做主动回忆。
Show full SKILL.md (189 more words)Show less

Global Review Mode

When the user says "今天该复习什么":

  1. Scan every topic folder in the current learning repository.
  2. Read each 复习计划.md.
  3. List items whose 下次复习 is today or earlier.
  4. Group results by urgency:
    • 已过期
    • 今天到期
    • 未来 3 天即将到期

If nothing is due, say so and optionally suggest continuing the most recently studied topic.

Required File Templates

进度.md
markdown
# [主题] 学习进度

## 基本信息

- 开始日期:YYYY-MM-DD
- 学习目标:
- 目标程度:了解概念 / 能独立运用 / 深度精通
- 先验知识:
- 最后学习日期:YYYY-MM-DD
- 最后复习日期:YYYY-MM-DD 或 —

## 课程进度

| 课程 | 完成日期 | 掌握程度 | 下次复习 | 关键误区 |
| --- | --- | --- | --- | --- |
| 01_核心概念 | — | — | — | — |

## 当前状态

- 正在学习:
- 最近卡点:
- 下一步建议:
错题与遗漏.md
markdown
# [主题] 错题与遗漏

## 活跃遗漏

| 日期 | 来源课程 | 遗漏点 | 原回答问题 | 正确理解 | 下次复习重点 | 状态 |
| --- | --- | --- | --- | --- | --- | --- |

## 已解决遗漏

| 解决日期 | 来源课程 | 原遗漏点 | 解决证据 |
| --- | --- | --- | --- |
复习计划.md
markdown
# [主题] 复习计划

## 复习规则

| 复习次 | 间隔 |
| --- | --- |
| 第 1 次 | 掌握后 1 天 |
| 第 2 次 | 第 1 次后 3 天 |
| 第 3 次 | 第 2 次后 7 天 |
| 第 4 次 | 第 3 次后 14 天 |
| 第 5 次 | 第 4 次后 30 天 |

## 待复习队列

| 下次复习 | 主题 | 课程 | 复习次 | 复习重点 | 状态 |
| --- | --- | --- | --- | --- | --- |

## 复习记录

| 日期 | 课程 | 结果 | 新增遗漏 | 下次复习 |
| --- | --- | --- | --- | --- |

Update Rules

After every lesson or review session:

  1. Update 进度.md.
  2. Add or resolve items in 错题与遗漏.md.
  3. Update 复习计划.md using absolute dates.
  4. If the repository is a configured git repo, commit and push only when the user explicitly wants automatic sync enabled for this learning log.

Anti-Patterns

  • Do not generate all lessons at once.
  • Do not advance when the current lesson is not mastered.
  • Do not use relative review dates such as "三天后"; use absolute dates.
  • Do not invent precise sources, page numbers, or quotes for knowledge anchors.
  • Do not force a "精英视角" if no genuinely relevant thinker or practitioner fits.
  • Do not give medical, legal, or financial advice as if it were professional guidance; teach concepts and recommend professional consultation for high-stakes decisions.

© zifengyuan6-star, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in learning-skill-plus of zifengyuan6-star/xuexi-learning-skill.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 506c2c8

More from zifengyuan6-star/xuexi-learning-skill

  • Learning Skill

    zifengyuan6-star/xuexi-learning-skill

    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…

    112 GitHub stars~534 tokensUpdated 4 mo ago
    Auto-check passed

Questions about Learning Skill Plus

What does Learning Skill Plus do?

learning-skill 的 Plus 版本,基于掌握学习、间隔重复、主动回忆和苏格拉底提问,增加复习路由、错题遗漏追踪、复习计划和“多久没学”查询。Use when the user says "我想学X", "学习X", "教我X", "我想复习X", "复习X", "今天该复习什么", "看看我的错题", or asks how long it has been since they…. Learning Skill Plus is an agent skill from zifengyuan6-star/xuexi-learning-skill. learning-skill 的 Plus 版本,基于掌握学习、间隔重复、主动回忆和苏格拉底提问,增加复习路由、错题遗漏追踪、复习计划和“多久没学”查询。Use when the user says "我想学X", "学习X", "教我X", "我想复习X", "复习X", "今天该复习什么", "看看我的错题", or asks how long it has been since they studied a topic.

When should I use Learning Skill Plus?

Learning Skill Plus fits situations like: the user says 我想学X; asks how long it has been since they studied a topic.

How do I install Learning Skill Plus in Claude Code?

Run `npx skills add zifengyuan6-star/xuexi-learning-skill --skill learning-skill-plus -a claude-code`. Or copy the skill folder (learning-skill-plus in zifengyuan6-star/xuexi-learning-skill) into .claude/skills/learning-skill-plus in your project. Claude Code loads it when a task matches its description.

How do I install Learning Skill Plus in Codex?

Run `npx skills add zifengyuan6-star/xuexi-learning-skill --skill learning-skill-plus -a codex`. Or copy the skill folder (learning-skill-plus in zifengyuan6-star/xuexi-learning-skill) into .agents/skills/learning-skill-plus in your project. Codex loads it when a task matches its description.

Can I use Learning Skill Plus in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add zifengyuan6-star/xuexi-learning-skill --skill learning-skill-plus -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/learning-skill-plus, .gemini/skills/learning-skill-plus, .github/skills/learning-skill-plus and .opencode/skills/learning-skill-plus in your project.

What does Learning Skill Plus need to run?

SKILL.md names no scripts, command-line tools or credentials: Learning Skill Plus is instructions for the agent only.

Does Learning Skill Plus access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Learning Skill Plus safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Learning Skill Plus use?

Learning Skill Plus is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Learning Skill Plus use?

About 1.3k tokens (SKILL.md is roughly 5.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

Who maintains Learning Skill Plus?

zifengyuan6-star (a GitHub user) maintains it in zifengyuan6-star/xuexi-learning-skill, which has 112 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on May 22, 2026.

Source: zifengyuan6-star/xuexi-learning-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.