AI Engineering from Scratch 课程的交互式课程 tutor。读取 LEARNING.md,获取下一课, 在终端按章节教学,结尾测验并记录进度。可在克隆仓库中或完全通过 raw.githubusercontent.com 工作—— 无需设置。触发短语:“下一课”、“教我”、“继续课程”、“我们来学习”、“继续学习”,或 "next lesson", "teach…

MITAuto-check passedEducation

Install Learn

skills CLI
$ npx skills add fancyboi999/ai-engineering-from-scratch-zh --skill learn -a claude-code

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

GitHub CLI
$ gh skill install fancyboi999/ai-engineering-from-scratch-zh learn --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/fancyboi999/ai-engineering-from-scratch-zh.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/learn .claude/skills/learn && 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
learn
GitHub stars
1.2k
Token cost
~1.1k tokens
SKILL.md length
310 words
Files
1
Skills in repo
14
Repo updated
First seen
Licence
MIT

At a glance

AI Engineering from Scratch 课程的交互式课程 tutor。读取 LEARNING.md,获取下一课, 在终端按章节教学,结尾测验并记录进度。可在克隆仓库中或完全通过 raw.githubusercontent.com 工作—— 无需设置。触发短语:“下一课”、“教我”、“继续课程”、“我们来学习”、“继续学习”,或 "next lesson", "teach…

  • Works in 5 steps: 建立问题背景:用 2-3 句话,并在自然时关联 LEARNING.md… → 核心概念:按学习者水平用自己的话解释,任何数学前先暂停并提出理解问题。逐步讲解方程… → 动手构建:将从零代码分为每段 5-15… → …
  • Tasks that involve Tutoring and explanations
  • SKILL.md covers 宿主调用契约, 内容来源, 跨课程模式的续学路由 and 专门 MCP 交接, plus 7 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Learn is an agent skill from fancyboi999/ai-engineering-from-scratch-zh. AI Engineering from Scratch 课程的交互式课程 tutor。读取 LEARNING.md,获取下一课, 在终端按章节教学,结尾测验并记录进度。可在克隆仓库中或完全通过 raw.githubusercontent.com 工作—— 无需设置。触发短语:“下一课”、“教我”、“继续课程”、“我们来学习”、“继续学习”,或 "next lesson", "teach me", "continue the course", "let's learn", "resume learning"

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Education, covering Tutoring and explanations. It works with Model Context Protocol. The repository describes itself as: Agent工程师最全学习路径 · 从零精通 AI 工程 · 20 阶段 503 课 · 中文全量翻译 + 配套站点 + 动画讲解视频 · 如何成为 AI Agent 工程师的修成指南. The licence is MIT.

When your agent uses it

  • Tasks that involve Tutoring and explanations

Example prompts

  • “next lesson”
  • “teach me”
  • “continue the course”
  • “/learn”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. 建立问题背景:用 2-3 句话,并在自然时关联 LEARNING.md 中学习者的 Mission。不要照读文件。
  2. 核心概念:按学习者水平用自己的话解释,任何数学前先暂停并提出理解问题。逐步讲解方程;尽量要求预测下一步(“这里 x 为负数时,gradient 会怎样?”)。
  3. 动手构建:将从零代码分为每段 5-15 行。对每段说明做什么、为何存在,并问一个预测问题。仓库已克隆且语言 runtime 可用时运行代码并展示真实输出;否则用微小具体输入手工跟踪。
  4. 实际使用:展示 production-library 版本,要求学习者指出该库替他们处理了哪些从零实现中显式呈现的工作。
  5. 每次暂停都必须真实交互:等待回答,针对其实际说法回应并调整深度。学习者说“我会这个,快一点”优先于脚本。

What it can do on your machine

Read from SKILL.md and the folder at commit fb127e2. 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.

    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

Learn loads about 1.1k tokens when it runs. Until then it costs about 65 tokens; SKILL.md has 310 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~65
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

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 fancyboi999/ai-engineering-from-scratch-zh at commit fb127e2, republished under its MIT licence (© fancyboi999). 310 words, ~1,128 tokens.

Download SKILL.mdSave it as .claude/skills/learn/SKILL.md (or your agent's skills folder).
name
learn
description
AI Engineering from Scratch 课程的交互式课程 tutor。读取 LEARNING.md,获取下一课, 在终端按章节教学,结尾测验并记录进度。可在克隆仓库中或完全通过 raw.githubusercontent.com 工作—— 无需设置。触发短语:“下一课”、“教我”、“继续课程”、“我们来学习”、“继续学习”,或 "next lesson", "teach me", "continue the course", "let's learn", "resume learning"
version
1.0.0
tags
tutor, curriculum, ai-engineering, interactive-learning

学习

你是 AI Engineering from Scratch 课程的 tutor。一次调用 = 一节课,必须交互式教学:学习者应输入、回答和运行内容,绝不能只滚动阅读。适用于任何 agent。

宿主调用契约

skill 名称可移植,但调用语法属于宿主。每次建议下一步时都要采用正确形式:

  • Codex:learn、start-learning、check-understanding 13 等 skill-name 形式,或告诉学习者从 /skills 选择 skill。
  • Claude Code:/learn、/start-learning、/check-understanding 13 等 /skill-name 形式。
  • 其他兼容宿主:使用自然语言,例如 Use start-learning to build my course plan. 或 Use check-understanding to quiz me on Phase 13.

绝不把斜杠命令说成通用语法。宿主未知时,使用自然语言形式。

内容来源

仓库已克隆时优先使用本地文件(当前目录或父目录有 phases/);否则从以下位置获取:

text
https://raw.githubusercontent.com/fancyboi999/ai-engineering-from-scratch-zh/main/<path>
  • 课程文本:phases/<phase-dir>/<lesson-dir>/docs/zh.md
  • 课程测验:phases/<phase-dir>/<lesson-dir>/quiz.json
  • 某阶段课程列表:README.md 的 Contents 部分(每阶段表格列出每课目录路径和标题)

跨课程模式的续学路由

第 0 步前,将每个“继续”或“续学”请求按以下支持的状态文件及路线所有者解析:

  • LEARNING.md 属于完整课程的 learn。
  • MCP-LEARNING.md 属于 Model Context Protocol (MCP) 路线的 learn-mcp。
  • MCP-ENGINEERING-LEARNING.md 是同一 learn-mcp 路线的旧文件名,不是独立路线。
  • AGENT-SKILLS-LEARNING.md 属于 learn-agent-skills。
  • CLAUDE-CERTIFICATION.md 属于 claude-certification。

学习者在续学请求中点名路线时,即使其他状态文件存在,也立即分派给所有者。所有者是 learn 时继续第 0 步;否则调用点名所有者并停止本 skill。

未点名的续学请求,收集存在状态文件的所有者,并将两个 MCP 文件名归为 learn-mcp。若恰有一个路线所有者,先恢复它;只有所有者是 learn 才在这里继续,否则调用该所有者并停止此 skill。learn-mcp 负责 legacy-file migration 与 collision reporting。若有两个或更多路线所有者,列出面向学习者的路线名,并在选择课程或更改任何状态前询问要恢复哪条。没有任何状态文件时进入第 0 步。绝不依据文件修改时间推断路线,也绝不把一条路线的进度合并到另一份状态中。

旧 runtime 可能将 learn-mcp-engineering 暴露为别名。只接受它以到达 learn-mcp;所有面向学习者的交接都渲染为 learn-mcp,路线名称为 Model Context Protocol (MCP)。

专门 MCP 交接

学习者要求 Model Context Protocol (MCP) 路线,或者存在 MCP-LEARNING.md/MCP-ENGINEERING-LEARNING.md 且其要求恢复 MCP 时(MCP-ENGINEERING-LEARNING.md exists),交接给可移植 skill learn-mcp。专注 tutor 在不丢失学习者证据的情况下迁移旧文件名(without discarding learner evidence)。其唯一事实来源为 learning-paths/model-context-protocol.json。不要选择数值上的下一节第 13 阶段课程,也不要把 MCP 状态复制到 LEARNING.md;专用 tutor 拥有路线顺序、wire checkpoints 与安全闸门。

专门 Agent Skills 交接

学习者要求 Agent Skills 路线,或者存在 AGENT-SKILLS-LEARNING.md 且其要求继续/恢复 Agent Skills 时,交接给可移植 skill learn-agent-skills。其唯一事实来源为 learning-paths/agent-skills.json。按宿主调用契约渲染交接。不要选择数值上的下一节第 13 阶段课程,也不要将 Agent Skills 状态复制到 LEARNING.md;专用 tutor 拥有五节课程顺序、真实宿主证据、sandbox boundaries、第 26 课前的第 25 课与 tool-poisoning prerequisite gate,以及 release gate。

第 0 步 —— 定位状态

从当前目录读取 LEARNING.md。

  • 找到: 下一课是状态为 Do 或 Review 的第一个阶段中第一节未记录课程(阶段顺序、课程顺序)。学习者明确点名课程或主题(“教我 backprop”)时,遵从该请求并在日志中记录此绕行。
  • 找到,但没有符合条件的课程:(每个 Do/Review 阶段均已完整记录)不进行教学。祝贺其完成路径,将任何完成阶段的状态设为 Done,并给出三个真实选择:完成 Review 队列、对自选阶段使用 check-understanding,或使用 start-learning 把计划延展到跳过阶段。两种 skill 调用均按宿主调用契约渲染。
  • 未找到: 说明 start-learning 可构建个性化计划,按宿主调用契约渲染,并提供两个选项——现在运行它,或无计划直接从第 1 阶段第 1 课开始。绝不因设置阻塞课程。

第 1 步 —— 热身回忆(仅在记录过前一课时)

在新内容前,从前一课的 quiz 随机抽 2 题。没有压力,不记分——每题答案给一句反馈。间隔后的提取能把知识转入长期记忆,这是本步骤全部目的。学习者两题都错时,提供重做该课的选择而非直接推进,但让其自行决定。

学习者回答前保持正确选项私密。回复格式提示绝不放真实答案字母、可能答案或 quiz 答案分布。纯文本使用 Reply with one letter: <A|B|C|D>.

第 2 步 —— 教授课程

获取课程的 docs/zh.md。课程共用固定骨架:problem、core concept、build-it-from-scratch、use-the-production-library、quiz、artifact。按此顺序交互教学:

  1. 建立问题背景:用 2-3 句话,并在自然时关联 LEARNING.md 中学习者的 Mission。不要照读文件。
  2. 核心概念:按学习者水平用自己的话解释,任何数学前先暂停并提出理解问题。逐步讲解方程;尽量要求预测下一步(“这里 x 为负数时,gradient 会怎样?”)。
  3. 动手构建:将从零代码分为每段 5-15 行。对每段说明做什么、为何存在,并问一个预测问题。仓库已克隆且语言 runtime 可用时运行代码并展示真实输出;否则用微小具体输入手工跟踪。
  4. 实际使用:展示 production-library 版本,要求学习者指出该库替他们处理了哪些从零实现中显式呈现的工作。
  5. 每次暂停都必须真实交互:等待回答,针对其实际说法回应并调整深度。学习者说“我会这个,快一点”优先于脚本。

第 3 步 —— 测验

获取 quiz.json,提问每一个 stage 为 "post" 的问题(没有标记时回退为全部题目)。一次一道,带字母选项,不给提示。每次回答后给出结论与文件中的解释。学习者回答前不暴露 correct、答案索引或带真实答案字母的示例。报告得分 N/M。

第 4 步 —— 记录

更新 LEARNING.md:

  • 在 Progress log 追加一行:日期、<phase>/<lesson>、得分及单行笔记(学习者困难或说过的内容,对下次热身有用)。
  • 得分低于 70%:将课程和遗漏主题加入 Review queue。
  • 阶段最后一课完成:将阶段 Status 设为 Done,并建议用 check-understanding <phase> 进行完整阶段测验,按宿主调用契约渲染。

没有 LEARNING.md(学习者拒绝设置)时,静默跳过,不要在第 0 步之后反复提醒。

第 5 步 —— 收尾

只用两行:他们现在能构建或解释、而一小时前还不能做到的内容;以及下一课标题作为钩子(“下一课:attention —— 为什么 ‘the cat sat on the mat’ 需要 36 次 dot products”)。

© fancyboi999, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/learn of fancyboi999/ai-engineering-from-scratch-zh.

Open the folder on GitHubat commit fb127e2

Compare with similar skills

Learn next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Learn compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Learn this skillfancyboi999/ai-engineering-from-scratch-zh1.2k—~1.1kAutomated safety check: PassMIT
AI Engineering Course Guiderohitg00/ai-engineering-from-scratch66k—~1.7kAutomated safety check: PassMIT
Workshopbrevdev/workshop-build-an-agent144—~1.4kAutomated safety check: PassApache-2.0
Workshopbrevdev/workshop-build-an-agent144—~1.4kAutomated safety check: PassApache-2.0
MCPA Certification Tutorrohitg00/ai-engineering-from-scratch66k—~3.5kAutomated safety check: PassMIT
Learn MCP Tutorrohitg00/ai-engineering-from-scratch66k—~2.4kAutomated safety check: PassMIT

Similar skills

  • AI Engineering Course Guide

    rohitg00/ai-engineering-from-scratch

    Routes a topic, question or bug to the exact lessons in the AI Engineering from Scratch curriculum and suggests the next command to run.

    66k GitHub stars~1.7k tokensUpdated yesterday
    EducationAuto-check passed
  • Workshop

    brevdev/workshop-build-an-agent

    This skill should be used when a learner wants to navigate or understand the Build-an-Agent workshop as a whole — e.g.

    144 GitHub stars~1.4k tokensUpdated yesterday
    EducationAuto-check passed
  • Workshop

    brevdev/workshop-build-an-agent

    This skill should be used when a learner wants to navigate or understand the Build-an-Agent workshop as a whole — e.g.

    144 GitHub stars~1.4k tokensUpdated yesterday
    EducationAuto-check passed
  • MCPA Certification Tutor

    rohitg00/ai-engineering-from-scratch

    Turns a GitHub course repository into an interactive tutor for the MCP Associate certification, making the learner explain and defend each step.

    66k GitHub stars~3.5k tokensUpdated yesterday
    EducationAuto-check passed
  • Learn MCP Tutor

    rohitg00/ai-engineering-from-scratch

    An interactive tutor for the Model Context Protocol path in AI Engineering from Scratch, teaching one lesson per invocation and recording wire evidence in MCP-LEARNING.md.

    66k GitHub stars~2.4k tokensUpdated yesterday
    EducationAuto-check passed
  • AI Engineering Project Tutor

    rohitg00/ai-engineering-from-scratch

    Tutors a learner through one stage of a hands-on AI engineering project per session: lesson, prediction, code, grader run and reflection, with hints but never full solutions.

    66k GitHub stars~1.6k tokensUpdated yesterday
    EducationAuto-check passed

More from fancyboi999/ai-engineering-from-scratch-zh

All 14 skills in this repo
  • Skill Release Gate

    fancyboi999/ai-engineering-from-scratch-zh

    在发布前评估 Agent Skill bundle 的结构完整性、触发质量、产物改进、脚本正确性、安全性、已安装目录树完整性和目标宿主可移植性。

    1.2k GitHub stars~472 tokensUpdated 10 days ago
    Auto-check passed
  • Find Your Level

    fancyboi999/ai-engineering-from-scratch-zh

    交互式测验,将你的 AI/ML 知识映射到 523 节课、20 个阶段的 AI Engineering from Scratch 课程起点。

    1.2k GitHub stars~1k tokensUpdated 10 days ago
    Auto-check passed
  • Check Understanding

    fancyboi999/ai-engineering-from-scratch-zh

    AI Engineering from Scratch 的阶段测验。用于“给我测验一下”、“测试阶段”、“检查我的理解”、“我掌握第 3 阶段了吗”,也支持 "quiz me", "test phase", "check my understanding", "do I know phase 3" 或 /check-understanding <phase。

    1.2k GitHub stars~1.1k tokensUpdated 10 days ago
    Auto-check passed
  • Claude Certification

    fancyboi999/ai-engineering-from-scratch-zh

    AI Engineering from Scratch 中四条独立 Claude 认证路线的 AI 原生导师与入门流程。适用于学习者 希望选择 Claude 认证、备考 CCAO-F、CCDV-F、CCAR-F 或 CCAR-P、继续认证路径、以交互方式学习 下一课、运行并验证实践实验、构建并评分产物、参加诊断或模拟测评,或通过 GitHub 上的 Claude Code、…

    1.2k GitHub stars~1.3k tokensUpdated 10 days ago
    Auto-check passed
  • Course Guide

    fancyboi999/ai-engineering-from-scratch-zh

    AI Engineering from Scratch 课程的主题路由器。给它一个主题、问题或正在处理的 bug, 它会指出精确教授它的课程,以及下一条正确命令。触发短语: “在哪里学习”、“哪节课涵盖”、“课程导航”、“我卡在”、“接下来该做什么”、 “教我 MCP”、“教我 Agent Skills”、“在哪里准备 Claude certification”,或 "where do I…

    1.2k GitHub stars~948 tokensUpdated 10 days ago
    Auto-check passed
  • Learn Agent Skills

    fancyboi999/ai-engineering-from-scratch-zh

    AI Engineering from Scratch 中 Agent Skills Engineering 路线的专注交互 tutor。

    1.2k GitHub stars~1.1k tokensUpdated 10 days ago
    Auto-check passed

Questions about Learn

What does Learn do?

AI Engineering from Scratch 课程的交互式课程 tutor。读取 LEARNING.md,获取下一课, 在终端按章节教学,结尾测验并记录进度。可在克隆仓库中或完全通过 raw.githubusercontent.com 工作—— 无需设置。触发短语:“下一课”、“教我”、“继续课程”、“我们来学习”、“继续学习”,或 "next lesson", "teach…. Learn is an agent skill from fancyboi999/ai-engineering-from-scratch-zh.

When should I use Learn?

Learn fits situations like: tasks that involve Tutoring and explanations.

How do I install Learn in Claude Code?

Run `npx skills add fancyboi999/ai-engineering-from-scratch-zh --skill learn -a claude-code`. Or copy the skill folder (skills/learn in fancyboi999/ai-engineering-from-scratch-zh) into .claude/skills/learn in your project. Claude Code loads it when a task matches its description.

How do I install Learn in Codex?

Run `npx skills add fancyboi999/ai-engineering-from-scratch-zh --skill learn -a codex`. Or copy the skill folder (skills/learn in fancyboi999/ai-engineering-from-scratch-zh) into .agents/skills/learn in your project. Codex loads it when a task matches its description.

Can I use Learn 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 fancyboi999/ai-engineering-from-scratch-zh --skill learn -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/learn, .gemini/skills/learn, .github/skills/learn and .opencode/skills/learn in your project.

What does Learn need to run?

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

Does Learn 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 Learn 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 Learn use?

Learn 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 Learn use?

About 1.1k tokens (SKILL.md is roughly 4.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Learn?

Skills that share tags, products or a category with Learn: AI Engineering Course Guide (rohitg00/ai-engineering-from-scratch, 66k stars), Workshop (brevdev/workshop-build-an-agent, 144 stars), Workshop (brevdev/workshop-build-an-agent, 144 stars) and MCPA Certification Tutor (rohitg00/ai-engineering-from-scratch, 66k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Learn?

fancyboi999 (a GitHub user) maintains it in fancyboi999/ai-engineering-from-scratch-zh, which has 1,182 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on September 28, 2026.

Source: fancyboi999/ai-engineering-from-scratch-zh on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.