ai-engineering-from-scratch-zh is a Chinese-language adaptation of a course that teaches AI engineering by implementing algorithms, tools, and agents from the ground up. It is for learners following a 20-stage path across mathematics, machine learning, agent systems, and production topics, with lessons using Python, TypeScript, Rust, and Julia. The catalogue entries provide agent skills and instructions associated with the course.
Borrowing it
Nothing to install: this file belongs to fancyboi999/ai-engineering-from-scratch-zh. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/fancyboi999/ai-engineering-from-scratch-zh/main/.claude/skills/course-guide/SKILL.mdgit clone --depth 1 https://github.com/fancyboi999/ai-engineering-from-scratch-zhWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/fancyboi999/ai-engineering-from-scratch-zh/course-guide)<a href="https://agentmods.dev/skills/fancyboi999/ai-engineering-from-scratch-zh/course-guide"><img src="https://agentmods.dev/badge/skills/fancyboi999/ai-engineering-from-scratch-zh/course-guide/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/fancyboi999/ai-engineering-from-scratch-zh/course-guide"><img src="https://agentmods.dev/badge/skills/fancyboi999/ai-engineering-from-scratch-zh/course-guide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00136 | $0.01716 |
| Opus 5 | $0.00068 | $0.00858 |
| Sonnet 5 | $0.00027 | $0.00343 |
| Haiku 4.5 | $0.00014 | $0.00172 |
Grade A, and why
course-guide scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
课程导航
你是 AI Engineering from Scratch 课程的导览层：523 节课、20 个阶段。学习者告诉你想理解、构建或修复什么；你准确指出它在课程中的位置，以及下一条要运行的命令。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。每次推荐下一步操作时，都要采用正确形式：
- Codex：
learn、start-learning、course-guide等skill-name形式，或告诉学习者从/skills选择该 skill。 - Claude Code：
/learn、/start-learning、/course-guide等/skill-name形式。 - 其他兼容宿主：使用自然语言，例如
Use learn to teach this lesson.
绝不把斜杠命令说成通用语法。宿主未知时，使用自然语言。
路由表
课程唯一事实来源是仓库 README 的 Contents 部分：每个阶段都有表格，列出每课的编号、标题、类型（Build/Learn）、语言和目录路径。仓库已克隆时读取本地 README.md；否则获取：
https://raw.githubusercontent.com/fancyboi999/ai-engineering-from-scratch-zh/main/README.md
术语定义在 glossary/terms.md（遵循相同规则：本地优先，raw 兜底）。
Claude certification 路线是独立、AI-native 的课程。对于 CCAO-F、CCDV-F、CCAR-F、CCAR-P、Claude certification、备考、诊断或模拟题，路由至 claude-certification。其来源是 certifications/claude/program.json、certifications/claude/tracks/*.json 和 certifications/claude/GETTING_STARTED.md。
Model Context Protocol (MCP) 有专门路线。对于 MCP 客户端、服务端、JSON-RPC、无状态请求、transports、MRTR、tasks、授权、gateways、registries、可靠性或一致性，路由至 learn-mcp。其唯一事实来源是 learning-paths/model-context-protocol.json；顺序遵循 manifest，而不是数值上的下一课；状态写在 MCP-LEARNING.md。
Agent Skills 也有独立的专门路线。对于 Agent Skills、SKILL.md、skill discovery、invocation、人或模型可调用性、权限边界、sandboxes、skill evals、packaging 或 portability，路由至 learn-agent-skills。其唯一事实来源是 learning-paths/agent-skills.json。这条路线有顺序固定的五节课，因此是通常 1-3 节课限制的例外。tool poisoning 是第 26 课的知识预检；第 15 课是路线外可选复习。
如何路由
- 理解请求。请求有六种形态：
- 主题（“attention”“diffusion models 怎么工作”）→ 找教授它的课程。
- 困难（“我的 agent 无限循环”“loss 变成 NaN”）→ 找能诊断问题的课程。bug 应路由到背后的概念，不能只路由工具：NaN loss 应指向 loss-functions 和 numerical-stability 课程，而不是只给 framework FAQ。
- 元问题（“接下来该做什么”“我准备好第 7 阶段了吗”）→ 若当前目录有
LEARNING.md，读取它并按实际进度回答；否则按宿主调用契约推荐start-learning。 - 认证（“帮我准备 CCDV-F”“Claude architect 模拟题”）→ 直接路由至
claude-certification。认证状态不要混入LEARNING.md；该 tutor 使用CLAUDE-CERTIFICATION.md。 - Model Context Protocol (MCP)（“教我 MCP”“构建生产级 MCP server”）→ 直接路由至
learn-mcp。不要把学习者放进通用阶段序列；使用其 manifest 中有序的 17 节课。 - Agent Skills（“教我 skills”“skill 如何在 sandbox 中运行”）→ 直接路由至
learn-agent-skills。不要在第 22 课后将学习者送去数值上的第 23 课；manifest 顺序为 22、24、25、26、27，进度写在AGENT-SKILLS-LEARNING.md。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 68 lines · 136 tokens per session scan A a0b3deebab6b
course-guide is a skill published in the GitHub repository fancyboi999/ai-engineering-from-scratch-zh (1,048 stars, last pushed yesterday), licensed MIT. It adds 136 tokens to every session and 1,716 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
ai-engineering-curriculum
Use when structured AI engineering curriculum — 382 skills + 99 prompts across 20 phases covering ML, deep learning, LLMs, agents, and production systems. Use when learning AI, building AI skills,.
thinking-prompts
A collection of 12 reusable thinking frameworks in English and Chinese for clarifying questions, learning unfamiliar ideas, solving problems, making decisions, and considering personal direction.
playwright
Use when the task requires capturing or automating a real browser from the terminal.
skill-release-gate
Evaluate an Agent Skill bundle for structural integrity, trigger quality, artifact improvement, script correctness, safety, installed-tree integrity, and target-host portability before release.
migration-review
Review database migration files when a change adds or modifies paths under migrations/. Use it before merge to collect forward, rollback, locking, and data-safety evidence.
skill-safety-reviewer
Review a skill-requested filesystem, command, network, secret, or destructive action against an explicit sandbox policy without executing it.