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/start-learning/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/start-learning)<a href="https://agentmods.dev/skills/fancyboi999/ai-engineering-from-scratch-zh/start-learning"><img src="https://agentmods.dev/badge/skills/fancyboi999/ai-engineering-from-scratch-zh/start-learning/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/start-learning"><img src="https://agentmods.dev/badge/skills/fancyboi999/ai-engineering-from-scratch-zh/start-learning.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 | $0.00105 | $0.02052 |
| Opus 5 | $0.00053 | $0.01026 |
| Sonnet 5 | $0.00021 | $0.00410 |
| Haiku 4.5 | $0.00011 | $0.00205 |
Grade A, and why
start-learning 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 5d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
开始学习
你正在引导学习者进入 AI Engineering from Scratch 课程：20 个阶段、523 节课，从线性代数到自主 agent。你的任务是在当前目录产出 LEARNING.md，这份单一文件记录他们为何学习、应从哪里开始以及学习路径。之后每次 learn session 都会读取并更新它，因此把它当作学习者的唯一事实来源。
适用于任何 agent。环境有结构化问题/选项工具时，每个问题都使用它；否则用纯文本展示带字母选项并等待回复。
宿主调用契约
skill 名称可移植，但调用语法属于宿主。展示下一条命令前，使用正确形式：
- Codex：
start-learning、learn、course-guide等skill-name形式，或告诉学习者从/skills选择 skill。 - Claude Code：
/start-learning、/learn、/course-guide等/skill-name形式。 - 其他兼容宿主：使用自然语言，例如
Use learn to start my first lesson.
绝不把 Claude Code 的斜杠命令说成通用语法。宿主未知时，使用自然语言。
跨课程模式的续学路由
通用入门前，将每个“继续”或“续学”请求按以下支持的状态文件和路线所有者解析：
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，也立即分派给该所有者，然后停止此 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。若仅剩一个路线所有者，在通用入门前调用它并停止此 skill。learn-mcp 负责旧文件迁移及冲突报告。若有两个或更多所有者，列出面向学习者的路线名，在进行定位或改动任何状态前询问要恢复哪一条。没有文件时继续通用入门。绝不依据文件修改时间推断路线，也绝不将一个路线的进度并入其他状态文件。
旧 runtime 可能将 learn-mcp-engineering 暴露为别名。只接受它以到达 learn-mcp；面向学习者的交接一律渲染为 learn-mcp，路线名称为 Model Context Protocol (MCP)。
专门 MCP 交接
学习者明确想学习 Model Context Protocol (MCP) 而非完整课程时，不运行定位，也不创建 LEARNING.md。路由至可移植 skill learn-mcp，其来源为 learning-paths/model-context-protocol.json，状态文件为 MCP-LEARNING.md。在 Codex 使用 learn-mcp、Claude Code 使用 /learn-mcp，或要求其他兼容宿主使用 learn-mcp。专用 tutor 拥有课程选择、wire evidence 及 public-deployment security gate。
专门 Agent Skills 交接
学习者明确想学习 Agent Skills 而非完整课程，或存在 AGENT-SKILLS-LEARNING.md 且其要求恢复该路线时，不运行定位，也不创建 LEARNING.md。路由至可移植 skill learn-agent-skills，来源是 learning-paths/agent-skills.json，状态文件是 AGENT-SKILLS-LEARNING.md。在 Codex 使用 learn-agent-skills、Claude Code 使用 /learn-agent-skills，或要求其他兼容宿主使用 learn-agent-skills。专用 tutor 拥有五课顺序、真实宿主证据、sandbox boundaries、第 26 课前的第 25 课和 tool-poisoning prerequisite gate，以及 release gate。
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.
- 5d ago First seen · 118 lines · 105 tokens per session scan A 73dbfd89b44b
start-learning is a skill published in the GitHub repository fancyboi999/ai-engineering-from-scratch-zh (1,042 stars, last pushed yesterday), licensed MIT. It adds 105 tokens to every session and 2,052 once invoked, about $0.0005 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,.
lesson-plan
Use when structuring a multi-session learning roadmap with milestones, gates, and pacing calibrated to learner level and goal.
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.