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/find-your-level/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/find-your-level)<a href="https://agentmods.dev/skills/fancyboi999/ai-engineering-from-scratch-zh/find-your-level"><img src="https://agentmods.dev/badge/skills/fancyboi999/ai-engineering-from-scratch-zh/find-your-level/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/find-your-level"><img src="https://agentmods.dev/badge/skills/fancyboi999/ai-engineering-from-scratch-zh/find-your-level.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 | $0.00115 | $0.02178 |
| Opus 5 | $0.00057 | $0.01089 |
| Sonnet 5 | $0.00023 | $0.00436 |
| Haiku 4.5 | $0.00012 | $0.00218 |
Grade A, and why
find-your-level 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 7d 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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
找到你的水平
你正在为 AI Engineering from Scratch 课程（20 个阶段、523 节课）进行分级测验。你的任务是找出学习者应从哪里开始，让他们跳过已掌握的材料，恰好从有挑战的地方起步。适用于任何 agent。
测验结构
共有 5 个知识领域，每个领域 2 道题，共 10 题。每轮展示 2 道题（每个领域一轮）。学习者答完一轮的两题后，为该领域评分再进入下一轮。
评分
每题 1 分（0 = 错误或空白，1 = 正确）。每个领域得分 0-2。总分范围为 0-10。
进行测验
先简短问候学习者，随即进入第 1 轮。环境有结构化问题/选项工具时，每题都使用它；否则用纯文本展示带字母的选项并等待回复。每轮后，先告知该领域得分（例如“数学与统计：2/2”）再进入下一轮。说明保持简短。所有答案解释都留到最后。
答案隔离
答案键特意存放在本测验正文之外的 references/answer-key.md。学习者提交当前轮两题答案之前，不要读取该引用。之后只读取当前轮的答案键、进行评分，并在五轮全部完成前保持解释私密。不要预加载后续轮次。
回复格式示例中绝不放入真实答案字母、可能答案或答案分布。纯文本时必须严格使用中性提示：请按此格式回复：Q1: <letter>, Q2: <letter>。替换当前题号，但两个值均保留为 <letter>。
第 1 轮 —— 数学与统计
Q1. 有两个向量，a = [1, 2, 3] 和 b = [4, 5, 6]。它们的点积是多少？
- A) 32
- B) 21
- C) 15
- D) 27
Q2. 一枚公平硬币抛掷 3 次。恰好出现 2 次正面的概率是多少？
- A) 1/4
- B) 1/2
- C) 1/8
- D) 3/8
第 2 轮 —— 经典机器学习
Q3. 在一个含 90% 负样本和 10% 正样本的分类任务中，模型把所有样本都预测为负类。它的准确率是多少？
- A) 50%
- B) 90%
- C) 10%
- D) 0%
Q4. 下列哪一项是 Random Forest 的超参数？
- A) 学得的划分阈值
- B) 叶节点预测值
- C) 树的数量
- D) 每个节点的 Gini impurity
第 3 轮 —— 深度学习
Q5. 在反向传播中，链式法则计算什么？
- A) 每个可训练权重的损失梯度
- B) 当前优化器的最佳学习率
- C) 网络所需层数的精确值
- D) 每个训练步骤使用的 batch size
Q6. ResNet 中的 residual connections（skip connections）主要解决什么问题？
- A) 小型训练数据集上的泛化不佳
- B) 从持久化存储加载 batch 很慢
- C) 模型推理时 activation memory 很高
- D) 在极深网络中的 gradient flow 太弱
第 4 轮 —— NLP 与 Transformer
Q7. 在 Transformer 架构中，attention mechanism 在什么之间计算？
- A) 像素和标签
- B) 仅 Encoder 和 Decoder
- C) Queries、Keys 和 Values
- D) 仅 Embeddings 和 positions
Q8. 使用 LoRA（Low-Rank Adaptation）微调大型语言模型的主要益处是什么？
- A) 从全新随机初始化开始，重新训练基础模型中的每一个参数
- B) 冻结基础模型权重，只训练低秩 adapters
- C) 无需带标签的示例或任务专属训练数据
- D) 复制模型层以提高适应容量
第 5 轮 —— 应用 AI
Q9. 在 RAG（Retrieval-Augmented Generation）系统中，LLM 生成答案之前会发生什么？
- A) 检索相关文档并加入模型 prompt
- B) 针对用户当前问题完整重新训练模型
- C) 用户在每次模型请求前选择所有上下文段落
- D) 模型只搜索预训练参数值
Q10. 在多 agent 系统中，“coordinator” 或 “orchestrator” agent 的首要职责是什么？
- A) 用一个通用模型替换所有专用 agent
- B) 分派任务、路由消息并协调其他 agent
- C) 最大化每次 agent 交互的 token 用量
- D) 为系统故障准备一份完全相同的备用模型
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago Changed · -39 lines · +44 tokens per session dc74b8005173
- 11d ago First seen · 229 lines · 71 tokens per session scan A 3bd5d7f529e6
find-your-level is a skill published in the GitHub repository fancyboi999/ai-engineering-from-scratch-zh (1,055 stars, last pushed 3d ago), licensed MIT. It adds 115 tokens to every session and 2,178 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
course-builder
Use when turning "I want to teach X" into a defensible course skeleton — measurable outcomes (Bloom + ABCD), assessment that proves each one, sequenced modules, and an outcome×module×assessment matrix — for a workshop, bootcamp, cohort or onboarding track. NOT making one concept land emotionally with story or analogy…
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.
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.