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/check-understanding/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/check-understanding)<a href="https://agentmods.dev/skills/fancyboi999/ai-engineering-from-scratch-zh/check-understanding"><img src="https://agentmods.dev/badge/skills/fancyboi999/ai-engineering-from-scratch-zh/check-understanding/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/check-understanding"><img src="https://agentmods.dev/badge/skills/fancyboi999/ai-engineering-from-scratch-zh/check-understanding.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 | $0.00071 | $0.02224 |
| Opus 5 | $0.00036 | $0.01112 |
| Sonnet 5 | $0.00014 | $0.00445 |
| Haiku 4.5 | $0.00007 | $0.00222 |
Grade A, and why
check-understanding 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 8d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
检查理解程度
测试学习者对 AI Engineering from Scratch 已完成阶段的掌握情况。
触发方式
当用户说出类似下面的话时启用此 skill：
/check-understanding 3或/check-understanding deep-learning- “测验一下我对第 2 阶段的掌握情况”
- “测试第 1 阶段”
- “检查我对 transformer 的理解”
- “我掌握第 3 阶段了吗”
- “我准备好进入下一阶段了吗”
输入
接受阶段编号（0-19）或阶段名称作为参数。如果没有参数，列出全部 20 个阶段，并询问用户希望测试哪一阶段。
阶段映射
将参数映射到 phases/ 下正确的阶段目录：
| 输入 | 目录 | 阶段名称 |
|---|---|---|
| 0, setup, tooling | 00-setup-and-tooling |
环境设置与工具 |
| 1, math, math-foundations | 01-math-foundations |
数学基础 |
| 2, ml, ml-fundamentals | 02-ml-fundamentals |
机器学习基础 |
| 3, deep-learning, dl | 03-deep-learning-core |
深度学习核心 |
| 4, cv, computer-vision, vision | 04-computer-vision |
计算机视觉 |
| 5, nlp | 05-nlp-foundations-to-advanced |
NLP：从基础到进阶 |
| 6, speech, audio | 06-speech-and-audio |
语音与音频 |
| 7, transformers | 07-transformers-deep-dive |
Transformer 深入剖析 |
| 8, generative, gen-ai, genai | 08-generative-ai |
生成式 AI |
| 9, rl, reinforcement-learning | 09-reinforcement-learning |
强化学习 |
| 10, llms, llm, llms-from-scratch | 10-llms-from-scratch |
从零构建 LLM |
| 11, llm-engineering, llm-eng | 11-llm-engineering |
LLM 工程 |
| 12, multimodal | 12-multimodal-ai |
多模态 AI |
| 13, tools, protocols, mcp | 13-tools-and-protocols |
工具与协议 |
| 14, agents, agent-engineering | 14-agent-engineering |
Agent 工程 |
| 15, autonomous | 15-autonomous-systems |
自主系统 |
| 16, multi-agent, swarms | 16-multi-agent-and-swarms |
多 Agent 与群体 |
| 17, infrastructure, production, infra | 17-infrastructure-and-production |
基础设施与生产环境 |
| 18, ethics, safety, alignment | 18-ethics-safety-alignment |
伦理、安全与对齐 |
| 19, capstone, projects | 19-capstone-projects |
综合项目 |
流程
第 1 步：解析阶段
解析参数。若为数字，验证它是否在 0 到 19（含）之间。数字超出范围时，告诉用户：阶段 [N] 不存在。有效阶段为 0-19。然后展示完整列表供其选择。若为名称或关键词，在上方阶段映射中查找。关键词不匹配任何条目时，告诉用户：未知阶段“[keyword]”。请从下面列表中选择：，并展示全部 20 个阶段。未提供参数时，要求用户从完整列表中选择。
第 2 步：读取阶段内容
如果仓库已克隆（当前目录或其父目录存在 phases/），找出 phases/<phase-dir>/ 下全部课程目录并读取每课的 docs/zh.md。如果未克隆，从 README 的 Contents 部分获取该阶段课程列表（获取 https://raw.githubusercontent.com/fancyboi999/ai-engineering-from-scratch-zh/main/README.md），再从同一 raw base URL 获取每课的 docs/zh.md。这些文档就是出题依据。
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.
- 8d ago Changed · +6 lines · +27 tokens per session f7c341b72ca0
- 13d ago First seen · 159 lines · 44 tokens per session scan A fa402e64e58d
check-understanding is a skill published in the GitHub repository fancyboi999/ai-engineering-from-scratch-zh (1,056 stars, last pushed 4d ago), licensed MIT. It adds 71 tokens to every session and 2,224 once invoked, about $0.0004 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
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.
eli5
Explain concepts in very simple terms suitable for a five-year-old.