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/write-manual/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/write-manual)<a href="https://agentmods.dev/skills/fancyboi999/ai-engineering-from-scratch-zh/write-manual"><img src="https://agentmods.dev/badge/skills/fancyboi999/ai-engineering-from-scratch-zh/write-manual/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/write-manual"><img src="https://agentmods.dev/badge/skills/fancyboi999/ai-engineering-from-scratch-zh/write-manual.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.02997 |
| Opus 5.5 | $0.00042 | $0.01199 |
| Sonnet 5.5 | $0.00021 | $0.00599 |
| Haiku 4.5 | $0.00011 | $0.00300 |
Grade A, and why
write-manual 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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
编写手册
手册深入解释协议、文件格式或运行时等主题的一个精确版本。课程讲完概念就继续，手册要让读者能预测未展示场景下的系统行为。
本技能包括研究、来源排序、冲突登记、离线运行记录、固定章节结构、写作限制，以及必须输出 TOTAL 0 的审计。适用于任意仓库。课程仓库已有工具，manuals/a2a-101/ 是完整示例。
适用情况
- 读者需要预测某系统固定版本在未展示场景下的行为。
- 主题有可固定到提交的规范、schema 或源码树。
- 能离线运行主题或忠实替代实现，记录请求与响应。
- 产物为 60 至 100 页，包含图表，且后续由其他人维护。
使用其他方式的情况
- 注意力或检索等通用概念：写课程。
- 无版本可固定，或每周变化：先明确稳定范围。
- 无法运行且无法记录输出：只能交付文章，不能声称有运行记录的手册。
- 简短操作指南或不足约十五节：无需这套完整结构。
入门手册规模
| 项目 | 目标 |
|---|---|
| 页数 | 60 至 100 |
| 篇数 | 6 至 8，加一篇参考 |
| 节数 | 约 25 |
| 图数 | 30 至 40 |
| manual.json 学习成果 | 至少 3 |
| 每节要点 | 恰好一个块，至少两项 |
完整示例有七篇、二十八节、七个参考节、三十一张图。
方法
- **固定主题。**记录版本、来源 URL、提交、发布日期、核验日期。
- **来源排序。**按 schema/proto、规范、项目文档、参考 SDK、运行记录排序。
- **按许可归档。**原样复制允许引用的来源到 research/sources/，旁边保留许可文件。
- **事实简报。**在 research/ 按章节和行号索引将使用的每条规则，见 研究与来源。
- **冲突登记。**发现来源分歧即分配 D1、D2 等 ID。
- **构建记录工具。**离线运行并把确定性文件写到 capture/out/，见 运行记录。
- **按规范规划目录。**每节以规范中可查的一项命名。
- **编写 manual.json。**填写版本、成果、配色、来源、引文来源、运行命令、篇章，见 声明文件。
- **前言。**标题为“如何阅读本手册”，按下文顺序写。
- **逐节编写。**遵循固定结构，所有 listing 都从运行记录截取。
- **按记录绘图。**遵守下方要求与 blueprint-figure。
- **构建与审计。**修复全部问题，直到 TOTAL 0，见 审计。
- **逐节提交。**每提交包含该节、图表与新增运行记录。已授权批量同步时可按可审查逻辑批次提交。
按规范规划目录
先用规范中的名称建目录，再决定每篇证明什么。
- 前言：front.md，标题“如何阅读本手册”。
- 第一篇：用两节说明主题标准化什么，以及一次完整运行交互。
- 中间各篇：每层一篇，例如发现、数据模型、操作、绑定、安全、扩展。
- 最后实现篇：构建客户端和服务端，用官方一致性工具测试，并解释从上一版本迁移。
- 参考篇：方法表、对象、状态、错误、术语、来源、冲突、图索引。
每节以规范中的对象、操作、绑定、头、错误或扩展命名。“CancelTask 与终止状态”具体可查，“状态机”过于泛化。通用概念放在拥有该概念的对象章节中。
前言
front.md 按顺序包含：
- 读者是谁，读完能做什么。
- 编写方法和来源权威排序表。
- 运行记录工具。
- 引文、示例截取、ID 缩写约定。
- 可离线执行的首次运行。
- 篇章顺序，以空 parts 块声明。
- 图表颜色，以空 palette 块声明。
- 图 0.1，解释本手册箭头与颜色语法。
章节结构
每节顺序如下。参考节和前言有中心论点、来源行，但不需要成果句或 takeaways。
- 首行一个 # 标题，使用规范术语。
- 标题下直接放 > 中心论点，一句，英文最多 30 词。
- 开头从读者经历过的具体场景切入。
- 前两段内包含“读完本节，你可以……”成果句。
- 正文由二级标题、以粗体术语开头的定义、图、示例、规则、表格构成。
- 恰好一个 takeaways 块，至少两个行动项。
- 最后段以 Sources: 开头，列出编写时使用的全部文件。
完整模板见 章节模板。
What ships with it
6 files 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.
- 5d ago First seen · 227 lines · 105 tokens per session scan A 40e2620592ac
write-manual is a skill published in the GitHub repository fancyboi999/ai-engineering-from-scratch-zh (1,276 stars, last pushed 4d ago), licensed MIT. It adds 105 tokens to every session and 2,997 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-20.
Other skills, from other repositories
technical-writing
Use when drafting or revising internal technical design docs, review notes, architecture writeups, or sharing posts in Chinese, especially when the tone should stay evidence-backed, calm, and suitable for peers or leaders rather than marketing or literary writing.
Documentation Gap Finder
Audits a codebase or docs folder and lists everything that is undocumented, outdated, or unclear.
documentation-writer
Write clear technical documentation including READMEs, API docs, architecture guides, and inline documentation. Use when creating or improving project documentation.
clear-writing
Write clear, concise prose for humans — documentation, READMEs, API docs, commit messages, error messages, UI text, reports, and explanations. Combines Strunk's rules for clearer prose with technical documentation patterns, structure templates, and review checklists.
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.
skill-invocation-router
Design and test explicit human, implicit model or agent, programmatic application, bounded skill-composition, and harness activation policies for an Agent Skill catalog.