AI Engineering from Scratch is a free, open-source curriculum that teaches people to build AI systems through lessons and reusable artifacts such as prompts, skills, agents, and MCP servers. It is for learners who want practical foundations or want to create AI applications, and the catalogue skills support parts of that curriculum.
Borrowing it
Nothing to install: this file belongs to rohitg00/ai-engineering-from-scratch. 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/rohitg00/ai-engineering-from-scratch/main/.claude/skills/write-manual/SKILL.mdgit clone --depth 1 https://github.com/rohitg00/ai-engineering-from-scratchWrote 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/rohitg00/ai-engineering-from-scratch/write-manual)<a href="https://agentmods.dev/skills/rohitg00/ai-engineering-from-scratch/write-manual"><img src="https://agentmods.dev/badge/skills/rohitg00/ai-engineering-from-scratch/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/rohitg00/ai-engineering-from-scratch/write-manual"><img src="https://agentmods.dev/badge/skills/rohitg00/ai-engineering-from-scratch/write-manual.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk 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 | $0.00101 | $0.03389 |
| Opus 5.5 | $0.00040 | $0.01356 |
| Sonnet 5.5 | $0.00020 | $0.00678 |
| Haiku 4.5 | $0.00010 | $0.00339 |
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 14d 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.
Write a manual
A manual explains one subject, such as a protocol, a file format, or a runtime, at one exact version. A lesson teaches a concept and moves on. A manual stays with one system until the reader can predict what it does in a case the manual never showed.
This skill gives the full method. It covers research, ranked sources, and a register of conflicts between sources. It also covers an offline capture kit, a fixed section shape, prose limits, and an audit that must report TOTAL 0. It works in any repository. Inside the AI Engineering from Scratch repo, the tooling already exists, and manuals/a2a-101/ is the worked example.
When to use
- The reader must predict the behavior of one system, at one version, in cases you did not show.
- The subject has a specification, a schema, or a source tree that you can pin to a commit.
- You can run the subject, or a faithful stand-in, offline and record its requests and responses.
- The result is 60 to 100 pages with figures, and other people will maintain it.
When not to use
- You teach a general concept, such as attention or retrieval. Write a lesson instead.
- The subject has no version to pin, or changes every week.
- You cannot run the subject and cannot record its output. A manual without captures is an essay.
- You want a short how-to. A manual of fewer than about 15 sections does not need this shape.
Size of a 101 manual
| Item | Target |
|---|---|
| pages | 60 to 100 |
| parts | 6 to 8, plus one reference part |
| sections | about 25 |
| figures | 30 to 40 |
outcomes in manual.json |
at least 3 |
| takeaways per section | exactly 1 block, with at least 2 items |
The worked example has 7 parts, 28 sections, 7 reference sections, and 31 figures.
Method
- Pin the subject. Record the version, source URL, commit, release date, and verified date.
- Rank the sources. List them in authority order: schema or proto, specification, project docs, reference SDK, capture kit.
- Vendor what the license allows. Copy each quotable source unchanged into
research/sources/, with its license file beside it. - Write the fact brief. Index every rule you will use by section and line number, in
research/. See references/research-and-sources.md. - Open the conflict register. Give each disagreement between two sources an id (
D1,D2, ...) as you find it. - Build the capture kit. Drive the subject offline and write deterministic files to
capture/out/. See references/capture-kit.md. - Plan the contents from the specification. Name each section after one thing the reader can find in the spec.
- Write
manual.json. Fill the pin, outcomes, palette, ranked sources, quote sources, capture commands, and parts. See references/manual-json.md. - Write the front matter. Title it "How to read this manual" and follow the order in "Front matter" below.
- Write one section at a time. Use the section shape below. Cut every listing from a capture file.
- Draw each figure from a capture. Follow the figure must-haves below and the sibling
blueprint-figureskill. - Build and audit. Fix every finding until the audit prints
TOTAL 0. See references/audit.md. - Size commits by judgment. A section with its figures and the captures it adds is a good unit.
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.
- 14d ago Changed f0c3f2e9b360
- 24d ago First seen · 227 lines · 101 tokens per session scan A ff3f5df91da4
write-manual is a skill published in the GitHub repository rohitg00/ai-engineering-from-scratch (77,007 stars, last pushed yesterday), licensed MIT. It adds 101 tokens to every session and 3,389 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 2026-10-14.
write-manual compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| write-manualrohitg00/ai-engineering-from-scratch | Skill | 77k | yesterday | MIT | A | 101 | Claude Code |
| Documentation Gap FinderNotysoty/openagentskills | Skill | 9 | 2mo ago | MIT | A | 24 | Claude Code, Codex |
| documentation-writerasgarovf/locusai | Skill | 23 | 8mo ago | MIT | A | 31 | Claude Code |
| clear-writingwpank/ai | Skill | 12 | 8mo ago | none | A | 56 | Claude Code, Codex |
| cocotraceSnowflake-Labs/cocoplus | Skill | 727 | 2d ago | MIT | A | 22 | Claude Code |
| compliance-testingproffesor-for-testing/agentic-qe | Skill | 525 | yesterday | MIT | A | 43 | Claude Code |
| skill-contract-reviewerfancyboi999/ai-engineering-from-scratch-zh | Skill | 1.3k | 3d ago | MIT | A | 24 | Claude Code, Codex |