ai-engineering-from-scratch-zh: Skill for Claude Code

.claude/skills/isometric-explainer/SKILL.md

isometric-explainer is a skill for Claude Code from fancyboi999/ai-engineering-from-scratch-zh. It costs 88 tokens per session (1,707 once invoked), scanned A, original, MIT.

A method for building an interactive isometric diagram, where each station represents one step in a process. A tested state model controls the animation, values, labels, and failure states.

In plain words
What is it for?
Use it to explain ordered systems such as queues, caches, retries, pipelines, and loops through controls for running, stepping, disabling, repairing, and resetting.
Why use it?
A static explanation may not show how a process changes over time or what breaks when a part is disabled. This approach keeps the visual display consistent with a deterministic model.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is fancyboi999/ai-engineering-from-scratch-zh's own configuration. It tells Claude Code how to work on ai-engineering-from-scratch-zh itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-engineering-from-scratch-zh configures →

About the project

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.

fancyboi999/ai-engineering-from-scratch-zh · 1,276 stars · on GitHub · aieng-zh.cn

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/fancyboi999/ai-engineering-from-scratch-zh/main/.claude/skills/isometric-explainer/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/fancyboi999/ai-engineering-from-scratch-zh

Made for: Claude Code.

Wrote 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.

agentmods badge for isometric-explainer

README.md
[![agentmods](https://agentmods.dev/badge/skills/fancyboi999/ai-engineering-from-scratch-zh/isometric-explainer/github.svg)](https://agentmods.dev/skills/fancyboi999/ai-engineering-from-scratch-zh/isometric-explainer)
Your own site
<a href="https://agentmods.dev/skills/fancyboi999/ai-engineering-from-scratch-zh/isometric-explainer"><img src="https://agentmods.dev/badge/skills/fancyboi999/ai-engineering-from-scratch-zh/isometric-explainer/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.

agentmods 80×15 button for isometric-explainer

Your own site · 80×15
<a href="https://agentmods.dev/skills/fancyboi999/ai-engineering-from-scratch-zh/isometric-explainer"><img src="https://agentmods.dev/badge/skills/fancyboi999/ai-engineering-from-scratch-zh/isometric-explainer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,707 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00088 $0.01707
Opus 5.5 $0.00035 $0.00683
Sonnet 5.5 $0.00018 $0.00341
Haiku 4.5 $0.00009 $0.00171

Measured 5d ago against content hash 160d5c650563, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

isometric-explainer 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.

The scan reads SKILL.md. This mod also ships 7 executable files (kit/iso-kit.mjs, kit/lathe.mjs, kit/tube.mjs, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.claude/skills/isometric-explainer/SKILL.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

等距机器讲解

制作单页交互图:工作台上的实体等距机器,每个工位对应流程一步。例如请求卡随车架移动、探针下降、压机给卡盖章。纯状态模型决定每个动作,使画面、数值与文字一致。templates 提供可运行起点,kit 提供几何库。

适用情况

  • 概念是带工位、顺序和失败模式的流程,例如循环、流水线、缓存、队列、重试策略。
  • 读者能禁用一个部件并观察故障。
  • 图表是页面主体。

使用其他方式的情况

  • 静态图即可解释,或概念没有顺序和状态变化:制作平面静态 SVG。
  • 课程或 README 中的小图:使用 blueprint-figure。
  • 无法写出确定性行为模型:先查明行为,不动画猜测。
  • 超过 150 个部件且未获用户批准:先确认规模。

方法

  1. 构思机器,写一句“X 经过 Y 移动,这个运动表示 Z”。写不清就换机器,见 references/concept.md。

  2. 绘图前按清单统计部件,选择规模。

    规模 部件数 确认
    图表 40 至 80 无需
    主图 80 至 150 无需
    更大 超过 150 先获得用户批准
  3. 先写纯确定性 model.mjs,无 DOM、无时钟。simulate(config) 返回事件和汇总。几何前先测试,见 references/state-model.md。

  4. 每个概念映射到工位,表中写工位、铭牌概念名、作用、缺少时的故障。

  5. 写部件清单,含装配组、世界尺寸、色调、是否运动,再写几何。

  6. 设定统一等距相机,世界单位,仰角 30 度,方位角让工作面朝向读者。投影同时容纳装配与展开姿态。

  7. 静态几何只构建一次,每部件一个有深度键的 SVG 组,运动部件加 data-live,见 references/geometry.md。

  8. 通过 transform 平移部件。只有形状改变(例如伸长杆)才重建路径。

  9. 按深度键加当前偏移深度,从后往前绘制。顺序变化时才重排 DOM。

  10. 只用一个强调色标出活动部件与铭牌,其他部分用四级灰度和四种线调。

  11. 控件改变真实 simulate 运行,运行、单步、禁用、修复、重置与开关都生效,配置写入 URL。见 references/live.md。

  12. 在真实浏览器验证桌面和手机、明暗主题,补 4 倍近景、线端检查、零控制台错误的场景遍历与接触表。见 references/verify.md。

规则

真实性:

  • 状态模型是唯一真相。运动、读数、轨迹、结果文字都来自事件。
  • 同配置 simulate 返回同样事件,测试覆盖全部配置组合。
  • 不伪装真实模型、服务或指标。脚本部分明确标为固定脚本。
  • 有模拟时间时,页面必须以“这是模拟。”开头说明时间为固定成本,不是实测。
  • 使用真实算术,测试断言页面打印的精确数值。

几何:

  • 坐标使用世界单位,只有投影出现像素。
  • 仰角 30 度,全页一个固定方位角,参考页为 60 度。
  • 实体用四级阴影和轮廓,线使用 hi、mid、lo、faint。
  • 线端接到实体或另一条线。有意悬空时标 data-free=start、end 或空值。
  • 每工位有概念铭牌,例如 CACHE、VERIFIER,中文页面对应翻译。
  • 放在其他部件上的部件加深度偏置,绘制在支撑物之后。

运动:

  • 运动部件只改 transform。变形路径尽量复用缓存结果。
  • 单节拍 0.1 至 1.3 秒,位移越远用时越长。
  • 展开弹簧刚度 64、阻尼 14.2,装配组错开 0.04 秒。
  • 单帧步长限制为 1/20 秒,慢帧不会跳过节拍。
  • 减少动态效果时运行加速 40 倍,展开立即到终态。
  • 舞台离屏或没有运动时停止动画循环。

页面:

  • 桌面工作台一屏显示:工具栏、舞台、读数放在 100svh 中。
  • 手机纵向堆叠,不横向滚动。
  • 按钮至少高 44px。舞台可聚焦,支持运行、单步、展开、禁用、修复键。
  • SVG 有 role=img,aria-label 说明全部工位。
  • aria-live=polite 在运行结束时播报结果。

完成前检查

  • 页面或构建笔记写出一句话机器说明。
  • 部件数符合已确认规模。
  • 模型测试通过,覆盖所有配置。
  • 重建页面没有差异。
  • 每个配置控件调用 simulate 并更新 URL。
  • 查询参数恢复同一配置。
  • 任一时刻只有一个强调色,跟随活动部件。
  • 手机明暗主题中铭牌都可读。
  • 线端检查零悬空端点。
  • 所有配置运行到底,控制台零错误。
  • 桌面与手机明暗截图无裁剪、无横向滚动。
  • 展开姿态不超舞台。
  • 页面有模拟说明。

Read the full file on GitHub · 113 lines

Changes

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.

  1. 5d ago First seen · 113 lines · 88 tokens per session scan A 160d5c650563

Subscribe to this mod's changes

isometric-explainer 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 88 tokens to every session and 1,707 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.