Skip to main content
skill Claude Code CX Codex Cursor GitHub Copilot

isometric-explainer — Claude Code skill: what it does, how to install

Builds an interactive single-page isometric machine where mechanical stations represent process steps driven by a deterministic state model.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add rohitg00/ai-engineering-from-scratch --skill isometric-explainer -a claude-code
Open on GitHub

What isometric-explainer does

The skill constructs a single-page interactive figure showing an invented machine on a bench. Every station stands for a discrete step in a workflow, like a cache lookup or a retry loop. Instead of freehand animations, a pure state model in model.mjs executes first without DOM access, providing the single source of truth for motion, numbers, and labels.

Geometry relies on world coordinates and an isometric camera locked at 30 degrees elevation. Solid parts use three flat tones alongside heavy ink silhouettes from kit/ink.mjs. Moving parts update purely via transform, while headless browser sweeps verify both themes, phone widths, and desktop viewports.

The model must stay strictly deterministic; animating assumptions without exact arithmetic is prohibited. If an assembly exceeds 150 parts, the skill requires explicit user approval before drafting geometry.

What it helps with

  • visualise sequential pipelines and retry loops as mechanical stations
  • tie interactive SVG animation directly to a verified deterministic state model
  • simulate failure modes and state changes with live browser controls
  • generate tested isometric diagrams with responsive layouts and accessible labels

Example prompts for the agent

  • Build an isometric explainer for our background task queue pipeline.
  • Explain this retry policy as a machine on a bench.
  • Show how it works inside with an interactive isometric figure.

How to install isometric-explainer

1Skills CLI (Vercel)

npx skills add rohitg00/ai-engineering-from-scratch --skill isometric-explainer -a claude-code

2Manually: put the files in place

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

Copy the whole skill folder; for one project use .claude/skills/isometric-explainer/

From the same set13

The whole set →
find-your-level rohitg00 A 10-question AI/ML quiz that tells you which phase of the AI Engineering from Scratch curriculum to start from. Claude Code CX Codex Cursor +1 4,500installs start-learning rohitg00 It onboards learners into the AI Engineering from Scratch curriculum, runs a placement quiz, and creates LEARNING.md as a persistent study plan. Claude Code CX Codex Cursor +1 4,500installs learn rohitg00 Walks you through the AI Engineering from Scratch curriculum: pulls the next lesson, teaches it section by section in the terminal, quizzes you, and logs progress. Claude Code CX Codex Cursor +1 4,200installs course-guide rohitg00 Finds AI Engineering from Scratch lessons for a topic, question, or bug and suggests a next action. Use it when you need a course route for what you are learning. Claude Code CX Codex Cursor +1 4,100installs claude-certification rohitg00 Walks you through one of four Claude certification tracks: teaches the lesson, runs the lab, checks your artifacts. Useful when you are preparing for an exam and want a tutor instead of a reading list. Claude Code CX Codex Cursor +1 3,300installs learn-mcp rohitg00 An interactive tutor for the Model Context Protocol. Use it to study MCP clients, servers, transports, security, and conformance step by step. Claude Code CX Codex Cursor +1 2,700installs mcpa-certification rohitg00 AI tutor for MCPA certification prep in AI Engineering from Scratch. It guides through MCP lessons, runs validation scripts, and tracks progress in a local file. Claude Code CX Codex Cursor +1 1,500installs build-project rohitg00 A project tutor skill for the AI Engineering from Scratch curriculum. It guides developers through project stages, runs tests, and tracks learning progress. Claude Code CX Codex Cursor +1 1,200installs

Similar

tailwind-design-system sickn33 A skill that keeps the agent on Tailwind while you build a design system: tokens, component variants, responsive patterns, accessibility. Useful when the UI drifts. Claude Code CX Codex Cursor +1 1,600installs edge-to-edge Google LLC Migrates Jetpack Compose apps to adaptive edge-to-edge layouts and fixes content blocked by system bars or the keyboard. Claude Code CX Codex Cursor +1 3,200installs swiftui-liquid-glass official OpenAI This skill helps build and review SwiftUI Liquid Glass interfaces for iOS 26+. Use it when adopting the API or checking fallbacks, interaction, and design fit. CX Codex GP ChatGPT 121installs vue-expert-js https://github.com/Jeffallan Builds Vue 3 code in JavaScript with JSDoc annotations instead of TypeScript. Use it for components, composables, routing, and state management in JS-only projects. Claude Code CX Codex Cursor +1 4,000installs frontend-design official anthropics This skill guides intentional visual design for new interfaces and redesigns. Use it when a generic generated UI is not enough. Claude Code Claude.ai 1,025,790installs design-taste-frontend Leonxlnx This skill directs the design of public pages and work screens, then checks the result in a browser through screenshots. Use it when an interface feels generic or unfinished. Claude Code CX Codex Cursor +1 673,100installs prototype Matt Pocock Creates throwaway prototypes for checking state logic or exploring UI before committing the decision to the main codebase. Claude Code 986,201installs hyperframes heygen-com Instructs coding agents on creating, validating, and rendering HTML-based videos using the HyperFrames framework and CLI. Claude Code CX Codex Cursor +1 1,200,000installs

Questions about isometric-explainer

How to install isometric-explainer in Claude Code?

Run npx skills add rohitg00/ai-engineering-from-scratch --skill isometric-explainer -a claude-code in your terminal.

When should this skill not be used?

Skip it when a flat static diagram is enough, when the system lacks sequential state changes, or when you cannot formulate a deterministic state model. For small inline lesson diagrams, the documentation recommends blueprint-figure instead.

What are the part count limits for the machine?

Machines fall into Figure (40 to 80 parts) and Hero (80 to 150 parts) tiers without special checks. Creating a machine with more than 150 parts requires prior user approval.

Source text

SKILL.md · MIT
---
name: isometric-explainer
version: 1.0.0
description: >
  Builds an interactive isometric machine page. Each station of one invented machine stands for one step of a process.
  A pure, tested state model drives the motion, the readouts and the copy. The page has controls and a verification loop.
  Trigger phrases: "isometric explainer", "machine explainer", "explain this as a machine",
  "interactive isometric figure", "explorable explainer", "show how it works inside".
tags: [isometric, svg, interactive, explainer, simulation]
---

# Isometric Explainer

This skill makes a single-page interactive figure. The figure is a solid isometric machine on a bench. Each station of the machine stands for one step of a process. For example, a request card moves on a carriage, a probe drops, and a press stamps the card. A pure state model decides every move, so the picture, the numbers and the words match. The `templates/` folder holds a working starter, and `kit/` holds the geometry library it uses.

## When to use

- The concept is a process with stations, order and failure modes: a loop, a pipeline, a cache, a queue, a retry policy.
- The reader can break one part and see what fails.
- The figure is the main content of a page.

## When not to use

- A static diagram explains the idea. Make a flat SVG figure instead.
- The concept has no order or state change. Make a static figure instead.
- The figure is a small diagram inside a lesson or a README. Use the sibling skill `blueprint-figure`.
- You cannot write a deterministic model of the behavior. Do not animate a guess.
- The job needs more than 150 parts and the user has not approved the size.

## Method

1. Invent the machine. Write one sentence: "X moves through Y, and that motion means Z." If you cannot write it, pick another machine. See `references/concept.md`.
2. Count the parts on paper before you draw, and pick a tier.

   | Tier | Parts | Approval |
   |---|---|---|
   | Figure | 40 to 80 | not needed |
   | Hero | 80 to 150 | not needed |
   | Larger | more than 150 | get the user's approval first |

3. Write the state model first. Make `model.mjs` pure and deterministic, with no DOM and no clock. `simulate(config)` returns an event list and totals. Test it before any geometry. See `references/state-model.md`.
4. Map each concept to a station. Write a table: station, concept word for its label, what it does, what fails without it.
5. Write the parts list. List each part with its assembly, size in world units, tone and whether it moves. Geometry comes after the list.
6. Set the camera. Use world units and one isometric camera. Set elevation to 30 degrees. Pick the azimuth so the working faces point at the viewer. Fit the projection over the assembled and the exploded pose.
7. Build the static geometry once. Each part becomes one SVG group with a depth key. Movers get a `data-live` hook. See `references/geometry.md`.
8. Animate by translation. Move a part by changing its `transform` only. Rebuild a path only when its shape changes, such as a rod that gets longer.
9. Paint from back to front. Sort groups by depth key plus the depth of their current offset. Reorder the DOM only when the order changes.
10. Paint with colour and ink. Each material has three flat tones, the main bodies have a heavy ink silhouette, and each body casts a short, flat, warm grey shadow on the bench. Exactly one accent colour marks the active part and its pill label. See `references/colour-and-ink.md`.
11. Add controls that change the model. Run, step, break, repair, reset and the config switches all act on a real `simulate` run. Write the config to the URL. See `references/live.md`.
12. Verify the page in a headless browser. Take screenshots at desktop and phone width in both themes. Add 4x close-ups, a line-end check, a scenario sweep with zero console errors and a contact sheet. See `references/verify.md`.

## Rules

Truth:
- The state model is the single source of truth. Motion, readouts, trace lines and outcome text all come from its events.
- `simulate` with the same config returns the same events. A test proves this for every config combination.
- Never fake a real model, a real service or real metrics. A scripted part says "fixed script" in the page copy.
- Every page with simulated timing shows a sentence that starts "This is a simulation." and says that times are fixed costs, not measurements.
- Use real arithmetic in the model. Tests assert the exact numbers that the page prints.

Geometry:
- All coordinates are world units. Pixels appear only in the projection.
- Elevation is 30 degrees. The azimuth is one fixed value for the whole page. The reference page uses 60.
- Solids use `inkSolid` from `kit/ink.mjs`: three flat tones for each material, an ink outline, and a heavier silhouette round each main body.
- Every line ends on a solid or on another line. A line with a deliberate loose end carries `data-free="start"`, `"end"` or `""`.
- Each station carries a pill label with a leader line to its working part, with its concept word in capitals, such as `CACHE` or `VERIFIER`. The page has a Labels switch and reads `?labels=0`.
- Status lights show the state the model gives each station: green when it finished, red when it failed or left a gap.
- Glass covers show what is inside a station: a light tint and one or two streaks.
- A part that rests on another part gets a depth bias so it paints after its support.

Motion:
- Movers change `transform` only. A path that changes shape is rebuilt from cached results where it can be.
- One beat lasts 0.1 to 1.3 seconds. Travel time grows with distance.
- Explode uses a spring with stiffness 64, damping 14.2 and a 0.04 s stagger per assembly.
- Clamp the frame step to 1/20 s so a slow frame never skips a beat.
- With reduced motion, runs advance 40 times faster and explode snaps to its end pose.
- The animation loop stops when the stage is off screen and when nothing moves.

Page:
- The workbench fits one screen at desktop width: toolbar, stage and readouts in `100svh`.
- At phone width the page stacks and never scrolls sideways.
- Buttons are at least 44 px tall. The stage takes focus and has keyboard keys for run, step, explode, break and repair.
- The SVG has `role="img"` and an `aria-label` that names every station.
- An `aria-live="polite"` region announces the outcome when a run ends.

## Check before you finish

- [ ] The one-sentence machine statement is written in the page copy or the build notes.
- [ ] The part count matches the approved tier.
- [ ] Model tests pass, including a sweep over every config combination.
- [ ] The page is the output of the build script. Rebuilding produces no diff.
- [ ] Every config control calls `simulate` and updates the URL.
- [ ] Opening the URL with `?` parameters restores the same config.
- [ ] Exactly one accent colour shows at any moment, and it follows the active part.
- [ ] Every station shows a readable pill label in both themes and at phone width, and no pill covers a mover or another pill.
- [ ] The wobble slider, the colour swatches and the Labels switch work, and `?labels=0` starts with the labels off.
- [ ] A "The big idea" line under the figure says the point in plain words.
- [ ] The line-end check reports zero loose ends.
- [ ] The scenario sweep runs every config to the end with zero console errors.
- [ ] Desktop and phone screenshots in light and dark show no clipping and no horizontal scroll.
- [ ] The exploded pose stays inside the stage.
- [ ] The simulation sentence is on the page.

## Files

- `references/concept.md`: invent the machine, the one-sentence test, concept mapping, sizing.
- `references/state-model.md`: the model contract, event shape, tests, URL state.
- `references/geometry.md`: units, camera, parts list, kit functions, shading, depth keys, labels.
- `references/colour-and-ink.md`: materials, tones, ink weights, cast shadows, glass, status lights, pill labels, wobble and the dark theme.
- `references/live.md`: the beat timeline, the draw loop, sorting, accent, controls, accessibility, layout.
- `references/verify.md`: the headless verification loop with a script.
- `templates/model.mjs`, `templates/model.test.mjs`, `templates/build.mjs`, `templates/live.js`: a working cache machine. Run `node templates/build.mjs` to write `templates/out.html`. Run `node --test templates/model.test.mjs` for the model tests.
- `kit/iso-kit.mjs`, `kit/lathe.mjs`, `kit/tube.mjs`: projection, solids, lathe bodies, tubes and the base CSS. Keep `kit/LICENSE` with the kit.
- `kit/ink.mjs`: the colour and ink layer: `inkSolid`, `silhouetteSvg`, `castShadowSvg`, `glassSvg`, `pillSvg`, `wobbleFilter`, `PALETTES` and `INK_CSS`.

Inside the AI Engineering from Scratch repo, also see `scripts/decompiler-machine/` and `site/test_decompiler_machine.js` for a full hero build in the colour and ink look, and `scripts/agent-machine/` for the older grey look.

© rohitg00 · MIT · rohitg00/ai-engineering-from-scratch

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor