Prototype · Preview: every server in the official registry, synced every 30 minutes. Sign in with Google to write reviews.Prototype · updated every 30 min
PopNx MCPMCP servers for people who use AI · explained in plain words

machine-skill Skill

Repository ↗

by AirsupHQ★ 6981 skills

Install

What it does

Describe any machine in one line. Claude builds a photoreal, physics based, interactive simulation of it in one HTML file, plus the film to post it. An open source Claude Code skill.

  • Connects Instruction files the AI reads
  • Account or key Not confirmed yet (README not read yet)
  • Category Coding
For makers: add a badge to your README

If you made this, paste this code into your README. The badge links back to this page.

[![Featured on PopNx MCP](https://mcp.popnx.com/badge/skill/airsuphq-machine-skill.svg)](https://mcp.popnx.com/en/skills/airsuphq-machine-skill)

Use together with

MCP servers that connect the AI to services for the same work

REA

Reverse engineer anything from your terminal or agent with one CLI and MCP server.

by morlutoWidely used↓ 388.7K/wk★ 464.1KUpdated 6 days ago

MCP · Connects a serviceRuns on your computer

Fallow

Codebase intelligence for TypeScript and JavaScript, exposed as structured MCP analysis tools.

by fallow-rsWidely used↓ 2.4M/wk★ 5.4KUpdated yesterday

MCP · Connects a serviceRuns on your computer

Desktop Commander

MCP server for terminal commands, file operations, and process management

by wonderwhy-erWidely used↓ 740.3K/wk★ 10.3KUpdated 6 days ago

MCP · Connects a serviceRuns on your computer

Similar Skills

Same kind of work, ordered like the Skills list

Compared with similar ones
This one
machine-skill
reaandrej-karpathy-skillsgraphifyMoneyPrinterTurbo
MakerAirsupHQmorlutomultica-aiGraphify-Labsharry0703
Skills11111
GitHub stars698465,460233,910149,364144,149
Last code changeOct 13, 2026Nov 17, 2026Apr 20, 2026Nov 17, 2026Nov 17, 2026
LicenseMITMIT–Apache-2.0MIT

1 skills (instruction sets) by AirsupHQ that an AI reads and follows · not an MCP server

How a Skill differs from MCP

MCP = the hands

Connects the AI to an outside service or data, such as reading Notion or creating an invoice. A program or server has to be running.

Skill = the manual

A text file that teaches the AI how to do a task. It connects to nothing.

Some overlap: a few Skills run scripts that call tools, and a few MCP servers only send knowledge. Start from the task you want done.

Works with

Claude CodeClaude (เว็บ/แอป)CodexCursor

From the maker’s README and the folders in the repo

Install

Is it safe?

  • Who made it

    GitHub account AirsupHQ (person) is only 1 months old: take extra care

  • Use and upkeep

    ★ 698 stars · code last changed Oct 13, 2026

  • Any scripts?

    9 scripts that can run on a computer: kit/lab-kit.js, scripts/inline.mjs, scripts/lib/browser.mjs, scripts/lib/guard.mjs and 5 more

  • Uses the internet?

    Scripts that go online: scripts/record.mjs

  • Changes machine-wide settings?

    No hooks or writes to machine settings found

Checked automatically from the repo files at commit e0bd066 (read only, nothing was run). Not a safety guarantee: read it and decide for yourself

First: which AI do you use?

Pick your app and this page shows only how to install it there

Option 1Upload to claude.ai (web and app)

Uploading to claude.ai would fail: the description is over 200 characters (869). Use "Let the AI install it" instead

Option 1Let Claude Code install it

Copy this sentence and paste it into a Claude Code chat

Where to install

Checking the commands · copy buttons appear once they pass

Checking the commands · copy buttons appear once they pass

For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing

The AI tells you what it will do first and asks your permission at every step

Restart Claude Code, then type /machine-skill or ask for a matching task and Claude picks it up

Checked against official docs Nov 12, 2026 · Source: code.claude.com

For Terminal users

A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.

The maker’s recommended way

Install Node.js (if you don’t have it)

Already installed? Check first · Open Terminal, type this command and press Enter

node -v
  • A version number such as v26.13.1 = installed, skip this step
  • "command not found" (on Windows: "is not recognized") = not installed yet, or installed but Terminal needs to be closed and reopened
How to open Terminal

Mac: press ⌘ + Space, type Terminal, press Enter

Windows: open Start, type Windows PowerShell, then Open

Not installed: Open the official download page, pick the LTS version and the click-through installer: .pkg on Mac · .msi on Windows. Double-click and follow it to the end. No curl command needed

Open the Node.js download page ↗

When it’s done, close Terminal, open it again and run the same command. You should see a version number: node -v

Install once; it works for everything that needs Node.js

Checking the commands · copy buttons appear once they pass

Copied from the maker’s README; it downloads and runs the maker’s code

  1. Open Terminal

    Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead

  2. Copy the skill folder to ~/.claude/skills

    This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md

    Checking the commands · copy buttons appear once they pass

  3. Restart Claude Code, then type /machine-skill or ask for a matching task and Claude picks it up

Skills you install yourself work in the ChatGPT desktop app, Codex CLI and the Codex IDE extension · ChatGPT on the web and mobile cannot use skills you install yourself, only skills that come with a plugin from the directory

ChatGPT desktop app

The ChatGPT desktop app has Codex built in, and Codex reads skills from ~/.agents/skills

Option 1Let ChatGPT install it

Open Codex in the ChatGPT desktop app and paste this sentence into the chat

Where to install

Checking the commands · copy buttons appear once they pass

Checking the commands · copy buttons appear once they pass

The AI always shows you the path before installing

The AI tells you what it will do first and asks your permission at every step

Option 2Put the folder there yourself

Put the machine folder at ~/.agents/skills/machine

~ is your home folder ($HOME)

For Terminal users

A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.

  1. Open Terminal

    Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead

  2. Copy the skill folder to ~/.agents/skills

    This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md

    Checking the commands · copy buttons appear once they pass

After installing

  • ChatGPT desktop app: open Skills in the sidebar to see that the skill is there
  • To use it: in ChatGPT type @ and pick the skill · in Codex CLI or the IDE extension run /skills or type $ and the skill name
  • Codex picks up newly installed skills by itself; if one does not show up, restart Codex

Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com

ChatGPT on the web and mobile

Skills you install yourself do not work here; only skills that come with a plugin from the directory

To use this skill with ChatGPT, use the ChatGPT desktop app as above

Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com

Option 1Let Codex install it

Copy this sentence and paste it into a Codex chat · Works in Codex inside the ChatGPT desktop app, Codex CLI and the IDE extension

Where to install

Checking the commands · copy buttons appear once they pass

Checking the commands · copy buttons appear once they pass

For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing

The AI tells you what it will do first and asks your permission at every step

Codex picks up newly installed skills by itself; if one does not show up, restart Codex · To use it: in ChatGPT type @ and pick the skill · in Codex CLI or the IDE extension run /skills or type $ and the skill name

Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com

For Terminal users

A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.

  1. Open Terminal

    Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead

  2. Copy the skill folder to ~/.agents/skills

    This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md

    Checking the commands · copy buttons appear once they pass

  3. Restart Codex, then ask for a matching task; Codex lists the skill

Option 1Let Cursor install it

Copy this sentence and paste it into a Cursor chat

Where to install

Checking the commands · copy buttons appear once they pass

Checking the commands · copy buttons appear once they pass

For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing

The AI tells you what it will do first and asks your permission at every step

In Cursor’s Agent chat, type / and pick machine-skill

Checked against official docs Nov 12, 2026 · Source: cursor.com

For Terminal users

A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.

  1. Open Terminal

    Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead

  2. Copy the skill folder to ~/.cursor/skills

    This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md

    Checking the commands · copy buttons appear once they pass

  3. In Cursor’s Agent chat, type / and pick machine-skill

Option 1Let the AI install it

For other apps that read skills. The sentence gives the paths for Claude Code, Codex and Cursor so the AI picks the one for your app · Copy this sentence into the app’s chat

Where to install

Checking the commands · copy buttons appear once they pass

Checking the commands · copy buttons appear once they pass

For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing

The AI tells you what it will do first and asks your permission at every step

Checked against official docs Nov 12, 2026 · Source: code.claude.com, learn.chatgpt.com, cursor.com

For Terminal users

Other apps that support Agent Skills (such as Gemini CLI or GitHub Copilot) use different folders. Check that app’s guide, then copy the folder with the SKILL.md there.

View on GitHub ↗

Skill folders checked against the official Claude Code, Codex and Cursor guides on Nov 11, 2026

View the original SKILL.md

The text below comes from the maker’s repo, not from PopNx MCP

Showing the first 8,000 characters · Open the full file on GitHub

---
name: machine
description: Turn one line ("a turbofan jet engine", "a mechanical watch", "an LVAD heart pump") into a photoreal, physics based, interactive 3D simulation of that machine in a single HTML file, plus a 20 to 30 second film to post it. Real proportions in metres, real materials (PBR metals, paints, polymers, glass), studio lighting with soft shadows, moving parts driven by a small solver that computes real numbers (thrust, torque, rpm, flow, pressure, efficiency), and modes to explode it, cut it open with clean section caps, x-ray it, slow it down, label it and break it. Use this whenever someone asks to build, simulate, visualise, explain or "show how X works" for any machine, engine, mechanism, device, instrument or piece of hardware, wants an interactive 3D model or a cutaway, or wants a video of a machine for a post, even if they never say "simulation" or "three.js".
---

# Machine Skill

You build a machine the way a product studio photographs one and an engineer explains one: the real thing at its real size, in real materials, on a clean studio set, running on real equations. One line in, one HTML file out, and a film in one command.

The output is always:

1. `<name>.html`: a single self contained page (three.js 0.170 from jsDelivr, the kit inlined). It opens from disk, from any static host, or inside an iframe.
2. A film: `node scripts/record.mjs <name>.html out/<name>.mp4 --music freepd:<Category>/<Name>`.

Open `examples/` first. Every example was made from the one line at the top of its page. `examples/turbofan.html` is the reference: read it end to end before you write anything.

## The bar

Before you start, picture the frame a viewer sees after three seconds. It must already look like a studio product photograph of the real machine: correct silhouette and proportions, metal that reads as metal, a soft shadow on a paper floor, nothing floating, nothing clipping, nothing placeholder. Then it moves, and every number on screen is computed.

A result is not done while any of these is true:

- a part a mechanic would expect is missing (no fuel nozzles in a combustor, no escapement in a watch, no valves in an engine)
- something floats, intersects, or has a visible seam or gap at a joint
- a material looks like plastic when it should be metal, or everything is one grey
- a number on screen is typed in rather than computed by the solver
- the cutaway shows hollow shells instead of solid section faces
- the first frame of the film is not beautiful

## Workflow

### 1. Research the real machine (5 minutes, no code)

Write down, in a comment block at the top of the machine script, from what you know (and the web if you have it):

- **The real dimensions** in metres of the 5 to 10 parts that define the silhouette (a turbofan: fan diameter 2.85 m, length 4.9 m, nacelle max diameter 3.44 m).
- **The parts list** in assembly order, each with its material. Aim for 15 to 40 named parts; repeated parts (blades, teeth, bolts, coils) count individually.
- **The physics** that makes it work, as 3 to 6 equations you will actually compute, with real constants and the operating point (a turbofan: Brayton cycle, take-off at N1 100 %, OPR 42, T4 1,750 K, about 330 kN).
- **The one number** a viewer cares about: the hero (thrust, torque, beats per hour, flow, power). It gets a huge serif readout and a thin bar.
- **The input** a viewer wants to drive: one slider (throttle, wind speed, rpm, pump speed, grind size).
- **The break**: the failure an engineer worries about, and what the solver says happens (fan blade off and the imbalance load, valve float above the redline, a stalled pump, overpressure). This must be a computed consequence, not an animation.

### 2. Build the page from the template

Copy `kit/template.html` to `<name>.html`. It has the import map (pinned three@0.170.0), the fonts, a marked block where the kit goes, and the four sections you fill in:

```js
const { THREE, Lab, MAT, GEO, heatGlow, clamp, lerp, approach, fmt } = window.LabKit
const lab = new Lab({ prompt, no, title, sub, size, view, cut })   // 1. the lab
// 2. the parts      lab.mesh(GEO..., MAT..., { name, pos, explode, xray, count })
// 3. the solver     lab.hero(...); lab.slider(...); lab.onTick((dt, lab) => { ... lab.setHero(...) })
// 4. break, explain, film      lab.breakIt(...); lab.how(...); lab.autoFilm(...); lab.start()
```

Right after copying, run `node <skill dir>/scripts/inline.mjs <name>.html`: it pastes the kit into the marked block so the page is one self contained file wherever it lives (the template's `src="../kit/lab-kit.js"` only resolves inside this repo). Then write your machine in the second script block.

### 3. Geometry: real solids at real size

Work in metres in the machine's own frame, Y up, the floor at y = 0 unless you set `ground`. Set `size` to the longest real dimension; the kit scales the display so every machine sits the same on the set, and the scale bar shows real size.

- **Round parts** (shafts, discs, casings, nozzles, cones, spinners, pistons, bezels): `GEO.lathe([[r, y], ...])` with a CLOSED profile. Walls: `GEO.shell(profile, thickness)`, tubes: `GEO.tube(rOut, rIn, h)`, chamfered discs: `GEO.disc(r, h)`. Corners stay crisp and curves shade smooth automatically.
- **Blades and vanes**: `GEO.rotor({ count, axis, r0, r1, chord, thick, camber, twist, pitch, sweep })` builds real cambered, twisted airfoils (NACA thickness) as closed solids and rings them. Use `[root, tip]` arrays for chord, thick and camber.
- **Gears**: `GEO.gear({ teeth, module, width, bore, helix, spokes, rim })`. Mesh two gears at centre distance `(z1 + z2) * module / 2` and turn them at the inverse tooth ratio, offset by half a tooth.
- **Pipes, hoses, wires**: `GEO.pipe(points, r)` (closed, capped). Route them along the structure from port to port, never through a part.
- **Fasteners**: `GEO.bolts(n, R, size, h)` on every flange. Springs: `GEO.spring(R, wire, turns, len)`. Boxes: `GEO.rbox(w, h, d, r)` (always rounded, never sharp). Plates with holes: `GEO.extrude(shape, depth)`.
- **Masses and inertias** come from the geometry: `GEO.volume(geo)` gives volume and centroid, multiply by the real density.

Rules that keep it clean:

- **Every part is a closed solid** (lathe profiles closed, shells with thickness, pipes capped). That is what lets the cutaway draw solid section faces. Open surfaces show as hollow when cut.
- **Nothing intersects visibly and nothing floats.** Every part touches what holds it (a flange sits on a face, a shaft runs in a bearing, a post reaches the floor). Check joints in close ups.
- **Detail where the eye goes**: bolt circles on flanges, chamfers, a lip, a label plate, fuel lines, a harness. Big flat areas get a seam, a panel line or a texture finish.
- **Give the machine a base**: a stand, cradle, plinth, bench or mount with feet on the floor. Machines rarely float in real life.
- **Budget**: up to about 700k triangles and 200 meshes. Merge repeated static parts with `GEO.merge` / `GEO.ring`; keep moving groups separate.

### 4. Materials: never one grey

Use `MAT.*` presets; they carry measured reflectances so steel, titanium, aluminium, brass and copper look different side by side. Every preset takes overrides (`color`, `roughness`, `clearcoat`, any MeshPhysicalMaterial field) and a `finish` (micro roughness texture: `turned` rings on lathe parts, `brushed` streaks, `cast` blotches, `smudge`, `knurl`).

| Use | Preset |
|---|---|
| shafts, discs, machined parts | `MAT.steel`, `MAT.stainless`, `MAT.chrome` |
| housings, castings | `MAT.aluminium`, `MAT.castIron`, `MAT.steelDark` |
| blades, aerospace | `MAT.titanium`, `MAT.inconel` (+ `heatGlow`) |
| fittings, wiring | `MAT.brass`, `MAT.copper`, `MAT.gold` |
| painted bodies | `MAT.paint({ color })`, `MAT.satin`, `MAT.anodised({ color })` |
| polymers | `MAT.plastic`, `MAT.rubber`, `MAT.carbon` |
| windows, crystals | `MAT.glass`, `MAT.sapphire`, `MAT.ruby`, `MAT.enamel` |
| l

Discussion

Ask, share a tip or report that it does not work. Sorted by what people marked helpful.

No posts yet. Be the first to ask or share.

Posts here are written by users, not the PopNx team.

Sign in to post

From GitHub

GitHub stars
698
Maker
AirsupHQ
License
MIT
Last code change
Oct 13, 2026
SKILL.md files in the repo (including translated copies and templates)
1
Topics
agent-skills, claude, claude-code, claude-skill, cutaway, engineering, physics, simulation, threejs, webgl