anatomy
Skill264 starsChanged 43 days agoApache-2.0View on GitHub
Explain how a machine works as an interactive isometric 3D cutaway. Use when the user asks how an engine, turbine, reactor, pump, clock, motor or any mechanism works and wants to see it, or types "/anatomy <machine>", for example "/anatomy explain how a big airliner turbofan engine like the A380's makes thrust, interactive". Produces a shareable three.ws link with real moving parts, shader effects (fire, exhaust, plasma, water, steam, sparks, arcs), flows, a section cut, an exploded view and a guided tour.
- Sends data out
We split this skill into the rules it gives an agent
4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 15 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 28
Read reference.md. It is the full spec format: parts and shapes, motion, effects, flows, the tour and the quality bar.
- Distinctive: line 31
Write one JSON object for the machine the user asked about.
- Distinctive: line 56
When you cannot write the spec yourself, let the server's writer do it.
- Distinctive: line 83
Start from it to make a variation.
“Common” is measured: kept by at least 6 in 10 of the 15 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Anatomy: machines as interactive cutaways
Describe a machine in one line and get back an interactive isometric wireframe cutaway on three.ws. Visitors can rotate it, step through a guided tour, explode it, cut it open, switch to x-ray and click any part to read what it does. Moving parts really move, and the physics is drawn with WebGL shaders.
The result is a permalink such as https://three.ws/anatomy/<id>. Share it as
the answer. It works on desktop and phones, with no account needed to view it.
Two ways to build one
1. You write the spec (best quality, recommended)
You know the machine. Write the spec yourself and publish it.
- Read reference.md. It is the full spec format: parts and shapes, motion, effects, flows, the tour and the quality bar. The server validates against exactly these rules.
- Write one JSON object for the machine the user asked about. If they named a
real machine (for example the Rolls-Royce Trent 900 on the A380), model that
machine and its real proportions, stage counts and numbers. If they were
vague, choose the most iconic real example and say which in
subtitle. - Publish it:
curl -s -X POST https://three.ws/api/anatomy \
-H 'content-type: application/json' \
--data-binary @- <<'JSON'
{ "action": "publish", "prompt": "<the user's request>", "spec": { ...your spec... } }
JSONThe response is { "design": { "id", "url", "title", "stats" }, "warnings": [] }.
Give the user design.url. stats counts parts, moving instances, effects,
flows and tour steps.
warnings lists anything the normalizer repaired, such as an unknown parent, an
unknown focus id or a clamped value. The machine still renders. If a warning
points at something that matters (a missing part, a broken hierarchy), fix the
spec and publish again. Each publish gets a new permalink.
2. Ask three.ws to write it
When you cannot write the spec yourself, let the server's writer do it. This takes one to several minutes.
curl -s -X POST https://three.ws/api/anatomy \
-H 'content-type: application/json' \
-d '{ "action": "generate", "prompt": "how a big airliner turbofan like the A380s makes thrust" }'The response has the same { design, warnings } shape. Pass "stream": true to
receive Server-Sent Events instead: stage, delta (the spec text as it is
written), reset, then one done (or error). Visitors can also type a prompt
straight into https://three.ws/anatomy and watch the machine assemble.
Errors
| status | error | what to do |
| 400 | invalid_spec | The spec is not a JSON object or has no renderable parts. detail lists the warnings. Fix and resend. |
| 400 | prompt_required | Send a prompt of at least 3 characters. |
| 413 | spec_too_large | Keep the spec under 400 KB. Use repeat instead of copying parts. |
| 429 | rate_limited | Wait for the retry-after header, then retry. |
| 503 | writer_unavailable / storage_unavailable | Retry in a minute. With path 1, the spec you wrote is still valid. |
Reading an existing machine
GET https://three.ws/api/anatomy?id=<uuid>returns{ design }with the full spec. Start from it to make a variation.GET https://three.ws/api/anatomy?list=recent&q=<text>lists recent machines without their specs.
What makes a great one
- Accurate: real part names, proportions and figures, such as pressure ratios, temperatures and rpm. Describe a relationship rather than inventing a number.
- Complete: typically 25 to 90 parts plus repeats.
- Built as hierarchies: blades and discs sit under the shaft that turns them.
- Readable at a glance:
glasscasings and aview.sectioncutaway show the inside. - A tour that teaches: it follows the physics in order (intake to exhaust, fuel to power) and focuses each step on the few parts that matter.
Other versions17 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 17
- wheresryan22/anatomy★ 20ksame name
- aaronjmars/aeon★ 787same name
- aeonfun/aeon★ 785same name
- felvieira/claude-skills-fv★ 27same name
- muzimu217/ui-design-agent-kit★ 23same name
- erafat/skills★ 17same name
- rfdiosuao/AgentSkill★ 15same name
- daftAI2026/awesome-jev★ 14same name
- Charlyhno-eng/jev-codex-pilot★ 7same name
- getedgehq/skills★ 5same name
7 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
Used alongsideProjects with it also use find-skills.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
VercelSkillfind-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Also in 3 projects that use this
In this repository62 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- docs/llms-full.txtllms.txt
- docs/llms.txtllms.txt
- llms-full.txtllms.txt
- llms.txtllms.txt
- public/llms-full.txtllms.txt
- public/llms.txtllms.txt
- authenticate-walletSkill
- build-an-agent-skillSkill
- connect-three-ws-mcpSkill
- create-3d-avatarSkill
- create-a-three-ws-agentSkill
- embed-three-ws-avatarSkill
- find-3d-assetsSkill
- fundSkill
- gcp-triageSkill
- generate-3d-modelSkill
- hire-an-agentSkill
- metamask-agent-walletSkill
- metamask-agent-workflowsSkill
- monetize-serviceSkill
- okx-agent-chatSkill
- okx-agentic-walletSkill
- okx-agent-identitySkill
- okx-agent-payments-protocolSkill
- okx-agent-taskSkill
- okx-ai-guideSkill
- okx-ai-supportSkill
- okx-audit-logSkill
- okx-dapp-discoverySkill
- okx-defi-investSkill
- okx-defi-portfolioSkill
- okx-dex-bridgeSkill
- okx-dex-marketSkill
- okx-dex-signalSkill
- okx-dex-socialSkill
- okx-dex-strategySkill
- okx-dex-swapSkill
- okx-dex-tokenSkill
- okx-dex-trenchesSkill
- okx-dex-wsSkill
- okx-growth-competitionSkill
- okx-how-to-playSkill
- okx-onchain-gatewaySkill
- okx-securitySkill
- okx-task-watchSkill
- okx-wallet-portfolioSkill
- pay-for-serviceSkill
- query-onchain-dataSkill
- rig-a-modelSkill
- search-for-serviceSkill
- sell-an-agent-skillSkill
- send-usdcSkill
- tradeSkill
- x402Skill
- changelog-and-docsSkill
- deploy-runbookSkill
- engineering-standardsSkill
- maintain-claude-mdSkill
- The first 60 shown.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

