threejs-web — Claude Code skill: features and installation
This Claude Code skill plans and builds Three.js web experiences or focused 3D features. It inspects the project and checks the result in a browser.
MIT 776 installs ★ 26 updated 2026-09-10
npx skills add cesartevisual/threejs-skills --skill threejs-web -a claude-codeWhat threejs-web does
The skill guides an agent through planning and building a Three.js web experience or adding a focused 3D feature. It starts by inspecting the project structure, installed Three.js revision, available assets, and target devices. Then it builds a first slice with a responsive canvas, a representative subject, camera framing, an interaction, and loading and error states.
The agent adds requested details while keeping navigation, forms, and core actions in semantic HTML. Depending on the project, it accounts for asset and frame budgets, resizing, resource ownership, reduced motion, and a non-WebGL fallback. It checks the visible result in a browser. The skill keeps the project's installed Three.js version and architecture instead of upgrading the stack to match an example.
What it helps with
- plan a Three.js web scene
- add a 3D feature to an existing project
- check a scene in the browser
- preserve the current architecture while changing a 3D interface
Example prompts for the agent
- Plan a Three.js web scene in this project and start with a basic version that has one interaction.
- Add a 3D object to the existing interface, keep the current stack, and check the result in a browser.
- Adapt the scene for the target devices and add a non-WebGL fallback if the project calls for one.
How to install threejs-web
1Skills CLI (Vercel)
npx skills add cesartevisual/threejs-skills --skill threejs-web -a claude-code2Manually: put the files in place
~/.claude/skills/threejs-web/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/threejs-web/
1Skills CLI (Vercel)
npx skills add cesartevisual/threejs-skills --skill threejs-web -a codex2Manually: put the files in place
.agents/skills/threejs-web/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add cesartevisual/threejs-skills --skill threejs-web -a cursor2Manually: put the files in place
.cursor/skills/threejs-web/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install cesartevisual/threejs-skills skills/threejs-web2Manually: put the files in place
.github/skills/threejs-web/SKILL.md1Skills CLI (Vercel)
npx skills add cesartevisual/threejs-skills --skill threejs-web -a gemini-cli2Platform CLI
gemini skills install https://github.com/cesartevisual/threejs-skills --path skills/threejs-webManually: put the files in place
.devin/skills/threejs-web/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add cesartevisual/threejs-skills --skill threejs-web -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about threejs-web
How do I install threejs-web in Claude Code?
Run npx skills add cesartevisual/threejs-skills --skill threejs-web -a claude-code. The skill file is at ~/.claude/skills/threejs-web/SKILL.md.
What does threejs-web do?
It guides an agent in planning and building a Three.js web experience or a focused 3D feature for an existing project. It also covers checking the result in a browser.
Does threejs-web upgrade the Three.js version?
It uses the revision already installed in the project and does not upgrade the stack just to match an example.
Source text
SKILL.md · MIT
--- name: threejs-web description: "Plan and implement complete Three.js web experiences, or select focused skills for an existing 3D feature." --- # Three.js Web Projects Use the project's installed versions and existing architecture. These instructions supplement the user's task; they do not authorize unrelated changes or external actions. Establish the visible outcome, interaction, asset inputs, existing stack, and target devices from the request and repository. Preserve the chosen framework and art direction. Ask only about decisions that materially block implementation. Inspect package manifests, lockfiles, routes, styles, current canvas ownership, and available assets. Record the installed Three.js revision, renderer backend, and companion package peer requirements. Use documentation or source matching those versions; do not upgrade the stack just to match an example. Build a vertical slice first: a responsive canvas, representative subject, camera framing, one interaction, and a usable loading/error state. Then add requested detail. Keep product text, navigation, forms, and core actions in semantic HTML. Choose only the relevant specialist instructions from [the routing guide](references/routing.md). Skills are optional focused guidance, not a requirement to run every workflow. When only this skill is installed, implement from the requirements and consult the official documentation directly. Define asset and frame budgets for the actual devices. Add resize handling, explicit resource ownership, reduced motion, and a non-WebGL fallback as appropriate to the experience. Verify visible results in a browser, not just compilation. Report what was built, checks actually performed, and unresolved device or asset limitations. Shipping instructions do not authorize publication outside the user's request. ## API reference Consult the [official documentation](https://threejs.org/manual/) for exact signatures and revision-specific behavior. If documentation access is unavailable, inspect installed types/source and state any remaining uncertainty.
© cesartevisual · MIT · cesartevisual/threejs-skills