agentleFS
vibe-cokitvibe-cokit/claude-code/skills/vk-design/SKILL.md

vk-design

Skill1 starsChanged 4 months agoApache-2.0View on GitHub

⚡⚡ Create a design from a task (--fast | --good | --3d)

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 1 is distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    No flag given: task names a 3D/WebGL/Three.js deliverable → --3d.

    line 24
  2. Very specific:

    Run the pipeline for the selected mode.

    line 28
  3. Very specific:

    If the user doesn't specify a stack, build in pure HTML/CSS/JS.

    line 29
  4. Very specific:

    Document shaders, particle systems, and reusable 3D components in ./docs/design-guidelines.md.

    line 39
  5. Distinctive:

    Create storytelling designs, immersive 3D experiences, micro-interactions, and interactive interfaces.

    line 45

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Design

Think hard to plan & start working on these tasks follow the Orchestration Protocol, Core Responsibilities, Subagents Team and Development Rules: <tasks>$ARGUMENTS</tasks>

IMPORTANT: Activate the ui-ux-pro-max skill (design decisions — style/palette/font/UX database, per-stack guidelines); add design-system when producing tokens or component specs.

Designing FROM a screenshot, video, or image? Use /vk-design-from-visual instead.

Modes

FlagModePipeline
--fast (default)Quick designui-ux-designer subagent straight to implementation.
--goodImmersive designresearcher subagent (style, trends, fonts, colors, borders, spacing, element positions) → ui-ux-designer implements from that research.
--3dInteractive 3Dui-ux-designer + researcher write a plan, then ui-ux-designer implements the Three.js scene.

No flag given: task names a 3D/WebGL/Three.js deliverable → --3d; task asks for stunning / immersive / award-winning → --good; otherwise --fast.

Workflow

  1. Run the pipeline for the selected mode. --good and --3d write a plan first — structure: skills/planning/references/plan-organization.md.
  2. If the user doesn't specify a stack, build in pure HTML/CSS/JS.
  3. Report a brief summary of the changes; ask the user to review and approve.
  4. On approval, update ./docs/design-guidelines.md if needed.

3D Requirements (--3d only)

  • Three.js scenes with proper optimization; custom GLSL vertex/fragment shaders; GPU-accelerated particle systems.
  • Immersive camera controls, cinematic effects, post-processing and render pipelines.
  • Responsive across devices, target smooth 60fps, interactive elements with smooth animations.
  • Stack: Three.js + GLSL + WebGL, HTML/CSS/JS for UI integration.
  • Document shaders, particle systems, and reusable 3D components in ./docs/design-guidelines.md.

Important Notes

  • ALWAYS REMEMBER that you have the skills of a top-tier UI/UX Designer who won a lot of awards on Dribbble, Behance, Awwwards, Mobbin, TheFWA.
  • Reference material, video frames, and the raster-asset policy: workflows/visual-input.md.
  • Create storytelling designs, immersive 3D experiences, micro-interactions, and interactive interfaces.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

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.