agentleFS
Sign inStart free
mithunycmithunyc/buildloop/skills/awesome-design-md/SKILL.md

awesome-design-md

Skill1 starsChanged 16 days agoMITView on GitHub

Use curated DESIGN.md references to guide AI-generated UI and visual design. Use when building or improving frontend UI, landing pages, dashboards, design systems, visual style, brand-inspired interfaces, or when the user asks for a UI to look like a known product, company, or design reference from the VoltAgent awesome-design-md catalog.

6 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

10 rules. 0 are common, 8 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 8

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    Use this skill to choose and apply a DESIGN.md-style design reference without loading a large design catalog into context by default.

    line 8
  2. Distinctive:

    If the user names a brand in the awesome-design-md catalog, use that brand.

    line 17
  3. Distinctive:

    If no brand is named, choose 1-3 suitable references and explain the tradeoff briefly.

    line 18
  4. Distinctive:

    Prefer references that fit the product job, not just a fashionable palette.

    line 19
  5. Very specific:

    Prefer a local checkout if present in the current workspace at repo-inspection/awesome-design-md/design-md/<brand>/README.md.

    line 22
  6. Distinctive:

    Do not bulk-load the whole catalog.

    line 24
  7. Distinctive:

    Avoid copying trademarked branding, logos, or exact protected assets unless the user owns or supplies them.

    line 28
  8. Distinctive:

    Keep accessibility, responsive behavior, and product usability above visual imitation.

    line 29
  9. Distinctive:

    Check that text fits, buttons and inputs are usable, contrast is acceptable, and visual hierarchy matches the chosen reference.

    line 33
  10. Distinctive:

    Use these as starting points, not rules.

    line 44

“Common” is measured: kept by at least 6 in 10 of the 4 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.

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

Awesome DESIGN.md

Use this skill to choose and apply a DESIGN.md-style design reference without loading a large design catalog into context by default.

Workflow

  1. Identify the target product category and design mood:
    • Enterprise SaaS, developer tool, fintech, consumer app, marketplace, media, automotive, AI platform, dashboard, docs, or mobile app.
    • Dense/utilitarian versus editorial/marketing versus cinematic/brand-forward.
  2. Pick a reference:
    • If the user names a brand in the awesome-design-md catalog, use that brand.
    • If no brand is named, choose 1-3 suitable references and explain the tradeoff briefly.
    • Prefer references that fit the product job, not just a fashionable palette.
  3. Load only the needed reference:
    • Prefer a local checkout if present in the current workspace at repo-inspection/awesome-design-md/design-md/<brand>/README.md.
    • Otherwise use the public catalog at https://github.com/VoltAgent/awesome-design-md.
    • Do not bulk-load the whole catalog.
  4. Apply the design as constraints:
    • Translate colors, type scale, component styling, spacing, density, interaction patterns, and do/don't rules into implementation choices.
    • Avoid copying trademarked branding, logos, or exact protected assets unless the user owns or supplies them.
    • Keep accessibility, responsive behavior, and product usability above visual imitation.
  5. Verify visually:
    • For implemented UI, inspect desktop and mobile states.
    • Check that text fits, buttons and inputs are usable, contrast is acceptable, and visual hierarchy matches the chosen reference.

Default Reference Choices

  • Enterprise operations dashboard: Linear, Airtable, IBM, HashiCorp, Sentry.
  • Developer platform or API docs: Vercel, Resend, Mintlify, Replicate, OpenCode AI.
  • AI product: Claude, Cohere, Mistral AI, VoltAgent, Together AI.
  • Fintech or trust-heavy product: Stripe, Coinbase, Wise, Mastercard.
  • Consumer marketplace or commerce: Airbnb, Shopify, Apple, Nike.
  • Editorial or media: WIRED, The Verge, Spotify.

Use these as starting points, not rules.

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.

Check your setup, free