agentleFS
Sign inStart free
eigent-aieigent-ai/agent-skills/skills/web-and-frontend-development/open-design/SKILL.md

open-design

Skill27 starsChanged 8 months agoApache-2.0View on GitHub

Generate web, mobile, and desktop prototypes, slides, dashboards, and editorial layouts from a single prompt using brand-grade design systems. Use when the user wants /web-prototype, /mobile-app, or /dashboard interactive HTML previews exportable to HTML, PDF, PPTX, or MP4 without Figma.

2 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

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    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
  1. Distinctive:

    Create an executive KPI dashboard — revenue vs target, burn rate, headcount by team, NPS trend, top 3 OKR progress bars.

    line 56
  2. Distinctive:

    Use realistic placeholder data — not lorem ipsum labels on charts.

    line 63
  3. Distinctive:

    Keep prototypes focused on the requested flows.

    line 64

≈ “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

Open Design

Local-first, open-source design system for rapid prototyping across web, mobile, and dashboards.

Source Repository

Runs on Claude Code, Cursor, Codex, Gemini CLI, and Copilot. Outputs sandboxed HTML preview with export to HTML, PDF, PPTX, or MP4.

/web-prototype

Generates a fully interactive web prototype from a text description — clickable HTML with real layout, components, and design system tokens. No Figma required.

Workflow:

  1. Clarify product type, primary user flows, and aesthetic (minimal SaaS, dark theme, etc.).
  2. Build sandboxed HTML with navigation between key views.
  3. Apply design tokens for spacing, color, and typography.
  4. Offer export format (HTML, PDF, PPTX, MP4).

Example prompts:

  • Build a B2B invoicing tool prototype — dashboard, invoice list with status badges, create-invoice modal. Clean minimal SaaS aesthetic.
  • Generate a landing page for an AI meeting notes product — hero with CTA, 3-feature grid, social proof, pricing table. Dark theme.
  • Prototype an internal HR leave request portal — employee form, manager approve/reject queue. Simple and functional.

/mobile-app

Generates pixel-accurate mobile app screens for iOS or Android — navigation, components, interaction states, spacing.

Example prompts:

  • Design a habit tracker — today view with checkboxes, streak counter, weekly stats chart, settings. iOS style, clean and minimal.
  • Generate a 4-screen onboarding flow for a food delivery app — welcome, location permission, cuisine picker, home feed. Bold, colorful.
  • Design notification settings for a fintech app — toggle alert types, quiet hours, push vs email. Android Material 3.

/dashboard

Generates data dashboard layouts — grid layouts, charts, KPI cards, tables, filters — as sandboxed HTML preview.

Example prompts:

  • Build a SaaS analytics dashboard — MRR trend, churn KPI, active users by plan, top features, recent signups table.
  • Design an ops monitoring dashboard — server uptime, error rate by endpoint, p95 latency, active deployments, incident log. Dark mode, high-density.
  • Create an executive KPI dashboard — revenue vs target, burn rate, headcount by team, NPS trend, top 3 OKR progress bars. Boardroom-ready.

Guardrails

  • Confirm target platform (web/mobile/dashboard) before generating.
  • Use realistic placeholder data — not lorem ipsum labels on charts.
  • Keep prototypes focused on the requested flows; avoid over-scoping.
  • Note export dependencies (PDF/PPTX/MP4) if tooling is unavailable.

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