agentleFS
ek0212ek0212/agent-ready-repo-kit/skills/frontend-design/SKILL.md

frontend-design

Skill0 starsChanged 4 months agoMITView on GitHub

Create distinctive production frontend UI with clear visual direction, emotional intent, responsive behavior, and accessible interaction states. Use when user says "build a landing page", "design a dashboard", "create a component", "make a web app", "build me a UI", "make this feel premium", or asks for polished web design without exact Figma source.

187 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use instantly-campaign, albert-dm and 10 more.

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.
  • yawningwhaleAISkill

    instantly-campaign

    Create a new Instantly cold-email campaign in the proven 5-email structure of the user's top-performing campaign (~16% reply rate). Use when the user wants to launch a new outbound campaign, write a cold email sequence, create an Instantly campaign, draft outreach for a new service or niche, or set up a sales sequence.

    Also in 6 projects that use this

  • yawningwhaleAISkill

    albert-dm

    Reply to DMs and messages the way Albert would. Use when the user asks "how would Albert reply to this", pastes a conversation and wants an Albert-style response, or asks you to draft/write a DM in Albert's voice. Albert sells AI voice agents / automations to local service businesses (Go High Level, lead follow-up, bookings).

    Also in 5 projects that use this

  • naman10parikhSkill

    ecosystem-reference

    Quick-access directory of Claude Code ecosystem repos, skills, plugins, MCPs, and patterns. Use when improving the harness.

    Also in 5 projects that use this

  • naman10parikhSkill

    fractal-delegation

    Also in 5 projects that use this

  • julianoczkowskiSkill

    brief-to-tasks

    Break a design brief into an ordered checklist of independently buildable tasks using vertical slices. Saves as a markdown checklist. Use when user wants to break down work, create tasks from a brief, plan implementation order, or mentions "tasks" or "breakdown".

    Also in 7 projects that use this

  • SeifBenayedSkill

    file-reading

    Use this skill when a file has been uploaded but its content is NOT in your context — only its path at /mnt/user-data/uploads/ is listed in an uploaded_files block. This skill is a router: it tells you which tool to use for each file type (pdf, docx, xlsx, csv, json, images, archives, ebooks) so you read the right amount the right way instead of blindly running cat on a binary. Triggers: any mention of /mnt/user-data/uploads/, an uploaded_files section, a file_path tag, or a user asking about an uploaded file you have not yet read. Do NOT use this skill if the file content is already visible in your context inside a documents block — you already have it.

    Also in 6 projects that use this

  • +6 more from naman10parikh

The file

We split this skill into the rules it gives an agent

10 rules. 0 are common, 9 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 181 edited versions we read keep these.

  • 9

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    Use for design-led web pages, components, apps, dashboards, and redesigns.

    line 11
  2. Distinctive:

    If brief vague, choose concrete audience and page job from repository context.

    line 26
  3. Distinctive:

    No manufactured urgency or engagement pattern against user goal.

    line 51
  4. Distinctive:

    Keep UI copy active, task-led, and consistent across control and state.

    line 60
  5. Distinctive:

    Run page. Check representative desktop and mobile widths.

    line 66
  6. Distinctive:

    No brand system: derive one restrained direction from product context.

    line 77
  7. Distinctive:

    No browser access: implement static pass and mark visual verification incomplete.

    line 79
  8. Distinctive:

    No text or navigation overflow.

    line 88
  9. Distinctive:

    All lifecycle states in scope handled.

    line 91
  10. Distinctive:

    Use direct simple sentences.

    line 96

“Common” is measured: kept by at least 6 in 10 of the 181 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

Build working UI with specific point of view, one justified signature move, and disciplined polish.

Scope

Use for design-led web pages, components, apps, dashboards, and redesigns. Use figma-to-ui when exact Figma selection defines target. Skip backend-only work and tiny visual bug fixes with no design judgment.

Inputs

  • Product, audience, page job, and primary action.
  • Existing repository, components, tokens, content, and constraints.
  • Brand cues, references, accessibility needs, and supported viewports.
  • Required states, data, routing, and interactions.

User and repository own product facts. Use real supplied content. Mark invented sample content.

Workflow

Step 1: Ground Brief

If brief vague, choose concrete audience and page job from repository context. State assumption. Pull cues from subject world: materials, tools, artifacts, language, rituals, and constraints.

Name target feeling at entry, core action, success, and failure. Name trust level. High-stakes flows favor calm feedback, visible state, reversible action, and clear confirmation.

Step 2: Set Direction

Before code, define:

  • Palette: four to six colors with roles.
  • Type: display, body, optional utility.
  • Layout: composition and responsive rule.
  • Signature: one remembered element.
  • Risk: one deliberate move and why it fits.
  • Emotion: target feeling and trust requirement.

Reject direction that fits any similar product. Avoid default purple gradients, generic SaaS cards, ornamental numbering, and copied trend palettes unless brief supports them.

Step 3: Design Behavior

  • First useful screen shows value and next action.
  • Early real success precedes optional setup.
  • Pending, success, failure, empty, disabled, and recovery states stay explicit.
  • Feedback is immediate and proportional.
  • Motion explains hierarchy, state, or cause. It never blocks progress.
  • Milestone feedback stays brief and skippable.
  • No manufactured urgency or engagement pattern against user goal.

Step 4: Build In Existing Stack

Reuse repository framework, components, tokens, icons, routing, and styling. Ask before new dependency or styling system.

  • Derive type, color, layout, texture, and motion from direction.
  • Let structure encode meaning.
  • Spend boldness in one place; keep rest quiet.
  • Keep UI copy active, task-led, and consistent across control and state.
  • Explain errors with cause and recovery.
  • Preserve semantic HTML, keyboard access, focus, contrast, alt text, and reduced motion.

Step 5: Refine In Browser

Run page. Check representative desktop and mobile widths. Fix in order:

  1. Information hierarchy and primary action.
  2. Layout, overflow, and responsive behavior.
  3. Type, spacing, alignment, and component states.
  4. Color, border, shadow, texture, and motion.

Cut decoration that does not support subject, hierarchy, trust, or feedback.

Fallbacks

  • No brand system: derive one restrained direction from product context; state choices.
  • High-stakes or enterprise flow: favor familiar patterns and clarity over aesthetic risk.
  • No browser access: implement static pass and mark visual verification incomplete.
  • Existing design system conflicts with concept: preserve system unless user approves broader change.

Verify

  • UI works, not mock-only.
  • Primary action clear.
  • Direction specific to subject.
  • Desktop and mobile work.
  • No text or navigation overflow.
  • Keyboard focus visible.
  • Reduced motion respected.
  • All lifecycle states in scope handled.
  • Browser comparison completed or named as limit.

Writing

Use direct simple sentences. Skip rhetorical flourishes. Avoid X-not-Y contrasts, self-answering rhetorical questions, em dashes, alliterative three-part phrases, vague inspirational pivots, unsourced claims, and unverified quotes.

Output

Return working code. Report direction, files changed, route, checks, viewports, assumptions, and known limits.

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.