agentleFS
TJM-NZTJM-NZ/claude-skills/design/SKILL.md

design

Skill0 starsChanged 10 days agoMITView on GitHub

Design a page, section or component, including layout, states, responsive behaviour and motion. Starts from the screen's job, proposes two distinct visual directions, refines the chosen one, and builds only after approval. Aims for a deliberate, product-specific result, not a template.

197 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use banner-design, ui-styling and 9 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.
  • seikaikyoSkill

    banner-design

    Design banners for social media, ads, website heroes, creative assets, and print. Multiple art direction options with optional generated or supplied visuals. Actions: design, create, generate banner. Platforms: Facebook, Twitter/X, LinkedIn, YouTube, Instagram, Google Display, website hero, print. Styles: minimalist, gradient, bold typography, photo-based, illustrated, geometric, retro, glassmorphism, 3D, neon, duotone, editorial, collage.

    Also in 38 projects that use this

  • MicrosoftSkill

    ui-styling

    Guide for the visual style, structure, and shared building blocks used by Semantic Link Labs interactive UI tools (HTML widgets and anywidget-based widgets). Use this when adding a new interactive UI, modifying an existing one, or adding shared visual components.

    Also in 39 projects that use this

  • seikaikyoSkill

    brand

    Brand voice, visual identity, messaging frameworks, asset management, brand consistency. Activate for branded content, tone of voice, marketing assets, brand compliance, style guides.

    Also in 43 projects that use this

  • mayankjain1815-commitsSkill

    infra-audit

    Reads docker-compose, env files, ORM configs, and connection strings to map current infrastructure. Flags missing layers (cache, queue, analytics) based on observed access patterns. Outputs a structured infrastructure manifest.

    Also in 3 projects that use this

  • JetBrainsSkill

    slides

    Create and edit presentation slide decks (`.pptx`) with PptxGenJS and render/validation utilities. Use when tasks involve building a new PowerPoint deck, recreating slides from screenshots/PDFs/reference decks, modifying slide content while preserving editable output, adding charts/diagrams/visuals, or diagnosing layout issues such as overflow, overlaps, and font substitution.

    Also in 42 projects that use this

  • henrikthome-archSkill

    infra

    Manage all infrastructure for the Volos school project — Render (API backend), Cloudflare (DNS + Pages frontend), PostgreSQL database, and GitHub Actions workflows.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 174 edited versions we read keep these.

  • 6

    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:

    Read product docs and the design system if present (follow it strictly for colour, type, spacing, shape and component states).

    line 15
  2. Distinctive:

    Read the files to be designed, the tokens and nearby components.

    line 31
  3. Distinctive:

    Ask which direction, or which elements of each.

    line 45
  4. Distinctive:

    Use the project's stack and tokens, never raw values that duplicate a token.

    line 53
  5. Distinctive:

    Run the project's typecheck, lint and build.

    line 55
  6. Distinctive:

    If a browser tool is available, check desktop and mobile widths, every state, keyboard navigation and reduced motion.

    line 56
  7. Distinctive:

    Don't replace one stock look with another.

    line 63

“Common” is measured: kept by at least 6 in 10 of the 174 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

Designer-engineer. Design for the job the screen does, then give it identity. Present a direction before any code; build only after the user approves.

Related: design-system for tokens (run first if none exist) | de-slop to audit the result for generic defaults | accessibility for compliance | copywrite for the words.

Step 1: Brief

Read product docs and the design system if present (follow it strictly for colour, type, spacing, shape and component states). If there is no system, offer design-system first, or continue using the codebase's existing tokens.

Establish, asking only what the repo can't answer:

QuestionWhy
What is the screen's job? Who uses it, and what must they do or decide?Layout follows the task
What is the primary action?Decides visual weight
What is the real content, and how much (3 items or 300)?Layouts break on real data
Context: marketing page, product UI, dashboard, content?Sets density and tone
Constraints: devices, performance, accessibility target, brand assetsRules out options early

Find the product's domain and what visual language it already has (see references/principles.md, Identity).

Step 2: Audit the target

Read the files to be designed, the tokens and nearby components. Note what already works and should stay. For motion work, list existing transitions and animations: which are generic, which are missing (state changes with no feedback), which slow the user down.

Step 3: Two directions (before any code)

Propose two directions that differ in substance, not variations on one theme. Each has:

  1. Concept name (2-3 words)
  2. Mood: one sentence
  3. Domain reference: a real object, space, material or printed form it draws from, not other websites
  4. Layout approach: reading path, hierarchy, density, where it breaks the grid and why. Include a rough text sketch of the structure.
  5. Key visual moves: 3-5 specific choices ("8px accent rule on the left edge of each entry", not "add visual interest")
  6. States and motion: what changes on interaction and what it communicates
  7. Trade-off: what this direction costs (density, effort, risk)

Ask which direction, or which elements of each.

Step 4: Refine

For the chosen direction specify: exact layout and spacing using tokens | type and colour use, including where colour is absent | all states (references/states.md) | responsive behaviour, meaning what the mobile version actually is, not "stack vertically" | motion (references/motion.md) | accessibility (focus order, contrast, targets, labels) | the real copy, or a note to run copywrite.

Step 5: Build (only after approval)

Use the project's stack and tokens, never raw values that duplicate a token. Then:

  1. Run the project's typecheck, lint and build.
  2. If a browser tool is available, check desktop and mobile widths, every state, keyboard navigation and reduced motion. Say "not visually verified" otherwise.
  3. Suggest de-slop on the result and accessibility for compliance.

Rules

  • Usability first, distinctiveness second. A memorable screen nobody can use is a failure.
  • Question defaults, don't ban patterns. A three-column grid is right for three parallel items; the test is whether the section would exist if you started from the user's task.
  • Don't replace one stock look with another. A "brutalist" or "editorial" costume is still a template.
  • Real content in every mock: long names, empty lists, many items.
  • Make no code changes until the user approves the refined design.

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.