agentleFS
ack-solutionsack-solutions/claude-code-ai-skills/skills/product-design/SKILL.md

product-design

Skill1 starsChanged 45 days agoMITView on GitHub

Create or revise user journeys, screens, components, and design systems. Use for UX flow design, interface design, interaction states, or visual refinement; use design-quality for a dedicated audit of existing designs.

26 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use ux-audit and i18n.

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.
  • shmehroSkill

    ux-audit

    Perform a heuristic UX audit on a UI screen, flow, or component description

    Also in 3 projects that use this

  • lbednerSkill

    i18n

    Use when a code or template change introduces a new translation message key, in either the framework CLI (aegis/i18n/locales/) or a generated project's CLI (the app/i18n/locales/ template tree). Covers adding the real English string, stubbing the same key into every other locale for parity, and the separate translation PR that later replaces placeholders with reviewed native text.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 21 edited versions we read keep these.

  • 2

    Distinctive

    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:

    When the project has a shared design specification, maintain foundations and cross-feature patterns there and link feature-specific flows …

    line 16
  2. Distinctive:

    Use the deliverable requested: flow description, wireframe, design-file changes, prototype or implementation.

    line 29

“Common” is measured: kept by at least 6 in 10 of the 21 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

Product design

Design an understandable, coherent experience for the intended audience and task. Respect the user's visual direction and established product behaviour.

Understand the design context

Inspect the relevant brief, screen/flow references, design tokens, components and target platforms. Discover the project's actual files and tools; do not assume Figma access, a particular framework or a mobile-first product. Inspect reference images before describing or recreating their details.

Identify the user's goal, primary action, information needed to decide, entry/exit points and constraints. Existing tokens and components take precedence over generic styling preferences. For a new product, propose a small coherent visual foundation before proliferating screens.

When the project has a shared design specification, maintain foundations and cross-feature patterns there and link feature-specific flows to it. Identify the approved reference revision, supported environments, acceptance targets and reviewer; do not treat a template or an unreviewed mockup as an approved design.

Design the experience

  1. Map the journey and meaningful alternatives, including cancel/back, interruption, validation and recovery. Keep technical implementation details out of product copy unless users need them to decide.
  2. Establish hierarchy, navigation and a deliberate visual direction: typography, spacing, color, imagery and motion tied to the audience and product. Premium quality comes from clear, consistent execution; choose decoration only when it serves the brief.
  3. Reuse or extend existing components with purposeful variants. Give new global components a real reuse/ownership reason. Keep one authoritative token system.
  4. Design the relevant loading, empty, error, disabled, success and permission states. Use realistic variable-length content, not only ideal mock data.
  5. Account for target widths, safe areas, keyboard, scrolling, text scaling, locales, assistive technology and reduced motion. Do not shrink critical text or targets merely to match a mockup.
  6. Explain trust signals, prices, consent and irreversible actions accurately. Label unverified claims and sponsored content according to product requirements; avoid deceptive urgency or hidden choices.

Produce and inspect the result

Use the deliverable requested: flow description, wireframe, design-file changes, prototype or implementation. Use available tool-specific guidance for the selected medium. Inspect the actual rendered result when possible, checking affected states and representative widths. A source-code read is not visual inspection.

Record new business behaviour as a requirement proposal rather than silently introducing it through a screen. Continue requested implementation when authorized; a design-only request does not authorize app changes or publishing.

Deliver

Link the design/artifact, explain the main choices, identify reused or added components, and report the visual/interaction checks actually performed. Flag open behaviours and untested platforms. Self-review is part of creation; a dedicated design-quality pass can independently compare the result with requirements.

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.