agentleFS
Sign inStart free
AboudjemAboudjem/ui-ux-suite/skills/design-audit/SKILL.md

design-audit

Skill8 starsChanged 7 months agoMITView on GitHub

Full project design audit that orchestrates all agents, scores across 12 dimensions, and generates a prioritized action plan. Use when the user asks to audit their design, run a design review or UX audit, review their UI, or asks how their design looks.

19 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use canvas-generative, compose-graphics 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.
  • JwuthriSkill

    canvas-generative

    Algorithmic and generative art with Canvas 2D - particles, flow fields, noise, fractals, L-systems.

    Also in 3 projects that use this

  • JwuthriSkill

    compose-graphics

    Advanced Compose visuals - Material 3 Expressive motion physics, AGSL shaders (Android 13+), Canvas/DrawScope generative, graphicsLayer effects.

    Also in 3 projects that use this

  • soilmassSkill

    motion-principles

    Motion design philosophy and principles from major design systems. Use when understanding why animations should behave certain ways, learning motion fundamentals, or aligning with design system philosophy. References M3, Carbon, Fluent, and Apple HIG principles.

    Also in 3 projects that use this

  • +9 more from Jwuthri

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 2 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 16 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run a comprehensive design audit on the current project or a specified path.

    line 8
  2. Distinctive:

    Load knowledge base: - Read the knowledge index and all 21 knowledge files:

    line 18
  3. Very specific:

    Use uiux_knowledge_query with listFiles: true to get the full inventory

    line 19
  4. Very specific:

    Every agent reads its assigned knowledge files (see knowledge/INDEX.md for the mapping)

    line 20
  5. Very specific:

    Scan project: - Use uiux_scan_project to detect framework, styling, component library, theme system

    line 22
  6. Very specific:

    Aggregate scores: - Use uiux_score_overall to calculate weighted total

    line 36

“Common” is measured: kept by at least 6 in 10 of the 16 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

/design-audit: Full Project Design Audit

Run a comprehensive design audit on the current project or a specified path.

Usage

/design-audit              # Audit current project
/design-audit /path/to/project  # Audit specific project

Flow

  1. Load knowledge base - Read the knowledge index and all 21 knowledge files:
    • Use uiux_knowledge_query with listFiles: true to get the full inventory
    • Every agent reads its assigned knowledge files (see knowledge/INDEX.md for the mapping)
    • The evidence base, principles, anti-patterns, and trends files are required reading for ALL agents
  2. Scan project - Use uiux_scan_project to detect framework, styling, component library, theme system
  3. Display profile - Show the user what was detected, ask for confirmation
  4. Dispatch agents - Launch all relevant specialist agents in parallel (each reads its knowledge files first):
    • color-analyst - Color system diagnosis
    • typography-analyst - Typography system diagnosis
    • layout-analyst - Layout, spacing, grid analysis
    • component-reviewer - Component quality and consistency
    • accessibility-auditor - WCAG compliance check
    • interaction-analyst - Motion, transitions, feedback
    • psychology-analyst - Cognitive load, hierarchy, trust
    • visual-style-advisor - Style direction evaluation
    • platform-advisor - Platform convention adherence
    • ux-flow-analyst - Navigation and user flows
    • performance-ux-analyst - Loading and perceived speed
  5. Aggregate scores - Use uiux_score_overall to calculate weighted total
  6. Generate report - Full markdown report with:
    • Project design profile
    • Score card (12 dimensions)
    • Top 20 findings ranked by impact
    • Detailed per-dimension reports
    • Prioritized action plan (quick wins / medium / major)

Agent dispatch strategy

Launch agents in parallel waves:

Wave 1 (always): color-analyst, typography-analyst, layout-analyst, accessibility-auditor, component-reviewer Wave 2 (always): interaction-analyst, psychology-analyst, visual-style-advisor Wave 3 (if applicable): platform-advisor (if mobile/cross-platform), ux-flow-analyst (if has routing), performance-ux-analyst (if has data fetching/images)

Output

Full audit report saved to design-audit-report.md in the project root. Score card displayed inline for quick overview.

Each finding may cite one or more UX laws inline (for example, [!] psychology: 12-item nav menu - violates Hick's Law, Choice Overload). When any finding carries laws, the report ends with a ## Laws of UX Coverage markdown table summarizing violation counts and worst offenders per law. Agents look up law display names and primary-source citations from knowledge/laws-of-ux.md and the uiux_laws_query MCP tool.

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