agentleFS
Sign inStart free
Dragoon0xDragoon0x/taste-skills/skills/perception/visual-audit/SKILL.md

visual-audit

Skill5 starsChanged 8 months agoMITView on GitHub

The 10-second design audit. Look at any design and name what's working and what's not within seconds. Trains rapid pattern recognition for hierarchy, spacing, type, and color. Use when evaluating designs quickly, giving first-impression feedback, or building perception speed.

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    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:

    Look at any design and name what's working and what's not.

    line 8
  2. Distinctive:

    MUST identify the primary visual element within 3 seconds of looking

    line 18
  3. Distinctive:

    MUST name 3 specific observations (not feelings) within 10 seconds

    line 19
  4. Distinctive:

    MUST distinguish between observations ("the CTA is the same weight as the nav") and reactions ("it looks cluttered")

    line 20
  5. Distinctive:

    NEVER use vague words: clean, nice, modern, sleek, beautiful, stunning, minimal, bold

    line 21
  6. Distinctive:

    SHOULD replace every vague word with a specific observation about hierarchy, weight, rhythm, density, or contrast

    line 22

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

Visual Audit

Look at any design and name what's working and what's not. Fast.

How to use

  • /visual-audit Apply rapid perception constraints to evaluate any design in this conversation.
  • /visual-audit <url or screenshot> Run a 10-second audit on the described or provided design.

Constraints

The 10-Second Rule

  • MUST identify the primary visual element within 3 seconds of looking
  • MUST name 3 specific observations (not feelings) within 10 seconds
  • MUST distinguish between observations ("the CTA is the same weight as the nav") and reactions ("it looks cluttered")
  • NEVER use vague words: clean, nice, modern, sleek, beautiful, stunning, minimal, bold
  • SHOULD replace every vague word with a specific observation about hierarchy, weight, rhythm, density, or contrast

What to Observe

  • Where does the eye go first? Is that intentional?
  • How many type sizes are visible? Is there a clear scale?
  • What's the spacing system? Is it consistent?
  • How many colors are in use? What roles do they play?
  • What's the density? Does it match the use case?
  • What states are visible? What states are missing?

Output Structure

  • First: name the design's apparent intent (what it's trying to do)
  • Second: name what's working (specific decisions, not aesthetics)
  • Third: name what's not working (specific decisions, with reasoning)
  • Fourth: one change that would have the most impact

Anti-Patterns

  • Listing only positive observations to be polite
  • Jumping to solutions before diagnosing the problem
  • Evaluating aesthetics instead of decisions
  • Giving feedback about style preferences rather than quality signals

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.

Reviews can't be read right now.

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