Visual audit

Skill Dragoon0x/taste-skills/skills/perception/visual-audit

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.From its SKILL.md

Install

npx -y skills add Dragoon0x/taste-skills --skill visual-audit

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

3 stars3 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.9 KB, 365 tokens by cl100k_base, as published. Nobody here has run it

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

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.