agentsclimarketplace

Interface quality audit

Skill thanhaq/interface-compass-skills/skills/interface-quality-audit

Frontend design skill pack for AI coding agents: briefs, design systems, audits, motion, copy, and ship checks.

Install
npx -y skills add thanhaq/interface-compass-skills --skill interface-quality-audit

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

2 things to look at

  • 15 days oldThe repository was created 15 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • 0 stars0 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.

What its author says it does

Copied from the file, not written here

Audit existing frontend interfaces for design quality, usability, accessibility, and implementation risks. Use when Codex needs to review screenshots or source code, run static UI heuristics, identify layout and hierarchy problems, prioritize fixes, and produce a concrete repair plan.

SKILL.md

1.5 KB, 262 tokens by cl100k_base, as published. Nobody here has run it

Interface Quality Audit

Goal

Find the highest-leverage interface problems and turn them into actionable fixes. Lead with evidence, not taste declarations.

Workflow

  1. Inspect the rendered UI when possible. Use screenshots across desktop and mobile for visual work.
  2. Inspect source files for implementation patterns that can create layout, accessibility, or polish regressions.
  3. Run the static helper when a local project is available:
node skills/interface-quality-audit/scripts/static-ui-audit.mjs <project-path>
  1. Score findings with references/rubric.md.
  2. Report prioritized findings first, then a short repair plan.
  3. If asked to fix the UI, implement the top issues and verify again.

Finding Format

P1/P2/P3 - Title
Evidence:
Impact:
Fix:
Verification:

Severity

  • P1: Blocks comprehension, task completion, accessibility, or release confidence.
  • P2: Creates visible confusion, weak hierarchy, layout fragility, or repeated user friction.
  • P3: Polish improvement with limited behavioral risk.

Resources

  • Use scripts/static-ui-audit.mjs for a quick source scan.
  • Read references/rubric.md for review criteria.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.