agentleFS
Sign inStart free
leighstillardleighstillard/coach-ship-skills/skills/design-check/SKILL.md

design-check

Skill2 starsChanged 5 months agoMITView on GitHub

Visual and UX review for user-visible changes: frontend components, HTML/CSS, templates, dashboards, rendered docs, emails, and CLI output formatting. Use as part of /ship when a diff touches UI/human-facing output. If nothing user-visible changed, explicitly mark not applicable and stop.

3 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions3 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 3

    1. arcasilesgroup/ai-engineering★ 65same name
    2. gihwan-dev/claude-code-gui★ 1same name
    3. marcin-urbanski/claude-skills★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository5 other files it gives its agents.

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 3 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:

    Do not review design from source alone.

    line 14
  2. Distinctive:

    If dark mode or responsive layouts exist, sample them.

    line 39

“Common” is measured: kept by at least 6 in 10 of the 3 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 Check

Step 0: Applicability

Inspect the diff. If no human-facing surface changed, say DESIGN N/A — no user-visible surface touched and stop.

Human-facing surfaces include web/mobile UI, templates, CSS, generated documents/emails, screenshots, terminal output, errors users see, and rendered docs.

Step 1: Render the actual output

Do not review design from source alone.

  • Web UI: run the app/storybook and capture desktop plus narrow mobile screenshots.
  • CLI/errors: run commands that show normal, empty, long, and error output.
  • Docs/emails/PDFs: render the final artifact.

Step 2: Review

Check:

  • Consistency with existing components/tokens/patterns.
  • Loading/empty/error/overflow/long-text states.
  • Keyboard/focus and accessible names for interactive elements.
  • Contrast and non-colour-only meaning.
  • Alignment, density, and avoidance of one-off AI-looking decoration.
  • Neighbouring surfaces affected by shared component changes.

Step 3: Fix or flag

Fix mechanical defects directly when safe. Flag judgement calls with screenshot/output evidence and a one-line recommendation. Do not redesign broadly without instruction.

Verdict

  • PASS — screenshots/output evidence included.
  • PASS WITH NOTES — non-blocking judgement calls listed.
  • FAIL — blocking design/accessibility/usability defects listed.
  • DESIGN N/A — no user-visible surface changed.

Gotchas

  • Source review is not design review.
  • If dark mode or responsive layouts exist, sample them.
  • CLI output is design when humans read it.

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