agentleFS
ghazanfar111212ghazanfar111212/claude-skills-performance-marketing/skills/design-qa/SKILL.md

design-qa

Skill0 starsChanged 37 days agoMITView on GitHub

Render-and-critique loop for landing pages - screenshot the built page in headless Chrome at mobile and desktop widths, visually critique the screenshots against the landing-page-visual-standards checklist, fix, and re-render until it passes. Use in Claude Code whenever a landing page or funnel page HTML file has been built or edited, before presenting it to the user. Trigger on "QA this page", "check the design", "does this look right", or automatically as the final step of any landing page build. Requires a local environment that can run Node + Playwright (Claude Code, not claude.ai chat).

  • Installs packages

11 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use accessibility-audit and ship.

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.
  • GitHubSkill

    accessibility-audit

    Audits actual components and routes against applicable WCAG 2.2 A/AA criteria using consumer-owned design-system evidence and repository tools. Use when asked for an accessibility audit, a11y check, keyboard or focus review, contrast check, or screen-reader verification.

    Also in 3 projects that use this

  • AWSSkill

    ship

    Finalize dev work on an issue branch — update docs, push, and open a PR.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 11 edited versions we read keep these.

  • 3

    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:

    Fix everything found. Re-render. Re-critique: Do not present the page to the user until a pass produces zero findings, or remaining …

    line 34
  2. Distinctive:

    Never skip the mobile fold screenshot - 70%+ of paid traffic is mobile and the fold decides the bounce.

    line 40
  3. Distinctive:

    If Playwright is unavailable, say so and fall back to line-by-line CSS review - but flag that visual QA didn't run.

    line 42

“Common” is measured: kept by at least 6 in 10 of the 11 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 QA - Render, Look, Fix, Repeat

Code review is not design review. This skill forces the loop a human designer runs by default: look at the rendered page, not the source.

Setup (once per machine)

npm init -y && npm install playwright
npx playwright install chromium

The loop (minimum 2 passes, typical 3)

  1. Render the page at both breakpoints:
    node scripts/screenshot.js path/to/page.html
    Produces qa/page-390.png (mobile, full page) and qa/page-1440.png (desktop, full page) plus qa/page-390-fold.png (mobile above-the-fold only).
  2. Read all three screenshots and critique them against landing-page-visual-standards/CHECKLIST.md, plus these render-only checks that source code can't reveal:
    • Above-the-fold (mobile): is the CTA fully visible? Is the headline uncomfortably wrapped (widows, 1-word lines)?
    • Spacing rhythm: do section gaps look even? Any section cramped against another?
    • Contrast in practice: is body text comfortably readable on its actual background?
    • Overflow: any horizontal scrollbar, clipped text, or element bleeding off-canvas at 390px?
    • The signature element: does it actually read as the hero moment, or does it get lost?
    • Font loading: did the display face render, or is it showing a fallback?
    • Squint test: blur your reading of the desktop shot - does the eye land on the CTA first?
  3. Fix everything found. Re-render. Re-critique. Do not present the page to the user until a pass produces zero findings, or remaining findings are explicitly listed as accepted trade-offs.
  4. Present the final screenshots alongside the file so the user sees what you saw.

Rules

  • Never skip the mobile fold screenshot - 70%+ of paid traffic is mobile and the fold decides the bounce.
  • Fix in code, never by cropping the screenshot story.
  • If Playwright is unavailable, say so and fall back to line-by-line CSS review - but flag that visual QA didn't run.

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.