How to use
- Copy the installation command and review the source package before installing it in your own agent environment.
- Check the source document for required tools, credentials and supported hosts.
- Describe your input and desired deliverable; review the output against the source material.
npx skills add https://github.com/plugin87/ux-ui-agent-skills --skill design-qaBefore you start
- Installation does not include a model subscription, API allowance or permission to access your files.
- Repository stars and installation counts describe activity, not an independent quality or security test.
Rendered from the source repository. Headings, examples, code, tables, links, and referenced images are preserved.
Skill: Design QA
Requirements
This skill needs the full UX/UI Agent Skills kit: the gates, the references and the design-system library. Install it with npx ux-ui-agent-skills@3.1.1 init or as the Claude Code plugin. npx skills@1.7.6 add copies the skill folder and nothing else. Installed that way, this skill runs in guidance-only mode: no gate runs, so it gives no verdict.
Step 0: is the kit here? Check once:ls ${CLAUDE_SKILL_DIR}/../../../tokens >/dev/null 2>&1 && echo KIT_OK || echo KIT_MISSINGOnKIT_MISSING, open your reply with: "Guidance-only mode: the UX/UI Agent Skills kit is not installed here, so no gate ran and nothing below is measured." Then work from this file and general practice, under three rules. Do not guess or cite the contents of a kit file you could not open. State no measured number (no contrast ratio, no N/N, no "passes WCAG"): write "not verified" where one would go. End with a lineSkipped (kit not installed):that names every gate script this file tells you to run, then the install command above.
Stand up the automated + manual gates that stop quality from regressing.
Steps
- Read
${CLAUDE_SKILL_DIR}/../../../workflows/design-qa.md(the QA pyramid: token/lint gates → automated a11y → visual regression → manual a11y). - Wire the fast gates first (every commit/PR):
python3 ${CLAUDE_SKILL_DIR}/../../../scripts/validate_tokens.py,python3 ${CLAUDE_SKILL_DIR}/../../../scripts/validate_contrast.py(batch WCAG over the token pairs), andpython3 ${CLAUDE_SKILL_DIR}/../../../scripts/lint_hardcodes.py <src>(no raw hex/px/timing in component code). The repo's.github/workflows/ci.ymlruns these. - Add automated a11y (axe-core / Pa11y) over each component's states (error/loading/disabled/expanded/selected), zero serious/critical to merge. Run the real-render contrast gate
node ${CLAUDE_SKILL_DIR}/../../../scripts/gate.mjs measure_render.mjs <file.html>(and--dark). It opens the page in headless Chromium, disables transitions, and measures the true computed-style + alpha-composited contrast of every text element (catches what static token checks miss). - Add visual regression snapshots across variants × sizes × states × light/dark + key breakpoints + RTL; freeze animations + deterministic data.
- Sign off the manual a11y checklist per release (keyboard, screen reader, 400% reflow, 200% text-spacing, reduced-motion, forced-colors;
${CLAUDE_SKILL_DIR}/../../../accessibility/*).
Verification (definition of done)
- An unreviewed PR cannot introduce an unresolved token alias, a contrast failure, a raw hex/px, or an axe violation: a gate blocks each.
- Snapshots cover dark mode + RTL + the semantic-changing states, not just the happy path.
- Manual a11y checklist signed off for the release.
