shopify-ui-audit
Skill0 starsChanged 22 days agoMITView on GitHub
Read-only Shopify UI design audit before redesign: hierarchy, typography, spacing, buttons, breakpoints, accessibility, theme editor settings, and visual regression. Use for Shopify UI audit, design consistency, or redesign review.
In this repository33 other files it gives its agents.
- AGENTS.mdAGENTS.md
- skills/setup-project-context/templates/CLAUDE.mdCLAUDE.md
- backend-architectureSkill
- build-review-loopSkill
- capability-intakeSkill
- competitor-market-analysisSkill
- context-auditSkill
- data-analysis-insightsSkill
- data-privacy-securitySkill
- dev-agentsSkill
- dev-patternsSkill
- frontend-system-designSkill
- idea-validatorSkill
- intellectual-property-licensingSkill
- international-legal-researchSkill
- legal-document-drafterSkill
- llm-councilSkill
- make-slidesSkill
- password-authentication-securitySkill
- privacy-data-protection-lawSkill
- project-estimation-planningSkill
- project-startSkill
- rea-researchSkill
- requirements-business-analystSkill
- secrets-credential-managerSkill
- seo-tech-stackSkill
- setup-project-contextSkill
- site-incidentSkill
- sop-process-builderSkill
- task-dispatchSkill
- technical-feasibilitySkill
- tech-research-intelligenceSkill
- update-mdSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
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
- Distinctive: line 13
Read the project's local context before examining theme files.
- Distinctive: line 16
Read-only mode: do not edit, push, publish, place orders, or toggle apps during an audit.
- Distinctive: line 34
Ask for explicit approval of the individual proposed changes.
- Distinctive: line 37
Run available lint/Theme Check, accessibility checks, product and cart smoke tests, and browser console checks.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Shopify UI audit
Audit first, propose changes second, and edit only after explicit approval. This skill reviews a Shopify storefront design, not conversion performance; route behavioral funnel claims to ecom-cro and technical SEO to seo-tech-stack.
Inputs and evidence
- Identify the client, URL, desktop/mobile page templates, theme and theme version when available.
- Read the project's local context before examining theme files. Preserve client ownership and confidentiality.
- Inspect homepage, a collection, a product page, cart, and any special landing page in scope.
- Record screenshots at representative mobile and desktop widths, observed CSS/DOM evidence, and affected selectors/files where accessible. Mark any inaccessible pages or settings as unverified.
- Read-only mode: do not edit, push, publish, place orders, or toggle apps during an audit.
Checklist
- Hierarchy: primary heading, price, variant, product CTA, supporting content, and disclosure order.
- Typography: font families, scale, weights, line heights, readability, text zoom, and wrapping.
- Spacing and layout: page rhythm, component spacing, responsive containers, content density, sticky overlays, and safe areas.
- Components: buttons, form inputs, radii, colors, focus/hover/disabled states, consistent tokens.
- Accessibility: keyboard navigation, visible focus, contrast, labels, error messages, reduced motion, and touch targets.
- Shopify behavior: theme editor settings and section/block schemas, product forms, variant updates, cart events, app embeds, checkout integration, locale/currency/Markets, tracking pixels.
- Performance: CLS risks, image dimensions, font loading, and interaction delays; use field data before claiming a measurable improvement.
Required report
For each issue provide: page URL/template, observed evidence, screenshot or file/selector reference, severity, proposed change, scope and risks, confidence, and how to verify it. Distinguish observed defects from aesthetic preferences. Provide a five-item prioritized proposal before implementation.
Approval and implementation
- Ask for explicit approval of the individual proposed changes.
- On approval, apply only to a local working copy or non-live development theme.
- Preserve schema compatibility and app integrations. Compare mobile and desktop screenshots before and after.
- Run available lint/Theme Check, accessibility checks, product and cart smoke tests, and browser console checks.
- Summarize verified results and remaining risks; publish only upon separate explicit approval.
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
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.

