skills/council/artisan/visual-audit/SKILL.md
Use when performing structured visual design critique of an interface. Covers hierarchy, contrast, spacing, typography, color, and component consistency with actionable fix recommendations. Do not use for design token architecture (use design-system-architecture) or animation specifications (use motion-design).
npx skillsauth add dtsong/my-claude-setup visual-auditInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Perform a structured visual design critique of an interface, producing specific actionable feedback on hierarchy, contrast, spacing, typography, color, and overall coherence.
Reads screenshots, mockups, or live implementation for visual analysis. Does not modify source code or design files. Does not generate new designs or components.
No user-provided values are used in commands or file paths. All inputs are treated as read-only analysis targets.
View the interface at arm's length (or blur it mentally). Identify:
Check the information hierarchy:
Check the type system:
Check color usage:
Check spatial consistency:
Check for visual consistency:
Compaction resilience: If context was lost during a long session, re-read the Inputs section to reconstruct what interface is being audited, check the Progress Checklist for completed steps, then resume from the earliest incomplete step.
# Visual Audit Report
## Overall Assessment
**Score:** [1-10]
**Summary:** [2-3 sentences on the interface's visual effectiveness]
## Squint Test Results
- **Primary focus:** [What draws the eye first — is this correct?]
- **Reading order:** [Clear / Unclear / Competing elements]
- **Visual noise:** [Low / Medium / High]
## Findings
### [CRITICAL] [Category] — [Finding]
**Current:** [What's happening now]
**Issue:** [Why it's a problem — cite specific principle]
**Fix:** [Specific change — exact values where possible]
### [IMPROVEMENT] [Category] — [Finding]
**Current:** [What's happening now]
**Suggestion:** [Specific improvement with rationale]
## Contrast Report
| Element | Foreground | Background | Ratio | Pass AA |
|---------|-----------|------------|-------|---------|
| Body text | #333 | #fff | 12.6:1 | Yes |
| Muted text | #999 | #fff | 2.8:1 | NO |
## Quick Wins
1. [Change that would have the biggest visual impact for the least effort]
2. [Second quick win]
3. [Third quick win]
development
Use when the council needs to surface organizational knowledge buried across multiple internal sources (wikis, design docs, ADRs, past tickets, postmortems, chat archives, code repos). Plans where to look, what to cross-reference, and how to synthesize findings into evidence the council can act on. Do not use for external market research (use competitive-analysis), library evaluation (use library-evaluation), or technology trend assessment (use technology-radar).
testing
Use to convert a Word .docx file to PDF and/or verify its page count. Triggers on: converting docx to pdf, rendering a document, checking how many pages a docx produces, or asserting a page-count constraint (e.g. a resume must stay 2 pages). Wraps LibreOffice headless conversion.
development
Security audit checklist for web applications. Use when reviewing, auditing, or hardening a web app's security posture. Covers rate limiting, auth headers, IP blocking, CORS, security middleware, input validation, file upload limits, ORM usage, and password hashing. Triggers on requests like "review security", "harden this app", "security audit", "check for vulnerabilities", or when building/reviewing API endpoints.
development
Interactive wizard to craft effective prompts using Claude Code best practices