letstakeawalk/design-critique
dot_claude/skills/design-critique/SKILL.md
UI/UX design critique before building. Describe what you want, get feedback on layout, flow, accessibility, and patterns. Use before implementing frontend features.
development
Updated Apr 23, 2026
$ install --global
skillsauthnpx skillsauth add letstakeawalk/dotfiles design-critiqueInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 23, 2026, 12:19 PM62.3s1 file scanned
SKILL.md
- name:
- design-critique
- description:
- UI/UX design critique before building. Describe what you want, get feedback on layout, flow, accessibility, and patterns. Use before implementing frontend features.
- allowed-tools:
- Read, Glob, Grep
- argument-hint:
- <description of UI to critique> or <file path to review>
Task
Provide UI/UX design critique before code is written. Catch layout issues, flow problems, accessibility gaps, and pattern mismatches early — when they're cheap to fix.
When Invoked
Parse $ARGUMENTS:
- Description (natural language): critique the proposed design
- File path (e.g.,
src/routes/+page.svelte): read and critique existing UI - Mockup/screenshot path: read image and critique visual design
- No arguments: ask what to critique
Critique Framework
1. Layout & Hierarchy
- Is visual hierarchy clear? Most important action obvious?
- Spacing and alignment consistent?
- Does it work at different viewport sizes?
- Is there visual clutter that can be removed?
2. User Flow
- Can user complete primary task in minimum steps?
- Are error states and empty states handled?
- Is navigation between states clear?
- Any dead ends or confusing transitions?
3. Accessibility
- Sufficient color contrast (WCAG AA minimum)?
- Keyboard navigable? Focus order logical?
- Screen reader friendly? Labels on interactive elements?
- Touch targets large enough (44x44px minimum)?
4. Patterns & Consistency
- Following established design system / component library?
- Consistent with rest of the app?
- Using standard patterns users already know?
- Any anti-patterns? (e.g., mystery meat navigation, hidden actions)
5. Copy & Messaging
- Labels clear and concise?
- Error messages actionable? (what happened + how to fix)
- Empty states guide user to next action?
- No jargon users won't understand?
Output Format
## Design Critique: [component/page name]
### Summary
[1-2 sentence overall assessment]
### Findings
1. [area]: [severity]: [issue]. [suggestion].
2. ...
### Strengths
- [what works well — reinforce good decisions]
### Recommendation
[build as-is | revise before building | needs major rethink]
Severity: blocker (will confuse users), risk (suboptimal UX), nit (minor polish).
Rules
- Critique the design, not the designer
- Be specific — "button is hard to find" → "primary CTA below fold on mobile, move above hero"
- Always mention what works well, not just problems
- If reviewing code, focus on UX impact, not code quality (that's
/review) - If no major issues, say so — don't manufacture problems
- For code quality issues, use
/reviewinstead — this skill is UX-only
Related Skills
letstakeawalk/test-audit
development
VerifiedTrustedCommunity
Analyze test coverage gaps — untested public APIs, missing edge cases, uncovered error paths. Spawns the test-analyzer agent.
SKILL.mdUpdated Apr 23, 2026
letstakeawalk/dot_claude/skills/review
tools
VerifiedTrustedCommunity
--- name: review description: "Code review — detects language and spawns the appropriate reviewer agent. Works with diffs, staged changes, files, or directories." allowed-tools: Read, Glob, Grep, Edit, Write, Bash(git diff:*), Bash(git log:*), Bash(git status:*), Bash(git branch:*) argument-hint: [file/dir|staged|lang] [security|performance|idioms|bugs|tests] [--fix] [--deep] --- ## Context - Branch: !`git branch --show-current` - Changed files: !`git diff --name-only HEAD` - Diff stats: !`git
SKILL.mdUpdated Apr 23, 2026
letstakeawalk/remember
testing
VerifiedTrustedCommunity
This skill should be used when the user says 'remember this', 'save this for later', 'note this down', 'always do X', 'never do Y', or wants to persist a decision or preference across sessions.
SKILL.mdUpdated Apr 23, 2026
letstakeawalk/dot_claude/skills/refactor
tools
VerifiedTrustedCommunity
--- name: refactor description: "Identify and apply refactoring opportunities — supports full analysis, cleanup, simplify, structure, naming, and DRY focus modes." allowed-tools: Read, Glob, Grep, Edit, Write, Bash(git diff:*), Bash(git branch:*) argument-hint: [file/dir|staged] [full|cleanup|simplify|structure|naming|dry] --- ## Context - Branch: !`git branch --show-current` - Changed files: !`git diff --name-only HEAD` - Diff stats: !`git diff --stat HEAD` ## Task Analyze code for refactori
SKILL.mdUpdated Apr 23, 2026