mikeparcewski/ux-review
skills/product/ux-review/SKILL.md
Use when evaluating UX quality — user flows, information architecture, user research synthesis, personas, and usability assessment. Also covers generative UX flow design from requirements. NOT for visual design consistency (use visual-review) or accessibility code audits (use product/accessibility).
$ install --global
skillsauthnpx skillsauth add mikeparcewski/wicked-garden ux-reviewInstall 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: May 8, 2026, 5:54 AM149.0s1 file scanned
SKILL.md
- name:
- ux-review
- description:
- |
- phase_relevance:
- ["clarify", "design", "review"]
- archetype_relevance:
- ["*"]
UX Review Skill
UX and design quality thinking embedded throughout delivery.
Core Concept
Good UX is how we build trust. Don't wait for polish phase—design with users in mind from the start.
Four Focus Areas
| Area | Expert | Focus | |------|--------|-------| | User Flows | UX Designer | Experience design, interactions, IA | | Visual Design | UI Reviewer | Consistency, components, design system | | Accessibility | A11y Expert | WCAG, keyboard, screen readers | | User Research | User Researcher | Needs, personas, journeys |
Commands
| Command | Purpose |
|---------|---------|
| /wicked-garden:product:ux-review | Run UX review (auto-detect focus) |
| /wicked-garden:product:ux-review --focus flows | User flow analysis |
| /wicked-garden:product:ux-review --focus ui | Visual design review |
| /wicked-garden:product:ux-review --focus a11y | Accessibility audit |
| /wicked-garden:product:ux-review --focus research | User research |
| /wicked-garden:product:ux-review --focus all | Comprehensive review |
Usage
# Auto-detect what to review
/wicked-garden:product:ux-review src/components/Dashboard
# Focus on accessibility
/wicked-garden:product:ux-review src/components/Form --focus a11y
# User research on requirements
/wicked-garden:product:ux-review outcome.md --focus research
# Comprehensive review
/wicked-garden:product:ux-review src/app --focus all
# Quick triage
/wicked-garden:product:ux-review src/components --quick
Output
Review produces:
- Issues: Critical / Major / Minor findings
- Recommendations: Specific, actionable improvements
- Evidence: Screenshots, code snippets, WCAG citations
- Tasks: Issues tracked via native TaskCreate for follow-up
Review Types
User Flow Review
- Happy path clarity
- Error handling
- User mental models
- Interaction patterns
- Information architecture
Visual Design Review
- Color consistency
- Typography scale
- Spacing system
- Component patterns
- Responsive design
- Visual polish
Accessibility Audit
- WCAG 2.1 Level AA compliance
- Keyboard navigation
- Screen reader support
- Semantic HTML
- ARIA patterns
- Color contrast
User Research
- User needs discovery
- Persona creation
- Journey mapping
- Problem validation
- Jobs to Be Done
Integration
Works with:
- wicked-crew: Auto-suggested after phases
- Read tool: Analyze screenshots directly; capture via browser automation if available
- Native tasks: Issue tracking via TaskCreate with
metadata.event_type="task" - wicked-brain:memory: Design system memory
- wicked-garden:search: Pattern discovery
Phase Integration
| Phase | Suggested Review | Expert | |-------|------------------|--------| | Clarify | User research | User Researcher | | Design | User flows + IA | UX Designer | | Build | A11y + UI consistency | A11y Expert + UI Reviewer | | Review | Comprehensive review | All experts |
Quick Checks
For fast feedback:
# Quick a11y scan
/wicked-garden:product:ux-review {file} --focus a11y --quick
# Quick UI consistency
/wicked-garden:product:ux-review {file} --focus ui --quick
# Quick flow check
/wicked-garden:product:ux-review {file} --focus flows --quick
Common Findings
UX: Unclear flows, missing error states, confusing navigation UI: Color/typography/spacing inconsistencies, missing states A11y: Missing alt text, poor contrast, no keyboard access Research: Assumed needs, missing personas, unmapped journeys
Output Artifacts
ux-review.md- Findings and recommendationspersonas/,journeys/- Research artifactsa11y-report.md- Accessibility results- Native tasks for tracking (TaskCreate with
metadata.event_type="task")
Best Practices
- Review early - catch issues in design phase
- Focus on users - always ask "how does this help?"
- Be specific - give actionable recommendations
- Cite standards - reference WCAG, design system
- Track issues - use native TaskCreate for follow-through
Getting Started
# Comprehensive quick review
/wicked-garden:product:ux-review src/ --focus all --quick
# Accessibility deep dive
/wicked-garden:product:ux-review src/components --focus a11y
# User research
/wicked-garden:product:ux-review outcome.md --focus research
Related Skills
mikeparcewski/skills/engineering/large-scale-migration
development
VerifiedTrustedCommunity
--- name: large-scale-migration description: How to execute a LARGE MECHANICAL change across any codebase with LEVERAGE instead of an agent-grind or hand-edits — a cross-cutting migration, refactor, rename, dialect/framework/DB port, library adoption, or bulk transform. The map→transform→gate pattern: a deterministic transform driven by a source-of-truth map, proven by a differential-equivalence gate. Use when the work is "migrate all X to Y", "rename Z everywhere", "port to a new DB/dialect/fra
8SKILL.mdUpdated Jun 3, 2026
mikeparcewski/wicked-garden:classify
testing
VerifiedTrustedCommunity
v11 LLM-based work-shape classifier. Replaces the regex archetype detector with the model's own reasoning. Reads the user's prompt, picks the right archetype(s) from the catalog, identifies signals (blast_radius, novelty, reversibility, etc.), and persists to SessionState so subsequent turns steer correctly. Use when: the prompt_submit hook emitted a `<wg classify-due />` directive, OR explicitly invoked at session start, OR when re-classifying after the user changes scope mid-session.
8SKILL.mdUpdated May 26, 2026
mikeparcewski/wicked-garden:archetype
tools
VerifiedTrustedCommunity
v11 work-shape archetype runner. When a prompt has been routed to one of the 9 archetypes (triage, explore, specify, decide, ship, review, incident, build, migrate), this skill is the entry point. It picks the right per-archetype playbook from refs/ and executes the phase shape declared in `.claude-plugin/archetypes.json`. Use when: a `<wg archetype="X">` or `<wg archetypes>` system-reminder tag appears, an explicit "let's run the X archetype" request, or when one of the per-archetype slash commands resolves to this skill.
8SKILL.mdUpdated May 8, 2026
mikeparcewski/intent
development
VerifiedTrustedCommunity
Show or set the session intent variable. Intent gates how loud the framework is — simple-edit (silent), feature/research (synthesis directive), rigor (full crew context). Auto-detected on turn 1; this skill overrides explicitly. Sticky for the session. Use when: "set intent", "intent override", "/wicked-garden:intent", "make the framework quiet", "force rigor", "what's my intent".
8SKILL.mdUpdated May 6, 2026