Roast
Multi-perspective UI/UX roasting workflow with iterative improvement cyclesFrom its SKILL.md
npx -y skills add muspelheim/claude-roaster --skill roastAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
7.4 KB, as published. Nobody here has run it
π₯ UI/UX Roast Skill
Brutally honest UI/UX critique with multi-perspective analysis and iterative improvement.
Command Syntax
/roast [mode] [target] [options]
# Modes
screen <target> # Single screen analysis (default)
flow <target> # Multi-screen user journey
audit # Full application review
# Options
--iterations=<1-10> # Roast cycles (default: 3)
--focus=<area> # Priority: a11y|conversion|usability|visual|implementation
--output=<path> # Output directory (default: reports/roast/)
--fix=<mode> # Fix handling: auto|report|ask (default: ask)
Examples
/roast screen login # Roast login screen
/roast screen settings --focus=a11y # Focus on accessibility
/roast flow checkout --iterations=5 # 5-iteration checkout flow
/roast flow onboarding --fix=auto # Auto-fix issues found
/roast audit # Full app audit
Execution Workflow
1. Immediate Start
Do NOT ask questions upfront. Apply smart defaults and begin immediately.
π₯ ROAST SESSION STARTED
ββ Mode: screen
ββ Target: login
ββ Iterations: 3
ββ Focus: balanced
ββ Output: reports/roast/
2. Screenshot Capture
Auto-detect screenshot method:
πΈ Capturing screenshot...
ββ Xcode MCP: [β found | β not found]
ββ Playwright MCP: [β found | β not found]
ββ Using: [xcode | playwright | manual upload]
Detection priority:
mcp__xcodebuildmcp__screenshotβ iOS/macOSmcp__playwright__browser_take_screenshotβ Web- Request user upload β Fallback
CRITICAL: Always specify the output path explicitly!
// First, ensure directory exists
Bash: mkdir -p reports/roast/screenshots
// Playwright MCP - specify filename parameter
mcp__playwright__browser_take_screenshot({
type: "png",
filename: "reports/roast/screenshots/[target]_[iteration].png"
})
// Xcode MCP - specify path parameter
mcp__xcodebuildmcp__screenshot({
path: "reports/roast/screenshots/[target]_[iteration].png"
})
Without explicit path, screenshots go to wrong location (e.g., .playwright-mcp/).
3. Parallel Analysis with Progress
Show real-time progress:
π₯ Roasting: login (1/3)
ββ πΈ Screenshot β
ββ π¨ Designer: analyzing...
ββ π» Developer: analyzing...
ββ π€ User: analyzing...
ββ βΏ A11y: analyzing...
ββ π Marketing: analyzing...
Launch agents in parallel:
// All 5 agents run simultaneously
Task(subagent_type="claude-roaster:roaster-designer", prompt="...")
Task(subagent_type="claude-roaster:roaster-developer", prompt="...")
Task(subagent_type="claude-roaster:roaster-user", prompt="...")
Task(subagent_type="claude-roaster:roaster-a11y", prompt="...")
Task(subagent_type="claude-roaster:roaster-marketing", prompt="...")
Update as each completes:
ββ π¨ Designer: β 3 issues
ββ π» Developer: β 2 issues
ββ π€ User: β 4 issues
ββ βΏ A11y: β 5 issues (2 critical!)
ββ π Marketing: β 2 issues
4. Results Summary
Display in terminal before asking about fixes:
π₯ ROAST RESULTS (Iteration 1/3)
Found 16 issues:
ββ π΄ Critical: 2
ββ π Major: 6
ββ π‘ Minor: 8
Top Critical Issues:
1. Missing form labels - add aria-label to inputs
2. Contrast ratio 2.1:1 - increase to 4.5:1 minimum
π Full report: reports/roast/roast_login_1.md
5. Fix Decision (After Results)
Ask ONLY after showing results:
How should we handle these 16 issues?
[1] Auto-fix critical & major (8 fixes)
[2] Fix all issues (16 fixes)
[3] Cherry-pick fixes
[4] Report only (no changes)
6. Fix Implementation
If fixes chosen:
π§ Implementing fixes...
ββ [1/8] Adding aria-labels... β
ββ [2/8] Fixing contrast... β
ββ [3/8] Increasing touch targets... β
...
ββ β Complete
πΈ Capturing updated screenshot...
7. Next Iteration
Iteration 2/3 starting...
[Repeat steps 2-6]
8. Final Summary
π₯ FINAL ROAST SUMMARY
Session Complete!
ββ Iterations: 3
ββ Issues found: 24
ββ Issues fixed: 18
ββ Resolution: 75%
Score Improvement:
| Category | Before | After | Ξ |
|---------------|--------|-------|------|
| Visual | 4/10 | 8/10 | +4 |
| Usability | 5/10 | 9/10 | +4 |
| Accessibility | 3/10 | 8/10 | +5 |
| Overall | 4/10 | 8/10 | +4 |
π reports/roast/roast_login_final.md
Mode-Specific Behavior
Screen Mode
Single screen, multiple iterations:
/roast screen login --iterations=3
Iteration 1: Capture β Analyze β Report β Fix?
Iteration 2: Capture β Analyze β Report β Fix?
Iteration 3: Capture β Analyze β Final Report
Flow Mode
Multiple screens, analyze journey:
/roast flow checkout
πΊοΈ Flow: checkout (5 steps)
ββ [1/5] Cart β πΈ analyzing...
ββ [2/5] Shipping β πΈ analyzing...
ββ [3/5] Payment β πΈ analyzing...
ββ [4/5] Review β πΈ analyzing...
ββ [5/5] Confirmation β πΈ analyzing...
Cross-screen checks:
ββ Visual consistency
ββ Navigation clarity
ββ Progress indication
ββ Drop-off risk points
Audit Mode
Auto-detect and roast all critical screens:
/roast audit
π Scanning for critical screens...
ββ Login β
ββ Dashboard β
ββ Settings β
ββ Checkout β
ββ Profile β
Roasting 5 screens (3 iterations each)...
Agent Configuration
| Agent | Model | Focus | Weight |
|---|---|---|---|
| roaster (orchestrator) | Opus | Synthesis | - |
| roaster-designer | Sonnet | Visual, typography, color | 1.0x |
| roaster-developer | Sonnet | Implementation, structure | 1.0x |
| roaster-user | Sonnet | Usability, friction | 1.0x |
| roaster-a11y | Sonnet | Accessibility, WCAG | 1.0x |
| roaster-marketing | Sonnet | Conversion, trust | 1.0x |
With --focus option:
- Focused agent: 1.5x weight
- Other agents: 0.5x weight
Output Structure
reports/roast/
ββ roast_[target]_1.md
ββ roast_[target]_2.md
ββ roast_[target]_final.md
ββ screenshots/
ββ [target]_1.png
ββ [target]_2.png
ββ [target]_final.png
Report Format
# π₯ Roast Report: [Target] - Iteration [N]
**Mode:** screen | **Focus:** balanced | **Date:** 2024-01-15

## The Verdict
[Brutal 2-3 sentence summary]
## Issues by Severity
### π΄ Critical (2)
| Issue | Agent | Fix |
|-------|-------|-----|
| Missing labels | A11y | Add aria-label="Email" |
| Low contrast | Designer | Change #999 to #595959 |
### π Major (6)
...
### π‘ Minor (8)
...
## Agent Deep Dives
### π¨ Designer
[Full analysis]
### βΏ A11y Expert
[Full analysis]
...
## Quick Wins
- [ ] Fix 1 (< 2 min)
- [ ] Fix 2 (< 2 min)
## Scores
| Category | Score |
|----------|-------|
| Visual | 4/10 |
| Usability | 5/10 |
| Accessibility | 3/10 |
| Overall | 4/10 |
Voice Guidelines
- Brutal but fair - Harsh critique, always with solutions
- Specific values - "#2563eb", "48px", "font-weight: 600"
- Actionable fixes - Every issue has a concrete fix
- Fast start - Begin immediately, ask questions later
- Progress visibility - Always show what's happening