zacczakk/metronome/design-critique
Claude Code and agent skill by zacczakk/metronome
- community
Checking that the SKILL.md file is still in the repository.
Review UI work for anti-slop tells, hierarchy, cognitive load, and UX quality. Use when the user asks to critique, review, evaluate, or improve an existing design.
Install
npx vskill@latest install zacczakk/metronome/design-critiqueSKILL.md
Review the requested UI directly and produce a concise, actionable critique.
Preparation
- Read the relevant code and UI files.
- Use project design context from loaded instructions or
.design-context.mdwhen available. - If context is missing, continue with explicit assumptions rather than blocking.
Evaluate
Assess the UI across these areas:
- Anti-pattern verdict: Does it look generic or AI-generated? Name the specific tells.
- Visual hierarchy: Is the primary action and reading order obvious?
- Cognitive load: Is the structure understandable, or does it overload the user?
- Tone and fit: Does it feel right for the audience and product?
- Discoverability: Are actions and paths obvious without explanation?
- Typography: Does type support hierarchy, readability, and tone?
- States and edge cases: Empty, loading, error, success, hover, focus.
- Microcopy: Are labels, buttons, and messages clear and human?
If persona framing helps, use only these compact archetypes:
- first-timer
- power user
- accessibility-dependent user
Output
Return findings in this shape:
Anti-Pattern Verdict
Pass or fail, with specific tells.
Overall Impression
Short gut-level assessment.
What's Working
List 2-3 concrete strengths.
Priority Issues
List 3-5 issues with P0-P3 severity. For each issue include:
- what is wrong
- why it matters
- the most direct fix
Recommended Next Commands
Recommend the smallest useful next actions, using only relevant design commands.
Keep the critique direct, specific, and actionable. Do not soften findings with vague language.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingconfigs/skills/design-critique/SKILL.md
Popularity
- 7-day trend score
- 5
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/zacczakk/metronome/design-critique)