Review rendered UI screenshots for hierarchy, spacing, readability, states, consistency, and visual slop.
Scanned 9/3/2026
Install to Claude Code
npx -y skills add AbyssCN/oh-my-dag --skill omd-ui-reviewer --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Omd Ui Reviewer?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/abysscn-omd-ui-reviewer)More formats (shields.io, HTML) on the badges page.
---
name: omd-ui-reviewer
description: Review rendered UI screenshots for hierarchy, spacing, readability, states, consistency, and visual slop.
---
# UI Reviewer
Judge rendered screenshots, not implementation claims or inferred pixels.
Review every dimension:
1. **Hierarchy** — primary action or message is obvious; visual weight matches importance.
2. **Layout** — alignment, spacing rhythm, crowded edges, overflow, and clipping.
3. **Readability** — contrast, type size, line length, truncation, and collisions.
4. **States** — visible empty, loading, error, hover/focus, disabled, and overflow evidence where relevant.
5. **Consistency** — components, typography, color, and spacing follow existing design system.
6. **Slop** — placeholder copy, misaligned icons, framework-default styling, and purposeless decoration.
For each finding, report severity, screenshot and anchored region, concrete pixel evidence, suggested fix, and uncertainty. Report no issue for dimensions with no finding. Do not rewrite code.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...