Design Critic Skill
Critique UI visual quality with observable design criteria. Use this skill whenever the user asks for visual critique, design review, polish, hierarchy, spacing, typography, contrast risk, consistency, brand fit, anti-slop review, screenshot critique, Figma frame critique, or a fix brief for a weak interface. Keep findings actionable and evidence-labeled. Do not require Attention Insight, Khroma,…
Install
$ agentstack add skill-sergekostenchuk-ui-ux-agent-skill-system-design-critic-skill ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-sergekostenchuk-ui-ux-agent-skill-system-design-critic-skill) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Design Critic Skill
Use this specialist when the main need is visual quality judgment and actionable polish, not full implementation or automated audit.
Operating Modes
screenshot-critique: review a screenshot or image.figma-critique: review a provided Figma frame/context.code-context-critique: critique likely visual issues from source and local screenshots.fix-brief: convert critique into implementation instructions for webapp or marketing skills.
Required Workflow
- Read [references/hierarchy-rubric.md](references/hierarchy-rubric.md).
- Read [references/anti-slop-patterns.md](references/anti-slop-patterns.md) before calling a design "polished".
- Use [references/taste-constraints.md](references/taste-constraints.md) to keep critique observable.
- Apply
../../shared/privacy-policy.mdbefore Figma/screenshots/external tools. - Use [assets/critique-report.template.md](assets/critique-report.template.md) for structured output.
- Mark evidence type: screenshot, Figma, source, browser, or
Manual.
Critique Rules
- Findings must map to observable issues: hierarchy, grouping, scan path, contrast risk, spacing, type scale, affordance, consistency, content density, or action priority.
- Avoid vague taste claims without fix direction.
- Do not invent accessibility, DOM, performance, or analytics evidence.
- Optional cloud tools can support ideation only after approval and cannot replace local judgment.
Validation
python3 $CODEX_SKILLS_DIR/.system/skill-creator/scripts/quick_validate.py $CODEX_SKILLS_DIR/design-critic-skill
python3 $CODEX_SKILLS_DIR/senior-skill-architect/scripts/lint_production_skill.py $CODEX_SKILLS_DIR/design-critic-skillOutput Shape
Input:
Evidence type:
Top findings:
Fix brief:
What not to change:
Verification:
Privacy notes:Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: sergekostenchuk
- Source: sergekostenchuk/ui-ux-agent-skill-system
- License: Apache-2.0
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.