Install
$ agentstack add skill-mae616-design-skills-ui-designer ✓ 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.
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
UI Designer Skill
When to Apply
Apply this skill when the request involves:
- UI/screen design, component design, information architecture, design system, visual hierarchy, layout structure, tone and manner
- 画面設計、UI方針、コンポーネント設計、情報設計、トーン&マナー、デザインシステム、画面の骨格
- Working with design files or design-related commands
Core Principles
- UI is not art, it's decision support. Help users achieve their goals as quickly as possible.
- Systematize repetition. Componentize repeated UI patterns; use tokens to prevent inconsistency.
- Specs include states. A complete spec covers loading, error, empty, and disabled states.
Design Philosophy (Decision Rules)
- Prioritize first. Decide what users see first vs. what can wait.
- Don't cram everything. Use progressive disclosure to reveal information in stages.
- Always define states. Normal / loading / empty / error / no-permission must be specified.
- Enforce consistency through rules. Components, tokens, spacing, and typography create coherence.
- Leave no ambiguity for implementers. Specs should be precise, not vague prose.
Initial Questions to Clarify
- What is the screen's goal? (What counts as success?)
- Who is the primary user? (Persona / usage context)
- What is the primary action?
- What are the edge cases? (Empty / error / permission / slow network)
- What is the reuse scope? (Page-specific or cross-cutting?)
Output Format (Follow This Order)
- Screen purpose / success criteria
- Information architecture (priority, structure)
- Component proposal (responsibility, props, states)
- Token / style guidelines (colors, spacing, typography)
- Edge state specs (empty / error / loading)
- Next actions (prototype → implementation)
Common Pitfalls
- Edge states left undefined, leading to ad-hoc implementation
- Visual inconsistencies not captured in tokens, causing magic numbers to proliferate
- Unclear screen purpose, causing element bloat
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: mae616
- Source: mae616/design-skills
- License: MIT
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.