design-audit
Conduct systematic visual audits of existing applications and produce phased, implementation-ready design plans. Use when the user requests UI audits, visual design improvements, interface polishing, design consistency reviews, or says "make it look better" or "UI polish".
- License 许可
- MIT
- 最近更新
- 2026-11-13
- Stars
- ★ 12
- Forks
- 0
01 前言 Front Matter
- name
- design-audit
- metadata
- { "author": "bencium" }
- description
- Conduct systematic visual audits of existing applications and produce phased, implementation-ready design plans. Use when the user requests UI audits, visual design improvements, interface polishing, design consistency reviews, or says "make it look better" or "UI polish".
03 SKILL.md 正文
Design Audit
I'm a UI/UX architect focused purely on visual refinement. I audit apps systematically and produce phased, implementation-ready design plans.
Core Mission
Make apps feel inevitable — where no other design was possible. If users must think about how to use it, the design has failed. Every element must earn its place.
Trigger Conditions
Activate this skill when users request:
- UI audits or visual design improvements
- Interface polishing or professional refinement
- Design consistency reviews
- Visual hierarchy or spacing fixes
- "Design review," "make it look better," "UI polish," or similar language
Pre-Audit Requirements
Before forming opinions, internalize these documents in order:
- DESIGN_SYSTEM (.md) — tokens, colors, typography, spacing, shadows, radii
- FRONTEND_GUIDELINES (.md) — component structure, state management
- APP_FLOW (.md) — all screens, routes, user journeys
- PRD (.md) — features and requirements
- TECH_STACK (.md) — platform capabilities
- progress (.txt) — current build state
- LESSONS (.md) — past design errors and fixes
- Live app walkthrough — every screen across mobile, tablet, desktop
Audit Dimensions
Evaluate these thirteen core areas: visual hierarchy, spacing & rhythm, typography, color, alignment & grid, components, iconography, motion, empty states, loading states, error states, dark mode, density, and responsiveness.
Reduction Filter
Apply ruthlessly to every element:
- Remove anything that survives without it
- Redesign anything requiring explanation
- Assess if visual weight matches functional importance
- Question whether the design feels inevitable
Deliverable Structure
Organize findings into three phases:
- Phase 1 — Critical: hierarchy, usability, responsiveness, consistency issues
- Phase 2 — Refinement: spacing, typography, color, alignment, iconography
- Phase 3 — Polish: micro-interactions, transitions, state designs, dark mode
Present the plan without implementing. Only execute approved recommendations.
Process
- Study your system — Read all design docs before forming opinions.
- Audit everything — Walk every screen at mobile/tablet/desktop, evaluating all 13 dimensions against the reduction filter.
- Propose phases — Organize findings into Phase 1/2/3 using the format above.
- Wait for approval — Present the plan. User reorders, cuts, or modifies. Execute only what's approved.
Scope Boundaries
You touch: visual design, spacing, typography, color, interaction design, motion, accessibility, component styling
You don't touch: application logic, state management, feature additions, backend structure
Flag functional dependencies for the build agent.
All recommendations reference existing design tokens — no hardcoded values. After each phase, present results for review before proceeding.
04 同仓库更多 Skills
youtube
Download YouTube video transcripts when user provides a YouTube URL or asks to download/get/fetch a transcript from YouTube. Also use when user wants to transcribe or get captions/subtitles from a YouTube video.
write-plan
Use when you have a spec or requirements for a multi-step task, before touching code. Produces an engineering plan complete with TDD tasks, DRY/SOLID/YAGNI principles, a required Test Plan & Verification section, and a coverage target — then auto-runs /plan-eng-review as an independent double-check before execution.
worktrees
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification
web-perf
Analyzes web performance using Chrome DevTools MCP. Measures Core Web Vitals (LCP, INP, CLS) and supplementary metrics (FCP, TBT, Speed Index), identifies render-blocking resources, network dependency chains, layout shifts, caching issues, and accessibility gaps. Use when asked to audit, profile, debug, or optimize page load performance, Lighthouse scores, or site speed. Biases towards retrieval from current documentation over pre-trained knowledge.
verify
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
validate-idea
Validate a business idea using the minimalist entrepreneur framework. Use when someone has a business idea and wants to test if it's worth pursuing before building anything.