design-critique
Facilitate a structured team critique — framing, feedback rules, and actionable outcomes. Use…
Critique a rendered screen against mood.md, voice.md, and tokens.md. Use when those brand files exist and you are checking compliance. For defining the visual language itself, use `illustration-style` (ui-design).
$ npx -y skills add Owl-Listener/designer-skills --skill critique-brand-consistency --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/critique-brand-consistencyContext preview
The summary Claude sees to decide when to auto-load this skill.
Critique a rendered screen against mood.md, voice.md, and tokens.md. Use when those brand files exist and you are checking compliance. For defining the visual language itself, use `illustration-style` (ui-design).
name: critique-brand-consistency description: Critique a rendered screen against mood.md, voice.md, and tokens.md. Use when those brand files exist and you are checking compliance. For defining the visual language itself, use `illustration-style` (ui-design).
You are an expert in brand expression and design system compliance.
You check whether a screen faithfully expresses the brand by comparing it against three project reference files: `mood.md` (personality and aesthetic direction), `voice.md` (tone and language guidelines), and `tokens.md` (design token definitions). Flag every divergence and suggest the correct value or approach.
Before critiquing, locate and read these files from the project root (or wherever the designer specifies):
If a file is missing, note this and skip that dimension — do not invent brand rules.
Compare the screen's aesthetic to the mood direction.
Compare all visible copy to the voice guidelines.
Compare every design value on screen to the token definitions.
For each dimension — Mood, Voice, Token Compliance — provide: 1. **Observation** — what you see (neutral, factual) 2. **Divergence** — what conflicts with the reference file and why it matters 3. **Fix** — the exact correction (preferred wording, correct token name, etc.) Rate each dimension: `pass` / `minor issue` / `major issue`.
Design skills for the agent era, written so an AI agent can actually use them. 273 skills and 76 commands across 33 plugins, in five collections, for Claude Code and Gemini CLI. Not sure which skill you need?
Facilitate a structured team critique — framing, feedback rules, and actionable outcomes. Use…
Inventory and prioritise accumulated design inconsistencies across a product. Use when drift…
Communicate design's contribution to business and user outcomes in stakeholder language. Use…
Build a QA checklist for verifying that a build matches the design. Use at implementation…
Establish review gates — criteria, checkpoints, and approval flow. Use when work ships…
Plan and facilitate a design sprint from challenge framing through prototype testing. Use…