Skip to main content
skill CX Codex

critique-brand-consistency — Claude Code skill: check a screen

Compares a rendered screen against mood.md, voice.md and tokens.md, then points out where styling and copy drifted from the brand.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add Owl-Listener/designer-skills --skill critique-brand-consistency -a claude-code
Open on GitHub

What critique-brand-consistency does

The skill reads three reference files from the project root. mood.md holds the brand personality and aesthetic direction, voice.md covers tone and language rules, tokens.md defines colour, spacing, radius, shadow and typography values. The screen is then checked on three axes: mood alignment, voice alignment and token compliance.

Each axis returns an observation, the divergence from the reference file, and the exact fix — the preferred wording or the correct token name. Every axis is rated pass, minor issue or major issue. Hardcoded values that should have come from tokens are listed separately, with their token equivalent.

If one of the three files is missing, that dimension is skipped rather than guessed at. So check that the files sit where you expect them before running the critique; otherwise you get a partial review. The author points to the illustration-style skill in the ui-design set for defining the visual language itself, not for auditing a finished screen.

What it helps with

  • check a rendered screen against the brand personality notes
  • find hardcoded hex values where a colour token belongs
  • audit button labels and error messages against the voice guide
  • spot mismatched radius and shadow values across one screen
  • get the exact token name to replace a non-compliant value

Example prompts for the agent

  • critique this screen against mood.md, voice.md and tokens.md
  • run critique-brand-consistency on the settings page
  • which values on this screen don't match tokens.md?

How to install critique-brand-consistency

1Skills CLI (Vercel)

npx skills add Owl-Listener/designer-skills --skill critique-brand-consistency -a claude-code

2Manually: put the files in place

~/.claude/skills/critique-brand-consistency/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/critique-brand-consistency/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about critique-brand-consistency

How do I install critique-brand-consistency in Claude?

Run npx skills add Owl-Listener/designer-skills --skill critique-brand-consistency -a claude-code. The skill file then lands at ~/.claude/skills/critique-brand-consistency/SKILL.md.

What does critique-brand-consistency do?

It compares a rendered screen with mood.md, voice.md and tokens.md, flags divergences in mood, voice and tokens, and suggests a fix for each.

What do I need before running it?

Three files in the project: mood.md, voice.md and tokens.md. When a file is missing, that dimension of the critique is skipped.

Source text

SKILL.md · MIT
---
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).
---
# Critique Brand Consistency
You are an expert in brand expression and design system compliance.
## What You Do
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.
## Reference Files
Before critiquing, locate and read these files from the project root (or wherever the designer specifies):
- **mood.md** — Brand personality, aesthetic keywords, visual references, do/don't examples
- **voice.md** — Tone of voice, language style, copy do/don't rules, vocabulary
- **tokens.md** — Canonical colour, spacing, radius, shadow, and typography token values
If a file is missing, note this and skip that dimension — do not invent brand rules.
## Critique Dimensions
### Mood Alignment
Compare the screen's aesthetic to the mood direction.
- Does the visual language (imagery style, illustration, iconography, colour feel) match the brand personality keywords?
- Are any elements tonally off — e.g., a playful brand using cold, corporate styling?
- Does the overall emotional register of the screen match what the mood file prescribes?
### Voice Alignment
Compare all visible copy to the voice guidelines.
- Does the tone match (e.g., direct vs. conversational, formal vs. friendly)?
- Are any prescribed vocabulary rules broken — forbidden words, required patterns?
- Are CTAs, labels, error messages, and microcopy consistent with the voice?
### Token Compliance
Compare every design value on screen to the token definitions.
- Are hardcoded hex values used where a colour token should apply?
- Are spacing, radius, or shadow values that deviate from tokens present?
- Are typography tokens applied correctly, or are raw font-size/weight values used?
- List every non-compliant value with its token equivalent.
## Output Format
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`.
## Common Failure Patterns
- Hardcoded values drifting from tokens over time
- Copy written without consulting voice guidelines, defaulting to generic UI language
- Imagery or illustration sourced outside the brand mood reference
- Inconsistent radius or shadow values across components on the same screen

© Owl-Listener · MIT · Owl-Listener/designer-skills

Similar skills

Everything for Design →

From the same set109

aesthetic-usability Applies the Aesthetic-Usability Effect when visual polish affects perceived ease of use and trust. Use it to diagnose functional designs that still make a poor first impression. CX Codex +1 1,900installs information-architecture A skill that designs content structure: sitemap, navigation model, taxonomy and content types. Useful when you need to organise what already exists. CX Codex +1 1,900installs critique-composition Critiques balance, negative space, visual rhythm, and gestalt grouping on rendered screens. Useful when layout hierarchy is solid but the spatial composition still feels off. CX Codex +1 1,900installs service-blueprint Maps how a service is delivered to users and behind the scenes. Use it to trace gaps between visible interactions, operations, and supporting systems. CX Codex +1 1,800installs navigation-patterns Helps select and design navigation patterns such as tab bars, sidebars, and breadcrumbs. Useful when mapping user journeys across mobile and desktop interfaces. CX Codex +1 1,800installs motion-system Defines one set of durations, easing curves and reduced-motion rules for a product. Useful when every component animates on its own timing. CX Codex +1 1,800installs design-negotiation Helps designers advocate for UX quality, scope, and timelines when negotiating with PMs and engineers using evidence instead of personal taste. CX Codex +1 1,700installs design-impact-reporting Turns design work into a report leadership can read: user, product and business metrics with the evidence behind them. CX Codex +1 1,700installs

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor