/visual-system-review
Use to evaluate visual consistency, hierarchy, and design-system adherence — typography, color, spacing, density, tokens.
$ npx -y skills add getcrew44/crew44 --skill visual-system-review --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/visual-system-review
Context preview
The summary Claude sees to decide when to auto-load this skill.
Use to evaluate visual consistency, hierarchy, and design-system adherence — typography, color, spacing, density, tokens.
SKILL.md
visual-system-review.SKILL.mdname: visual-system-review
description: Use to evaluate visual consistency, hierarchy, and design-system adherence — typography, color, spacing, density, tokens.
Visual System Review
Check that visual choices serve the user and match (or extend, deliberately) the existing design language.
What to evaluate
1. **Hierarchy.** Does the eye go to the right place first? Does importance match visual weight? 2. **Consistency.** Are buttons, inputs, spacing, and typography drawn from the existing system, or invented locally? 3. **Information density.** Is the screen too quiet or too noisy for its purpose? 4. **Copy fit.** Does the text fit the container at the longest realistic length? At the shortest? 5. **Contrast and readability.** Does it work for users with vision impairments and on small screens? 6. **Affordances.** Are interactive elements obviously interactive? Are read-only elements clearly not?
Token discipline
Visual choices should resolve to tokens, not magic numbers:
- **Typography:** a defined scale (xs/sm/base/lg/xl…), 2–3 weights max, line-height 1.1–1.3 for headings, 1.5–1.7 for body.
- **Spacing:** a defined scale (4px or 8px base). Component padding 16–24px, section gaps 32–64px, icon-text gap 8px.
- **Color:** semantic roles (primary, success, warning, error, neutral 50–900). Contrast ≥ 4.5:1 for body, ≥ 3:1 for large text and UI components.
- **Icons:** a defined size scale (12/16/20/24/32). One stroke-weight family.
When a token is missing for something that should have one, flag it as a design-system gap, not just a local issue.
Subtraction default
For every element, ask: does this earn its pixels? If not, cut it. Most screens improve when something is removed.
Output
- Specific issues with the screen as it is.
- Suggested changes, ranked by user impact.
- Anything that violates the existing design system (new button styles, ad-hoc spacing, custom colors, off-scale type).
- Tokens or patterns missing from the design system that this work surfaces.
Read more
name: visual-system-review description: Use to evaluate visual consistency, hierarchy, and design-system adherence — typography, color, spacing, density, tokens.
Visual System Review
Check that visual choices serve the user and match (or extend, deliberately) the existing design language.
What to evaluate
1. **Hierarchy.** Does the eye go to the right place first? Does importance match visual weight? 2. **Consistency.** Are buttons, inputs, spacing, and typography drawn from the existing system, or invented locally? 3. **Information density.** Is the screen too quiet or too noisy for its purpose? 4. **Copy fit.** Does the text fit the container at the longest realistic length? At the shortest? 5. **Contrast and readability.** Does it work for users with vision impairments and on small screens? 6. **Affordances.** Are interactive elements obviously interactive? Are read-only elements clearly not?
Token discipline
Visual choices should resolve to tokens, not magic numbers:
- **Typography:** a defined scale (xs/sm/base/lg/xl…), 2–3 weights max, line-height 1.1–1.3 for headings, 1.5–1.7 for body.
- **Spacing:** a defined scale (4px or 8px base). Component padding 16–24px, section gaps 32–64px, icon-text gap 8px.
- **Color:** semantic roles (primary, success, warning, error, neutral 50–900). Contrast ≥ 4.5:1 for body, ≥ 3:1 for large text and UI components.
- **Icons:** a defined size scale (12/16/20/24/32). One stroke-weight family.
When a token is missing for something that should have one, flag it as a design-system gap, not just a local issue.
Subtraction default
For every element, ask: does this earn its pixels? If not, cut it. Most screens improve when something is removed.
Output
- Specific issues with the screen as it is.
- Suggested changes, ranked by user impact.
- Anything that violates the existing design system (new button styles, ad-hoc spacing, custom colors, off-scale type).
- Tokens or patterns missing from the design system that this work surfaces.
Orchestrate a crew of specialist AI agents in one local-first workspace. Each role on its best model, with memory and skills that compound. Free, MIT.
Repo: getcrew44/crew44
Other skills on crew44.
- /brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Open skill - /executing-plans
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Open skill - /finishing-a-development-branch
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
Open skill - /receiving-code-review
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
Open skill - /requesting-code-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
Open skill - /systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
Open skill

