brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent,…
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.
/visual-system-reviewContext 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.
name: visual-system-review description: Use to evaluate visual consistency, hierarchy, and design-system adherence — typography, color, spacing, density, tokens.
Check that visual choices serve the user and match (or extend, deliberately) the existing design language.
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?
Visual choices should resolve to tokens, not magic numbers:
When a token is missing for something that should have one, flag it as a design-system gap, not just a local issue.
For every element, ask: does this earn its pixels? If not, cut it. Most screens improve when something is removed.
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
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent,…
Use when you have a written implementation plan to execute in a separate session with review checkpoints
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…
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical…
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes