brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior.…
Use to evaluate visual consistency, hierarchy, and design-system adherence — typography, color, spacing, density, tokens.
Claude Code
$ npx -y skills add getcrew44/crew44 --skill visual-system-review --agent claude-code
Codex
$ npx skills add getcrew44/crew44 --skill visual-system-review -a codex -y
Cursor
$ npx skills add getcrew44/crew44 --skill visual-system-review -a cursor -y
Gemini CLI
$ npx skills add getcrew44/crew44 --skill visual-system-review -a gemini-cli -y
GitHub Copilot
$ npx skills add getcrew44/crew44 --skill visual-system-review -a github-copilot -y
OpenCode
$ npx skills add getcrew44/crew44 --skill visual-system-review -a opencode -y
Windsurf
$ npx skills add getcrew44/crew44 --skill visual-system-review -a windsurf -y
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.
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior.…
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…
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically…
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
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…
Ask which skill or flow fits your situation. A router over the skills in this repo.