New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Visual System Review

by getcrew44 in getcrew44/crew44

A skill your agent uses to evaluate visual consistency, hierarchy, and design-system adherence — typography, color, spacing, density, tokens.

MITAuto-check passedFrontend & Design

Install Visual System Review

skills CLI
$ npx skills add getcrew44/crew44 --skill visual-system-review -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install getcrew44/crew44 visual-system-review --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/getcrew44/crew44.git skills-src && mkdir -p .claude/skills && cp -r skills-src/daemon/internal/presets/defaultcrew/skills/designer/visual-system-review .claude/skills/visual-system-review && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
visual-system-review
GitHub stars
356
Token cost
~508 tokens
SKILL.md length
272 words
Files
1
Skills in repo
9
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses to evaluate visual consistency, hierarchy, and design-system adherence — typography, color, spacing, density, tokens.

  • Works in 6 steps: Hierarchy. Does the eye go to the right… → Consistency. Are buttons, inputs,… → Information density. Is the screen too… → …
  • Evaluate visual consistency
  • SKILL.md covers What to evaluate, Token discipline, Subtraction default and Output
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Visual System Review is an agent skill from getcrew44/crew44. Use to evaluate visual consistency, hierarchy, and design-system adherence — typography, color, spacing, density, tokens.

Its SKILL.md is about 510 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Frontend & Design, covering Typography and Design systems. The repository describes itself as: 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. The licence is MIT.

When your agent uses it

  • Evaluate visual consistency
  • Design-system adherence — typography

Example prompts

  • “/visual-system-review”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  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?

What it can do on your machine

Read from SKILL.md and the folder at commit cfcf1e7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Visual System Review loads about 508 tokens when it runs. Until then it costs about 36 tokens; SKILL.md has 272 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~36
When it runs · the whole SKILL.md, loaded when a task matches
~508

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from getcrew44/crew44 at commit cfcf1e7, republished under its MIT licence (© getcrew44). 272 words, ~508 tokens.

Download SKILL.mdSave it as .claude/skills/visual-system-review/SKILL.md (or your agent's skills folder).
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.

© getcrew44, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in daemon/internal/presets/defaultcrew/skills/designer/visual-system-review of getcrew44/crew44.

Open the folder on GitHubat commit cfcf1e7

Compare with similar skills

Visual System Review next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Visual System Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Visual System Review this skillgetcrew44/crew44356—~508Automated safety check: PassMIT
Impeccablebestofjs/bestofjs3.1k27 repos~2.6kAutomated safety check: PassMIT
Design SystemOhh-889/skyroc79511 repos~1.7kAutomated safety check: PassMIT
Stitch Taste Design Systemgoogle-labs-code/stitch-skills8.4k15 repos~3.1kAutomated safety check: PassApache-2.0
Scalar Design Systemscalar/scalar16k—~2.7kAutomated safety check: PassMIT
UI/UX Design System AdvisorGalaxy-Dawn/claude-scholar5.7k1 repos~1.1kAutomated safety check: PassMIT

Similar skills

  • Impeccable

    bestofjs/bestofjs

    A skill your agent uses when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a…

    3.1k GitHub starsUsed in 27 repos~2.6k tokens
    Frontend & DesignAuto-check passed

  • Design System

    Ohh-889/skyroc

    Token architecture, component specifications, and slide generation.

    795 GitHub starsUsed in 11 repos~1.7k tokens
    Frontend & DesignAuto-check passed

  • Stitch Taste Design System

    google-labs-code/stitch-skills

    Official

    Generates a DESIGN.md design-language file for Google Stitch that encodes color, typography, layout, component behavior and motion rules to avoid generic AI-looking UI.

    8.4k GitHub starsUsed in 15 repos~3.1k tokens
    Frontend & DesignAuto-check passed

  • Scalar Design System

    scalar/scalar

    Scalar's design system — design tokens, theming (@scalar/themes), CSS variables, and the @scalar/components library.

    16k GitHub stars~2.7k tokensUpdated today
    Frontend & DesignAuto-check passed

  • UI/UX Design System Advisor

    Galaxy-Dawn/claude-scholar

    Turns a vague UI request into a concrete design system with style, palette, typography and layout guidance from a search script, plus stack-specific implementation advice.

    5.7k GitHub starsUsed in 1 repo~1.1k tokens
    Frontend & DesignAuto-check passed

  • Use UI Kit

    tetherto/pearpass-app-desktop

    A skill your agent uses whenever creating or editing UI in this repo — React components, modals, dialogs, forms, buttons, inputs, typography, styling, icons, or any .tsx/.jsx work.

    538 GitHub stars~3.3k tokensUpdated 1 mo ago
    Frontend & DesignAuto-check passed

More from getcrew44/crew44

All 9 skills in this repo

  • End-of-Life Announcement Writer

    getcrew44/crew44

    Drafts a clear, empathetic end-of-life announcement for a product, feature or plan, covering rationale, customer impact, transition support, timeline and next steps.

    356 GitHub stars~3.1k tokensUpdated 3 mo ago
    Auto-check passed

  • Session Skill Mining

    getcrew44/crew44

    Reviews past Codex or Claude Code sessions from a time range you choose and proposes skills to codify and memories to pin, as a summary plus structured JSON.

    356 GitHub stars~5.3k tokensUpdated 3 mo ago
    Auto-check passed

  • WCAG 2.1 AA Accessibility Review

    getcrew44/crew44

    Audits a design or page against WCAG 2.1 AA for contrast, keyboard use, focus, labels, touch targets and screen reader behavior, with a severity-ranked report.

    356 GitHub stars~741 tokensUpdated 3 mo ago
    Auto-check passed

  • Design Critique

    getcrew44/crew44

    Walks an agent through five review passes on a screen, flow or mockup, then returns ranked findings with a severity and a suggested fix for each one.

    356 GitHub stars~691 tokensUpdated 3 mo ago
    Auto-check passed

  • Design Handoff Spec

    getcrew44/crew44

    Produces an implementation-ready spec from a finished design, covering layout, tokens, states, responsive behavior, edge cases, motion and accessibility, so engineers do not have to guess.

    356 GitHub stars~680 tokensUpdated 3 mo ago
    Auto-check passed

  • Interaction Review

    getcrew44/crew44

    A skill your agent uses to evaluate or design a user interaction flow — states, edge cases, microinteractions, motion, and feedback patterns.

    356 GitHub stars~586 tokensUpdated 3 mo ago
    Auto-check passed

Categories

Questions about Visual System Review

What does Visual System Review do?

A skill your agent uses to evaluate visual consistency, hierarchy, and design-system adherence — typography, color, spacing, density, tokens. Visual System Review is an agent skill from getcrew44/crew44. Use to evaluate visual consistency, hierarchy, and design-system adherence — typography, color, spacing, density, tokens.

When should I use Visual System Review?

Visual System Review fits situations like: evaluate visual consistency; design-system adherence — typography.

How do I install Visual System Review in Claude Code?

Run `npx skills add getcrew44/crew44 --skill visual-system-review -a claude-code`. Or copy the skill folder (daemon/internal/presets/defaultcrew/skills/designer/visual-system-review in getcrew44/crew44) into .claude/skills/visual-system-review in your project. Claude Code loads it when a task matches its description.

How do I install Visual System Review in Codex?

Run `npx skills add getcrew44/crew44 --skill visual-system-review -a codex`. Or copy the skill folder (daemon/internal/presets/defaultcrew/skills/designer/visual-system-review in getcrew44/crew44) into .agents/skills/visual-system-review in your project. Codex loads it when a task matches its description.

Can I use Visual System Review in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add getcrew44/crew44 --skill visual-system-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/visual-system-review, .gemini/skills/visual-system-review, .github/skills/visual-system-review and .opencode/skills/visual-system-review in your project.

What does Visual System Review need to run?

SKILL.md names no scripts, command-line tools or credentials: Visual System Review is instructions for the agent only.

Does Visual System Review access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Visual System Review safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Visual System Review use?

Visual System Review is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Visual System Review use?

About 508 tokens (SKILL.md is roughly 2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Visual System Review?

Skills that share tags, products or a category with Visual System Review: Impeccable (bestofjs/bestofjs, 3.1k stars), Design System (Ohh-889/skyroc, 795 stars), Stitch Taste Design System (google-labs-code/stitch-skills, 8.4k stars) and Scalar Design System (scalar/scalar, 16k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Visual System Review?

getcrew44 (a GitHub organization) maintains it in getcrew44/crew44, which has 356 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on June 11, 2026.

Source: getcrew44/crew44 on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.