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

Design Critique

by getcrew44 in 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.

MITAuto-check passedFrontend & Design

Install Design Critique

skills CLI
$ npx skills add getcrew44/crew44 --skill design-critique -a claude-code

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

GitHub CLI
$ gh skill install getcrew44/crew44 design-critique --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/design-critique .claude/skills/design-critique && 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
design-critique
GitHub stars
356
Token cost
~691 tokens
SKILL.md length
377 words
Files
1
Skills in repo
9
Repo updated
First seen
Licence
MIT

At a glance

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.

  • Getting structured feedback on a mockup before it goes to developers
  • SKILL.md covers Frame the critique, Pass 1: First impression (two…, Pass 2: Hierarchy and reading… and Pass 3: Usability, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Reviewing a shipped screen for hierarchy and usability problems

What it does

You tell the agent the stage of the work (exploration, refinement or polish), who the screen is for and which slice you want reviewed, and the critique is framed around that. It then goes through five passes: a two-second first impression, hierarchy and reading flow, usability, consistency with the existing design system, and an accessibility floor covering contrast ratios, touch target size, focus order and form labels.

Feedback is meant to be specific, tied to a user need and ranked by impact, with a suggested direction and a note on what already works. The output is a short overall impression, findings grouped by pass that name the element, the issue, a critical, moderate or minor severity and a fix, and a brief list of strengths to preserve.

When your agent uses it

  • Getting structured feedback on a mockup before it goes to developers
  • Reviewing a shipped screen for hierarchy and usability problems
  • Checking a form or flow against basic accessibility thresholds
  • Deciding which design fixes to make first

Example prompts

  • “Critique the checkout screen in ./mockups/checkout.png and rank what to fix first.”
  • “We're at the polish stage on the onboarding flow. What did we miss?”
  • “Review the dashboard empty state against our design system tokens.”

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

Design Critique loads about 691 tokens when it runs. Until then it costs about 42 tokens; SKILL.md has 377 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~42
When it runs · the whole SKILL.md, loaded when a task matches
~691

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). 377 words, ~691 tokens.

Download SKILL.mdSave it as .claude/skills/design-critique/SKILL.md (or your agent's skills folder).
name
design-critique
description
Use to give structured feedback on a screen, flow, or mockup — first impression, hierarchy, usability, consistency, accessibility, and what to fix first.

Design Critique

Give the kind of feedback a designer actually wants: specific, prioritized, and tied to the user's goal — not adjectives.

Frame the critique

Ask, then critique. The same screen gets different feedback at different stages.

  • Stage. Exploration (push for range), refinement (tighten), or polish (catch what shipped).
  • Context. Who is it for? What is the user trying to do? What is this screen in service of?
  • Focus. All of it, or one slice (navigation, the empty state, the hero, the form)?

Pass 1: First impression (two seconds)

  • What draws the eye first? Is that what should?
  • Is the purpose of the screen clear before you read any copy?
  • What's the emotional read — calm, urgent, dense, sparse — and does that match the user's state?

Pass 2: Hierarchy and reading flow

  • Does the reading order match what the user is trying to do?
  • Are the right elements emphasized? Anything competing with the primary action?
  • Is whitespace doing work, or just sitting there?

Pass 3: Usability

  • Can the user accomplish the goal without backtracking?
  • Are interactive elements obviously interactive? Are read-only elements clearly not?
  • Are there unnecessary steps, fields, or confirmations?

Pass 4: Consistency

  • Does this match the existing design system, or invent locally? Name the specific deviations.
  • Spacing, typography, color tokens — pulled from the system, or magic numbers?
  • Do similar elements behave similarly across the screen?
Show full SKILL.md (152 more words)Show less

Pass 5: Accessibility floor

  • Color contrast: body text ≥ 4.5:1, large text and UI ≥ 3:1.
  • Touch targets ≥ 44×44.
  • Focus order is logical; focus indicators are visible.
  • Form inputs have labels, not just placeholders.

How to deliver feedback

  • Be specific. "The CTA competes with the navigation" beats "the layout is confusing."
  • Explain the why. Tie each note to a user need or principle, not just taste.
  • Suggest, don't just diagnose. A direction is more useful than a problem.
  • Call out what works. Reinforces the moves to keep.
  • Rank by impact. Lead with the change that buys the most.

Output

  • Overall impression — one or two sentences. What works, what's the biggest opportunity.
  • Findings — grouped by pass (hierarchy, usability, consistency, accessibility). Each finding names the element, the issue, the severity (critical / moderate / minor), and the suggested fix.
  • What works well — short list. Preserve these.
  • Top three changes — prioritized. For each: what to change, why, expected effect.

© 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/design-critique of getcrew44/crew44.

Open the folder on GitHubat commit cfcf1e7

Compare with similar skills

Design Critique 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.

Design Critique compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Design Critique this skillgetcrew44/crew44356—~691Automated safety check: PassMIT
Design ReviewTheDecipherist/claude-code-mastery-project-starter-kit338—~712Automated safety check: PassMIT
UI Reviewespennilsen/pi122—~1.4kAutomated safety check: PassMIT
Product Designeraakashg/pm-claude-skills112—~2.4kAutomated safety check: PassMIT
UX Spec ReviewDonchitos/Claude-Code-Game-Studios26k—~3.7kAutomated safety check: PassMIT
Web Interface Guidelines Reviewervercel-labs/openreview1.7k97 repos~308Automated safety check: PassNone

Similar skills

  • Design Review

    TheDecipherist/claude-code-mastery-project-starter-kit

    Critique UI and UX for usability, accessibility, and distinctiveness with cited, evidence-based findings.

    338 GitHub stars~712 tokensUpdated 3 mo ago
    Frontend & DesignAuto-check passed

  • UI Review

    espennilsen/pi

    Review UI designs and implementations for accessibility, consistency, usability, and visual quality.

    122 GitHub stars~1.4k tokensUpdated 17 days ago
    Frontend & DesignAuto-check passed

  • Product Designer

    aakashg/pm-claude-skills

    A skill your agent uses when the user asks to review a design, critique a UI or mockup, give design feedback, or check a screen for usability and accessibility issues.

    112 GitHub stars~2.4k tokensUpdated 2 mo ago
    Frontend & DesignAuto-check passed

  • UX Spec Review

    Donchitos/Claude-Code-Game-Studios

    Validates a UX spec, HUD design or interaction pattern library for accessibility, design-doc alignment and implementation readiness, ending in one of four verdicts.

    26k GitHub stars~3.7k tokensUpdated yesterday
    Frontend & DesignAuto-check passed

  • Web Interface Guidelines Reviewer

    vercel-labs/openreview

    Official

    Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my…

    1.7k GitHub starsUsed in 97 repos~308 tokens
    Frontend & DesignAuto-check passed

  • Interface Design for Dashboards and Apps

    holaboss-ai/holaOS

    Pushes an agent past generic defaults when designing dashboards, admin panels, SaaS apps and tools, with attention to structure, type, navigation and how data is shown.

    11k GitHub starsUsed in 3 repos~6k tokens
    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 4 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 4 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 4 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 4 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 4 mo ago
    Auto-check passed

  • UX Copy

    getcrew44/crew44

    A skill your agent uses to write or review microcopy — CTAs, error messages, empty states, confirmation dialogs, tooltips, onboarding text.

    356 GitHub stars~783 tokensUpdated 4 mo ago
    Auto-check passed

Categories

Questions about Design Critique

What does Design Critique do?

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. You tell the agent the stage of the work (exploration, refinement or polish), who the screen is for and which slice you want reviewed, and the critique is framed around that. It then goes through five passes: a two-second first impression, hierarchy and reading flow, usability, consistency with the existing design system, and an accessibility floor covering contrast ratios, touch target size, focus order and form labels.

When should I use Design Critique?

Design Critique fits situations like: getting structured feedback on a mockup before it goes to developers; reviewing a shipped screen for hierarchy and usability problems; checking a form or flow against basic accessibility thresholds; deciding which design fixes to make first.

How do I install Design Critique in Claude Code?

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

How do I install Design Critique in Codex?

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

Can I use Design Critique 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 design-critique -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/design-critique, .gemini/skills/design-critique, .github/skills/design-critique and .opencode/skills/design-critique in your project.

What does Design Critique need to run?

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

Does Design Critique 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 Design Critique 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 Design Critique use?

Design Critique 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 Design Critique use?

About 691 tokens (SKILL.md is roughly 2.8k 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 Design Critique?

Skills that share tags, products or a category with Design Critique: Design Review (TheDecipherist/claude-code-mastery-project-starter-kit, 338 stars), UI Review (espennilsen/pi, 122 stars), Product Designer (aakashg/pm-claude-skills, 112 stars) and UX Spec Review (Donchitos/Claude-Code-Game-Studios, 26k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Design Critique?

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.