Skip to main content
skill CX Codex

critique · plugin87 — Claude Code skill: what it does, how to install

The critique Claude Code skill challenges a finished interface and finds grounds to reject it. Run it after the project gates pass.

MIT ★ 3,216 updated 2026-11-10

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add plugin87/ux-ui-agent-skills
/plugin install ux-ui-agent-skills@ux-ui-agent-skills
Open on GitHub

What critique does

The skill hands the target to a critic in a separate context, without access to the conversation that produced the work. The critic renders a file or directory at 1280 and 390 pixels in light and dark themes, then clicks each control and records what changes.

It needs the complete UX/UI Agent Skills kit: gates, references, and the design-system library. The critic runs audit scripts plus overflow and responsive checks, then returns a verdict, three reasons for rejection, and a findings table with evidence. Claude Code 2.1.218 or later is required; without the full kit, the review stops.

What it helps with

  • spot visual defects in a finished interface
  • check whether controls respond to clicks
  • find responsive and overflow issues
  • record evidence for design changes

Example prompts for the agent

  • Run critique on src/App.tsx after the project gates pass.
  • Review the interface in src/pages and list verified defects.
  • Critique src/App.tsx in light and dark themes.

How to install critique

1Plugin marketplace

/plugin marketplace add plugin87/ux-ui-agent-skills
/plugin install ux-ui-agent-skills@ux-ui-agent-skills

This installs the whole ux-ui-agent-skills plugin with all its skills

2Skills CLI (Vercel)

npx skills add plugin87/ux-ui-agent-skills --skill critique -a claude-code

3Manually: put the files in place

~/.claude/skills/critique/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/critique/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about critique

How do I install critique in Claude Code?

Add the marketplace with /plugin marketplace add plugin87/ux-ui-agent-skills, then install the plugin with /plugin install ux-ui-agent-skills@ux-ui-agent-skills.

What does critique do?

It delegates a visual review to a separate critic that cannot see the conversation behind the work. The critic examines rendered screens and controls, runs the kit's checks, and reports evidence-backed findings.

What does critique need to run?

It requires the complete UX/UI Agent Skills kit, including its gates, references, and design-system library. Claude Code 2.1.218 or later is also required.

Source text

SKILL.md · MIT
---
name: critique
description: Adversarial design critique of the current work. Render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.
# Converted from .claude/commands/ so it has a CLAUDE_SKILL_DIR of its own and
# its paths resolve on every install route.
disable-model-invocation: true
# The critic runs in a forked subagent: a fresh context that never sees the
# conversation that produced the work. That is the whole point. A critic that
# has read the maker's reasoning is reviewing the argument, not the artifact,
# and it agrees far too easily.
context: fork
# Wait for the verdict in this turn. Forked skills run in the background by
# default, which would hand the user a "started" message and no critique.
# Requires Claude Code v2.1.218 or later.
background: false
#
# There is deliberately NO `agent:` field, and it is not an oversight.
#
# A plugin namespaces every component under the plugin name, so this repo's
# critic is `design-critic` when installed with `npx [email protected] init` (a
# project file in .claude/agents/) and `ux-ui-agent-skills:design-critic` when
# installed as a plugin. One frontmatter value cannot be both, and a wrong one
# is the `invocation:` failure again: a field that looks right, is silently
# ignored or unresolved, and leaves the behaviour it promised switched off.
#
# So the fork is generic and the body below loads the critic's instructions from
# a ${CLAUDE_SKILL_DIR}-relative path, which does resolve on both routes.
---
This skill runs in a forked context. The conversation that produced the work
is not visible here, there is no way to ask the user a question, and nothing
from elsewhere applies. Everything the review needs is below or on disk.

## Requirements

This skill needs the full UX/UI Agent Skills kit: the gates, the references and
the design-system library. Install it with `npx [email protected] init`
or as the Claude Code plugin. `npx [email protected] add` copies the skill folder and
nothing else, and this skill has no guidance-only mode: its whole job is to
hand the work to the kit's design-critic agent, so without the kit there is nothing for it to do.

> **Step 0: is the kit here?** Check once:
> `ls ${CLAUDE_SKILL_DIR}/../../../tokens >/dev/null 2>&1 && echo KIT_OK || echo KIT_MISSING`
> On `KIT_MISSING`, say plainly that only the skill folder was installed, name
> the install command above, and stop. Do not guess the contents of a file you
> could not open, and do not report a result you did not produce.

**Step 1: take the critic's instructions, in full.**

```bash
cat ${CLAUDE_SKILL_DIR}/../../../.claude/agents/design-critic.md
```

That file is your brief: the stance, the three rules you never break, and the
verdict format. Read it and follow it literally. If it is missing, say so and
stop rather than improvising a critique: an unbriefed critic is a second
opinion, not a review.

**Step 2: resolve the target.**

Target: `$ARGUMENTS`, a file or a directory.

You cannot ask. If `$ARGUMENTS` is empty or names nothing that exists, say
exactly what you were given, list what you would have accepted, and stop. A
critique of a guessed target is worse than no critique, because it reads like a
verdict on the real work.

**Step 3: refuse to critique blind.**

A critique written from source alone is worthless. Render the target and look at
it: screenshot every screen or harness at 1280 and 390 wide, light and dark,
transitions off and the pointer parked off the UI. Then click every control and
write down what actually changed. A control that changes nothing is a finding.

**Step 4: gather the numbers you will cite.**

```bash
KIT=${CLAUDE_SKILL_DIR}/../../..
DS_REQUIRE_BROWSER=1 node $KIT/scripts/taste_audit.mjs      <file> && DS_REQUIRE_BROWSER=1 node $KIT/scripts/taste_audit.mjs <file> --dark
DS_REQUIRE_BROWSER=1 node $KIT/scripts/slop_tells.mjs       <file> && DS_REQUIRE_BROWSER=1 node $KIT/scripts/slop_tells.mjs  <file> --dark
node $KIT/scripts/gate.mjs verify_overflow.mjs  <file|dir>
node $KIT/scripts/gate.mjs verify_responsive.mjs <file|dir> --scale=1.25
```

Report what they actually printed. These are heuristics: they name what you saw,
they do not decide whether it is good. A clean run is not a defence: the kit's
own seeded-defect fixtures pass every one of these gates, in both themes, and
every one of them is work a senior designer would send back.

**Step 5: write the verdict.**

In the format `design-critic.md` specifies: the verdict, the three reasons a
senior designer would send this back, and the findings table with evidence per
finding. Name the file and the element. "The spacing feels off" is not a finding;
"the card's 12px internal gap is the same as the 12px gap between cards, so the
grouping reads as one block" is.

Do not soften it, and do not pad the "what is good" list to balance the tone.

**Step 6: state the scope, every time.**

This is judgement, not measurement. It produces no percentage, and no percentage
in this repo covers taste. Say so in the output.

---

## After the critique comes back

For the session that invoked this skill, not for the fork:

Act on it. Fix every Critical and Major finding, re-run `/gate`, and run this
critique again on what changed. The loop ends when the remaining findings are
Minor or Enhancement, not when you are tired of it.

Scoring the critic itself, rather than the work, is a maintainer task and lives
with the harness in the kit's repository - not here. This skill installs into
your project, and nothing it tells you to do should name a file your install
does not have.

© Thientan Soparat · MIT · plugin87/ux-ui-agent-skills

Similar skills

All skills for Design →

critique by other authors comes first.

critique nexu-io critique scores any HTML artifact against five design criteria and builds a standalone HTML report with a radar chart and Keep / Fix / Quick-wins lists. CX Codex +1 256installs critique NeoLabHQ The critique skill runs finished work past several AI judges: they review it independently, debate their findings, and agree on a shared list of issues. CX Codex +1 1,400installs critique aladicf critique evaluates interface designs from a UX angle, scoring hierarchy and cognitive load. Highlights AI slop patterns and clarifies user flows. CX Codex +1 819installs critique-composition Owl-Listener critique-composition critiques balance, negative space, visual rhythm, and gestalt grouping on rendered screens. Useful when layout hierarchy is solid but the spatial composition still feels off. CX Codex +1 2,500installs critique-affordance Owl-Listener critique-affordance audits rendered screens for interaction signals, state visibility, action discoverability, and primary CTA clarity. CX Codex +1 2,000installs frontend-design-ui-ux ulpi-io The frontend-design-ui-ux skill creates a locked design language and UX/UI specification for a feature or screen. Use it before handing the build to an engineering agent. CX Codex +1 2,500installs claude-design-critic OneWave-AI The claude-design-critic skill reviews a website or UI for generic design and copy, then ranks concrete fixes. Use it after generating a frontend or when a page feels bland. CX Codex +1 184installs audit aladicf audit runs code-level checks on accessibility, performance, theming, responsive design and anti-patterns. Returns a scored report with a fix plan. CX Codex +1 729installs ui-design Starchild-ai-agent ui-design — a build guide and quality gate for visual interfaces, covering track selection, accessibility, responsive behavior, themes, motion, and preview delivery. CX Codex +1 1,800installs

From the same set35

The whole set →
review-and-research review-and-research standardizes UI audits, usability checks, and design handoff requirements. Activates when Claude Code inspects screens or prepares components for developers. CX Codex +1 ★ 3,216repo stars brand-and-operations brand-and-operations is a Claude Code rule for brand consistency, motion, and UI copy. It loads when an agent sets an aesthetic direction, writes interface text, or works on system operations. CX Codex +1 ★ 3,216repo stars typography-and-spacing typography-and-spacing is a Claude Code rule for choosing type scales and layout spacing when an agent works on page typography or rhythm. It also covers checks for Thai text. CX Codex +1 ★ 3,216repo stars scaffold-project scaffold-project — a Claude Code skill that scaffolds a product design workspace with design tokens, rules, and folder structure. Runs when initiating a fresh design system or web application. CX Codex +1 ★ 3,216repo stars design-critic design-critic — a subagent for Claude Code reviews rendered UI screens as an adversarial design director looking for reasons to reject the build. Runs after automated test gates pass. CX Codex ★ 3,216repo stars grill-me The grill-me Claude Code skill asks about a project before implementation and records unanswered decisions as assumptions. Run it before building an interface. CX Codex +1 ★ 3,216repo stars tokens-and-color tokens-and-color is a Claude Code rule for creating, extending, or auditing tokens and choosing interface colors. It defines token layers and contrast requirements. CX Codex +1 ★ 3,216repo stars design-screen The design-screen Claude Code skill plans and builds screens, websites, and interfaces from a request. It routes dense dashboards, redesigns, and screenshot-based work to more specific skills. CX Codex +1 ★ 3,216repo stars

Project sponsors

Companies that keep this analytics open