Skip to content
Agentmart
Submit a tool

critique

Score a codebase's design quality 0-100 across six categories (typography, color, spacing, motion, accessibility, consistency) plus an overall weighted score.

Skill by Dragoon0x

IndexedMIT★ 4
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/dragoon0x-critique

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Score a codebase's design quality 0-100 across six categories (typography, color, spacing, motion, accessibility, consistency) plus an overall weighted score. Every score is derived from concrete metrics in dragoon.json with transparent math, no LLM, no vibes. Use when the user asks "what's the design quality of this codebase", "rate my design", "audit the design system", or wants a CI gate for design. Includes a per-category breakdown explaining each deduction. Auto-scans if no manifest exists. Run as `node ~/.claude/skills/dragoon/skills/critique/scripts/critique.js [root]`.

Use cases: design, devops, ml, security

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Node.js package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/critique

What's inside

Skill name
critique
Description
Score a codebase's design quality 0-100 across six categories (typography, color, spacing, motion, accessibility, consistency) plus an overall weighted score. Every score is derived from concrete metrics in dragoon.json with transparent math, no LLM, no vibes. Use when the user asks "what's the design quality of this codebase", "rate my design", "audit the design system", or wants a CI gate for design. Includes a per-category breakdown explaining each deduction. Auto-scans if no manifest exists. Run as `node ~/.claude/skills/dragoon/skills/critique/scripts/critique.js [root]`.
License
MIT
Instructions
53 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (2)

  • SKILL.md
  • critique.js · scripts/

SKILL.md (first lines)

# /critique

0-100 scores for design quality. Transparent math. Every deduction is traceable to a metric in `dragoon.json`.

## When to use

Run /critique when:
- The user asks for a design quality score, audit, rating, or grade
- Setting up a CI gate that fails when design quality drops below a threshold
- Comparing design quality before and after a redesign
- The user says "how good is this", "give me a score", "rate the design system"

## What it produces

Six category scores plus an overall:
- **typography** - font family count, scale ratio confidence, font size variant count
- **color** - distinct color count, palette balance
- **spacing** - grid detection confidence, spacing variant count
- **motion** - easing variant count, duration variant count
- **accessibility** - alt rate, button label rate, semantic tag presence
- **consistency** - shadow variant count, radius variant count

Weighted overall:
```
typography 1.0  color 1.0  spacing 1.2  motion 0.8  accessibility 1.2  consistency 1.0
```

Each score includes a breakdown listing every deduction and reason. You can read exactly why your score is what it is.

## Run it

```
node ~/.claude/skills/dragoon/skills/critique/scripts/critique.js [root]
```

Flags:
- `--manifest <p>` use existing manifest instead of scanning
- `--json` machine-readable
- `--threshold <n>` exit non-zero if overall score below n (CI gate)
- `--no-breakdown` show scores only
- `--quiet` show only the final score
- `--help` full usage

## Use as a CI gate

In package.json:
```
"design:check": "node ~/.claude/skills/dragoon/skills/critique/scripts/critique.js --threshold 80 --quiet"
```

The command exits 1 if the overall score drops below 80, blocking the PR.

From Dragoon0x/dragoon-skills, MIT.

More from Dragoon0x/dragoon-skills

Signals

Stars
4
Forks
0
Open issues
0
Last commit (this folder)
Apr 28, 2026 (6 months ago)
Last release
Apr 28, 2026 (6 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from Dragoon0x

Cite this page

critique skill. Agent Mart. https://agentmart.dev/skills/dragoon0x-critique (last updated 2026-10-24)