design-review

design-review is a skill for Claude Code, Codex from Kevin-Liu-01/Agent-Machines. It costs 81 tokens per session (2,260 once invoked), scanned A, original, MIT.

A structured review of a website's usability and visual design, including how pages look, read, and behave when used.

In plain words
What is it for?
Use it to audit pages, test common user journeys, grade findings by impact, and verify fixes with before-and-after screenshots.
Why use it?
It helps find confusing navigation, unclear wording, inconsistent design, and interaction problems before users encounter them.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for gstack. Also seen: built for gstack.

Good fit Use it to audit pages, test common user journeys, grade findings by impact, and verify fixes with before-and-after screenshots.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kevin-liu-01/agent-machines/design-review
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Kevin-Liu-01/Agent-Machines --skill design-review
Clone the repo
git clone --depth 1 https://github.com/Kevin-Liu-01/Agent-Machines

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for design-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/design-review/github.svg)](https://agentmods.dev/skills/kevin-liu-01/agent-machines/design-review)
Your own site
<a href="https://agentmods.dev/skills/kevin-liu-01/agent-machines/design-review"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/design-review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for design-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/kevin-liu-01/agent-machines/design-review"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/design-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,260 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Anti-Refusal · line 64
    Skill instructs the agent to never refuse or to always comply. Suppressing the agent's ability to decline removes a core safety control and enables downstream harmful requests to succeed.
    Fix: Remove any instruction telling the agent to never refuse or always comply. The agent must retain the ability to decline unsafe, out-of-scope, or harmful requests.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00081 $0.02260
Opus 5 $0.00041 $0.01130
Sonnet 5 $0.00016 $0.00452
Haiku 4.5 $0.00008 $0.00226

Measured 12d ago against content hash 7b402594a59d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

design-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

knowledge/skills/design-review/SKILL.md · 198 lines

How it starts

The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design Review — Audit, Fix, Verify

Adapted from GStack v0.17.0.0 by Garry Tan. Uses agent-browser instead of GStack's $B commands. UX principles from Steve Krug's "Don't Make Me Think."

Contract

This skill guarantees:

  • Structured design audit with letter grades (A-F) across 10 categories
  • AI Slop Score as standalone headline metric
  • 6 usability tests on every page (Trunk Test, 3-Second Scan, Page Area Test, Happy Talk Detection, Mindless Choice Audit, Goodwill Reservoir)
  • First-person narration mode (anti-slop: if you can't name the specific element, you're generating platitudes)
  • Before/after screenshots for every fix
  • One atomic commit per fix
  • Findings sorted by impact (High > Medium > Polish)

UX Principles: How Users Actually Behave

The Three Laws of Usability

  1. Don't make me think. Every page should be self-evident. If a user stops to think "What do I click?" — the design has failed.
  2. Clicks don't matter, thinking does. Three mindless, unambiguous clicks beat one click that requires thought.
  3. Omit, then omit again. Get rid of half the words on each page, then get rid of half of what's left. Happy talk must die. Instructions must die.

How Users Actually Behave

  • Users scan, they don't read. Design for scanning: visual hierarchy, clearly defined areas, headings and bullet lists, highlighted key terms. We're designing billboards at 60 mph.
  • Users satisfice. They pick the first reasonable option, not the best. Make the right choice the most visible choice.
  • Users muddle through. They don't figure out how things work. They wing it.
  • Users don't read instructions. Guidance must be brief, timely, and unavoidable.

Billboard Design for Interfaces

  • Use conventions. Logo top-left, nav top/left, search = magnifying glass. Don't innovate on navigation to be clever.
  • Visual hierarchy is everything. More important = more prominent. If everything shouts, nothing is heard.
  • Make clickable things obviously clickable. No relying on hover states for discoverability.
  • Eliminate noise. Fix noise by removal, not addition.
  • Clarity trumps consistency.

Read the full file on GitHub · 198 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 198 lines · 81 tokens per session scan A 7b402594a59d

Subscribe to this mod's changes

design-review is a skill published in the GitHub repository Kevin-Liu-01/Agent-Machines (29 stars, last pushed today), licensed MIT. It adds 81 tokens to every session and 2,260 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

21st-ui

Find, install, and generate UI with 21st.dev. Use when the user asks for a UI component (pricing table, hero, navbar, dashboard, form, etc.), wants design inspiration, needs a brand logo as an SVG component, or wants to generate new UI from a prompt.

21st-dev/magic-mcp · 63 tokens

omarchy-theme-maker

Use when an Omarchy desktop should be themed from a wallpaper or photo by deriving a contrast-checked colors.toml palette from the image, installing it as the theme background, and applying it with omarchy theme set.

asimons81/hermes-field-kit · 49 tokens

kernelcad-authoring

Author or modify kernelCAD models in TypeScript. Scripts live in .kcad.ts files; the kernelCAD CLI (kernelcad evaluate and kernelcad export stl|step|dxf|3mf|glb -o ) executes them via an OpenCASCADE WASM kernel.

w1ne/kernelCAD-web · 55 tokens

maya-primitives

Authoring stage — schema-validated quick path for creating polygon primitives and editing transforms. Use for predictable, agent-driven primitive creation; the parameters are validated by inputSchema and the results carry structured object names. For complex mesh editing use maya-mesh-ops, for materials use…

dcc-mcp/dcc-mcp-maya · 81 tokens

kernelcad-trace-from-image

Convert pixel-space features from a reference photo into normalized [0,1] waypoints, then into mm coordinates feedable to path().spline / path().nurbsSegment. Uses the tracefromimage MCP tool. Load when your blockout is in place and the next step is an organic-curve outline (eyewear brow, ergonomic handle, sneaker…

w1ne/kernelCAD-web · 96 tokens

holix-cron

Schedule recurring agent tasks via Holix built-in gateway cron (not crontab or custom scripts).

javded-itres/Holix · 25 tokens