God Review logo

God Review

Community
cumabozkurt
god-review

Structured design critique and quality audit - a 10-dimension scored rubric (concept, hierarchy, layout, typography, color, imagery, consistency, usability, accessibility, craft/polish), screenshot or code review workflow, prioritized fix lists, and medium-specific checklists for web, mobile, social, print, branding and slides. Use when asked to review, critique, audit, grade or improve an existing design, mockup, screenshot, URL or front-end code.

Overview

Publishercumabozkurt
Repositorygod-of-design
Skill namegod-review
Stars
7
Forks
1
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by cumabozkurt on GitHub. Read the source before you install it.

Installation

Install the God Review AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/cumabozkurt/god-of-design/tree/main/skills/god-review
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/cumabozkurt/god-of-design.git /tmp/god-of-design
mkdir -p .claude/skills
cp -r /tmp/god-of-design/skills/god-review .claude/skills/god-review
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable God Review in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads God Review on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so God Review is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

God Review: Design Critique

Workflow

  1. Understand intent. What is it, who is it for, what is its single job? If unknown, infer and state your assumption.
  2. Look like a user, then like a designer. First impression in 5 seconds (what do you notice, what do you understand?), then a systematic pass.
  3. Score each dimension 0–10 with one-line evidence.
  4. Prioritise fixes: P0 (broken: usability, accessibility, legal), P1 (strong quality gains), P2 (polish). Give each fix as an exact change (value, token, code), not advice.
  5. Optionally apply the fixes if you have file access and the user wants it. Re-score after.

Rubric (0–10 each, total /100)

#Dimension9–10 looks like
1Concept & directionClear, ownable idea rooted in the subject; consistent everywhere
2HierarchyObvious first/second/third read; the primary action is unmistakable
3Layout & spacingGrid-aligned, a consistent spacing scale, rhythm with deliberate breaks
4TypographyDeliberate fonts, a modular scale, good measure/leading, correct language support
5ColourPurposeful palette, one accent, semantic roles, harmony
6Imagery & iconographySpecific, high quality, a consistent style, no generic stock or emoji
7Consistency & systemTokens, reusable components, the same patterns for the same things
8Usability & UXClear flows, conventions respected, all states designed, fast
9AccessibilityWCAG 2.2 AA met: contrast, focus, semantics, motion, alt text
10Craft & polishOptical alignment, concentric radii, crisp assets, no orphans, real copy

Bands: 90+ exceptional · 75–89 strong, ship with tweaks · 60–74 decent but generic · < 60 rework the direction.

Output format

markdown
## Design review: <name>  ·  Score: 72/100 (decent but generic)
**Intent (assumed):** …
**5-second read:** …

| Dimension | Score | Evidence |
|---|---|---|
| Concept | 6 | Reads as a generic SaaS template; nothing from the tea-ceremony subject |
…

### P0: must fix
1. Body text #9CA3AF on #FFFFFF = 2.5:1 → use #4B5563 (7.6:1).
### P1: high impact
1. Replace the 3 identical feature cards with a split layout:
   image left, 3 numbered steps right (real sequence).
### P2: polish
1. Inner radius 16px inside a 16px card with 16px padding → inner radius 0–4px (concentric).

Medium checklists

  • Web/app: responsive 320→1440, focus states, form errors, empty/loading states, performance (LCP < 2.5s, CLS < 0.1, INP < 200ms), SEO basics (title, meta description, OG image 1200×630, semantic headings).
  • Social: exact platform size, safe zones, legible at 30% scale, ≤ 25 words/frame, brand consistency across the series, alt text and captions.
  • Print: bleed/safe area, CMYK, 300ppi, rich black only for large areas, fonts outlined/embedded, spelling of names and dates, QR tested.
  • Branding: works at 16px and in 1 colour, distinct from competitors, construction consistent, a full lockup set, trademark sanity check.
  • Slides: assertion titles, one idea per slide, ≥ 28px body at 1920 width, charts with highlighted takeaways, consistent layouts.
  • Image generation: anatomy, hands, text artefacts, style consistency, licence/ethics.

Always run god-anti-slop's slop gate as part of the review.

Frequently asked questions

What does the God Review AI skill do?

Structured design critique and quality audit - a 10-dimension scored rubric (concept, hierarchy, layout, typography, color, imagery, consistency, usability, accessibility, craft/polish), screenshot or code review workflow, prioritized fix lists, and medium-specific checklists for web, mobile, social, print, branding and slides. Use when asked to review, critique, audit, grade or improve an existing design, mockup, screenshot, URL or front-end code.

Why use God Review on TypingMind?

Because you install it once and use it with any model. God Review is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install God Review in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/cumabozkurt/god-of-design/tree/main/skills/god-review. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use God Review?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with God Review?

As many as you like. As long as a model supports skills, you can use God Review with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the God Review AI skill free?

Yes. It is published on GitHub by cumabozkurt under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇