Design Critique logo

Design Critique

Community
Dragoon0x
design-critique

Structured frameworks for giving and receiving design feedback that makes work better, not just different.

Overview

PublisherDragoon0x
Repositoryeverything-design-taste
Skill namedesign-critique
Stars
13
Forks
2
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 Dragoon0x on GitHub. Read the source before you install it.

Installation

Install the Design Critique 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/Dragoon0x/everything-design-taste/tree/main/skills/design-critique
  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/Dragoon0x/everything-design-taste.git /tmp/everything-design-taste
mkdir -p .claude/skills
cp -r /tmp/everything-design-taste/skills/design-critique .claude/skills/design-critique
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Design Critique 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 Design Critique 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 Design Critique 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.

Design Critique

Giving Critique

The Framework

For every piece of feedback, hit three points:

  1. Observation — What you see (factual, not opinion)
  2. Impact — Why it matters (connects to goals, users, or principles)
  3. Direction — What to explore (not prescriptive, but generative)

Example:

  • Observation: "The CTA is the same visual weight as the navigation links."
  • Impact: "Users scanning the page won't know where to click first."
  • Direction: "Try increasing the size or contrast of the CTA, or reducing the visual weight of the nav."

What Good Critique Sounds Like

  • "I notice [observation]. How does that serve [the user/the goal]?"
  • "This works well because [specific reason]. What if we pushed it further by..."
  • "The hierarchy here reads as [X] before [Y]. Is that the intended priority?"
  • "I'm drawn to [element], but I think it might compete with [other element]."

What Bad Critique Sounds Like

  • "I don't like it" (not actionable)
  • "Make it pop" (meaningless)
  • "Can we try it in blue?" (prescriptive without rationale)
  • "This is wrong" (no direction, pure criticism)
  • "What if we added..." (solution before understanding the problem)

Critique Priority Order

  1. Strategy — Is this solving the right problem?
  2. Structure — Is the information architecture correct?
  3. Interaction — Does the flow make sense?
  4. Visual — Does it look right?
  5. Polish — Are the details refined?

Don't critique polish when the strategy is wrong.

Receiving Critique

How to Present Work for Critique

  • State what you want feedback on (scope the conversation)
  • Explain the constraints you're working within
  • Share what you've already tried and why you moved past it
  • Don't apologize for unfinished work (it's a critique, not a showcase)

How to Process Feedback

  • Write it down before responding
  • Ask clarifying questions ("Can you say more about what feels off?")
  • Look for patterns (if 3 people mention hierarchy, it's a hierarchy problem)
  • Separate "I don't prefer this" from "this doesn't work for users"
  • You don't have to act on everything. But you should understand everything.

Running a Critique Session

Format (60 min max)

  1. Context (5 min) — Designer presents the problem, constraints, current state
  2. Silent review (5 min) — Everyone looks without speaking
  3. Clarifying questions (5 min) — "What does this state do?" not "Why did you..."
  4. Feedback (30 min) — One at a time, using the observation-impact-direction framework
  5. Synthesis (10 min) — Designer summarizes what they heard and intended next steps
  6. Written follow-up — Key feedback documented within 24 hours

Frequently asked questions

What does the Design Critique AI skill do?

Structured frameworks for giving and receiving design feedback that makes work better, not just different.

Why use Design Critique on TypingMind?

Because you install it once and use it with any model. Design Critique 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 Design Critique in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Dragoon0x/everything-design-taste/tree/main/skills/design-critique. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Design Critique?

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 Design Critique?

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

Is the Design Critique AI skill free?

Yes. It is published on GitHub by Dragoon0x 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 👇