Ux Design Review logo

Ux Design Review

Organization
Uxcel-Lab
ux-design-review

Orchestrated, holistic UX review of a screen, flow, or component. Establishes context once, auto-runs the always-relevant lenses (usability, microcopy, dark patterns), offers the context-dependent ones (accessibility, aesthetics, IA, mobile, visual foundations), and returns one prioritized report. Trigger when the user asks for a full design review, "review my UI/screen/flow", "is this good UX", "audit this design", or general design feedback — but NOT when they name a single specific lens.

Overview

PublisherUxcel-Lab
Repositoryproduct-skills
Skill nameux-design-review
Stars
35
Forks
8
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 Uxcel-Lab on GitHub. Read the source before you install it.

Installation

Install the Ux Design 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/Uxcel-Lab/product-skills/tree/main/ux/workflows/design-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/Uxcel-Lab/product-skills.git /tmp/product-skills
mkdir -p .claude/skills
cp -r /tmp/product-skills/ux/workflows/design-review .claude/skills/ux-design-review
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ux Design 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 Ux Design 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 Ux Design 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.

Design Review (UX Orchestrator) Skill

How this skill behaves (read first)

This is the front door for holistic UX review. It is the executable form of docs/orchestration-policy.md — it decides which audit lenses run, which are offered, and which are suppressed, then returns one prioritized report instead of a pile of separate audits.

Its whole job is to avoid two opposite failures: doing a flat "looks good" review with no framework, and firing every audit in the repo regardless of relevance (the bandwagon).

When NOT to use this skill: if the user named a specific lens ("run the accessibility audit", "check this for dark patterns"), skip this orchestrator and invoke that one skill directly. Explicit scope overrides orchestration.


Step 0 — Establish the context profile (once)

Infer these from what the user gave you; ask only the one that's unknown and changes what runs. Persist for the session — don't re-ask.

  • Design system in play? Infer yes if they provided tokens, a styleguide, a component library, a Figma library, themed component code, or said "our design system / our brand guidelines." Otherwise ask once: "Are you working from an established design system, or designing from scratch?" — this is the single biggest driver of what gets skipped.
  • Platform — mobile or web (decides whether mobile-responsiveness is relevant).
  • Primary task — what the user actually came to do (used to resolve conflicts later).

State the assumptions you're proceeding with in one line.


Step 1 — Determine the traits of the work

Look at the artifact and note which are true:

  • Interactive UI? (almost always yes)
  • Contains user-facing copy?
  • Involves conversion / pricing / sign-up friction / opt-ins / cancellation?
  • Multi-screen or structures content?
  • Targets mobile?

Step 2 — Auto-run the always-relevant lenses (Tier A)

Run these whenever their trait is present. They don't depend on the visual system and almost always earn their keep:

  • ux-heuristics-audit — any interactive UI. Usability behavior, feedback, error recovery.
  • ux-microcopy-audit — any user-facing copy. Clarity, tone, error/empty/CTA wording.
  • ux-dark-patterns-audit — any conversion/pricing/opt-in/cancellation surface.

These run unprompted. The design-system profile does not suppress them.

Each lens is named by its installable skill name. Invoke a lens only if that skill is installed; if one isn't, list it under "available but not run" in the report and don't block — this orchestrator degrades to whichever lenses are present.


Step 3 — Offer the context-dependent lenses (Tier B)

These are relevant but should be offered, not fired — and several are suppressed when a design system is in play. Apply the suppression matrix from the policy:

LensOffer whenIf design system in play
ux-accessibility-auditany UINarrow to usage — custom color combos, focus order, alt text, labels; don't re-audit the token palette
ux-aesthetics-auditany visual UISuppress — visual harmony is already defined
ux-information-architecture-auditmulti-screen / structured contentUnaffected — offer
ux-mobile-responsiveness-auditplatform = mobileUnaffected — offer
ux-color (as lens)palette is being defined/changedSuppress — tokens own color
ux-typography (as lens)type is being defined/changedSuppress — tokens own type
ux-layout-spacing-grids (as lens)spacing/grid is being defined/changedSuppress — the scale owns spacing

Say the suppression out loud, briefly: "Your design system owns color, type, and spacing, so I'm skipping those and checking how the system is applied (accessibility-in-use, IA, copy)."

Then offer the rest: "Want me to also run accessibility-in-use and an IA pass?" If the user opts in, run them; otherwise leave them listed as available.


Step 4 — Merge into one prioritized report

De-duplicate findings across lenses (if heuristics and accessibility both flag the same unlabeled control, report it once, tagged with both). Resolve any cross-lens conflicts toward the primary task from Step 0. Output a single severity-ordered list:

## Design Review — [target]
Context: [platform · design system: yes/no · primary task]
Lenses run: [heuristics, microcopy, …]   Lenses available but not run: [aesthetics, …]

### Critical
- [Issue] — what's wrong → fix. (heuristic / a11y / dark-pattern / …)
### Major
- …
### Minor
- …
### Working well ✓
- …

**Top 3 priorities:** the highest-impact fixes across all lenses.
Offered, not run: accessibility-in-use, IA — say the word and I'll add them.

Common do/don't patterns

❌ Don't✅ Do
Fire all seven UX audits because the work "is a UI"Auto-run Tier A; offer Tier B; suppress what the design system owns
Re-audit color/type/spacing when the user has a design systemSkip them out loud; check application instead
Return one report per auditMerge into a single prioritized, de-duplicated list
Run this orchestrator when the user asked for one named lensDefer to that lens directly (explicit scope wins)
Silently skip accessibility because there's a design systemNarrow it to usage checks — never drop it entirely

Relationship to the policy

This skill is docs/orchestration-policy.md in executable form. If the two ever diverge, the policy governs; update this skill to match it.

Source lessons (Uxcel)

This is an orchestrator — its substance lives in the lenses it routes to. See the source lessons in each: ux-heuristics-audit, ux-microcopy-audit, ux-dark-patterns-audit, ux-accessibility-audit, ux-aesthetics-audit, ux-information-architecture-audit, ux-mobile-responsiveness-audit.

Frequently asked questions

What does the Ux Design Review AI skill do?

Orchestrated, holistic UX review of a screen, flow, or component. Establishes context once, auto-runs the always-relevant lenses (usability, microcopy, dark patterns), offers the context-dependent ones (accessibility, aesthetics, IA, mobile, visual foundations), and returns one prioritized report. Trigger when the user asks for a full design review, "review my UI/screen/flow", "is this good UX", "audit this design", or general design feedback — but NOT when they name a single specific lens.

Why use Ux Design Review on TypingMind?

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

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

Which AI models can use Ux Design 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 Ux Design Review?

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

Is the Ux Design Review AI skill free?

Yes. It is published on GitHub by Uxcel-Lab 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 👇