Mobile Design Review

Organization

draftbit

mobile-design-review

Audit an existing React Native / Expo app's design - run the AI-tells grep checklist, inspect screens against a ten-category rubric, Trunk Test each screen, and produce impact-rated findings with a Design Score and an AI Slop Score plus a regression baseline. Report-only by default; opt-in fix mode. Use when asked to review, audit, critique, or QA an app's design or UI quality. For building new screens use mobile-taste; for actually redesigning use mobile-redesign-screen or mobile-redesign-app.

Overview

Publisher	draftbit
Repository	`mobile-taste-skill`
Skill name	`mobile-design-review`
Stars	8
Forks	1
Bundled files	Instructions only
Links	Skill source Repository

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 draftbit on GitHub. Read the source before you install it.

Installation

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

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/draftbit/mobile-taste-skill/tree/main/skills/mobile-design-review
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.

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/draftbit/mobile-taste-skill.git /tmp/mobile-taste-skill
mkdir -p .claude/skills
cp -r /tmp/mobile-taste-skill/skills/mobile-design-review .claude/skills/mobile-design-review

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Mobile 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 Mobile 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 Mobile 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.

mobile-design-review: Audit, Score, Baseline

Report-only by default. --fix (or the user asking you to fix what you find) enables the fix loop. Never both silently.

The method is ../_shared/references/review-rubric.md (passes, narration, Trunk Test, finding format, ten categories, scoring math, baseline file) and ../_shared/references/tells.md (the grep checklist + tell catalog). Fix recommendations cite ../_shared/references/redesign-protocol.md (lever order) and sections of ../mobile-taste/SKILL.md. Read all four before starting.

Flow

Stack sniff. package.json / app.json / theme files / MOBILE-DESIGN.md / design-baseline.json. If a baseline exists, this run is a REGRESSION run - deltas lead the report.
Scope. Whole app by default; a named screen/flow if the user scoped it. List the screens you will cover (from the route tree) so coverage is explicit.
Static pass (always): the tells.md grep block, then code inspection per the ten rubric categories. Triage every hit.
Live pass (when reachable): simulator/emulator → Expo web phone-viewport → user-provided screenshots, in that order. Per screen: screenshot, first-impression narration, Trunk Test, touch targets, dark mode + large fonts when practical. If nothing is reachable, say so and continue static-only.
Findings. review-rubric.md format: FINDING-NNN [impact | category], evidence, tell number when it maps, concrete fix.
Scores. Design Score + AI Slop Score per the mechanical letter math. Per-category letters in a table. No rounding up.
Baseline. Write/refresh design-baseline.json. On a regression run, the delta table (category changes, new, resolved) comes FIRST.
Report. Narrations, Trunk Test results, findings by impact, scores, the explicit unverified list ("no device reachable: keyboard, splash, scroll perf, font scale, edge-to-edge NOT verified"), and - report-only mode - a recommended fix order (the modernization-lever order from ../_shared/references/redesign-protocol.md).

Fix mode (opt-in only)

Runs the fix loop from redesign-protocol.md: one finding per atomic commit (style(design): FINDING-NNN ...), before/after screenshots when a live pass exists, re-check to close, risk governor (stop > 20%, hard cap 20 fixes), findings marked fixed in the baseline. Constraints:

Never touches navigation structure, route names, deep links, tab order, token names, or form field semantics - those are redesign-skill territory and approval-gated there.
High-impact findings first, then medium; polish only if the user asked for polish.
Stopping at the governor is a success state: report fixed / remaining / risk math.

Rules that bind this skill

Report-only means ZERO app-file edits. The one sanctioned write is design-baseline.json (the review's own artifact); skip even that if the user asked for zero writes and inline the JSON in the report instead.
Every score follows the math; every dismissed grep hit gets its one-line reason.
If the project declares design commitments - MOBILE-DESIGN.md, or any equivalent committed design doc - findings also flag DRIFT from them (a declared accent used inconsistently, a Nav Read the code no longer matches). Name the doc you used.

Frequently asked questions

What does the Mobile Design Review AI skill do?

Why use Mobile Design Review on TypingMind?

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

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

Which AI models can use Mobile 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 Mobile Design Review?

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

Is the Mobile Design Review AI skill free?

It is published on GitHub by draftbit. Check the repository for licensing terms. 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

Proof Video

openclaw

OrganizationPopular

Add subtitles, captions, narration cues, or zoom to a proof video or PR recording using repo-local capture helpers and a system ffmpeg renderer.

Slack E2e

Test Slack with Convex-leased user OAuth or QA bots; check credentials, exercise owned messages, prove Gateway behavior, and distinguish API evidence from real Slack client interactions.

Telegram E2e Userbot

Prove user-visible OpenClaw Telegram behavior on Telegram's Test Server with Convex-leased team credentials; drive real-user turns and record messages, edits, deletions, reactions, typing, or rich…

Module Regression

Govern cross-module regression in large repositories with a REGRESSION.md ledger that records each module's downstream consumers and executable acceptance command. After a change, run the changed…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

mobile-design-review: Audit, Score, Baseline

Flow

Fix mode (opt-in only)

Rules that bind this skill

Frequently asked questions

Related AI Skills

Set up your own AI workspace now