TypingMindTypingMindThe best frontend for AI
Mobile Redesign Screen logo

Mobile Redesign Screen

Organization
draftbit
mobile-redesign-screen

Audit-first redesign of ONE React Native screen (or one flow of 2-3 screens) - extract its current tokens and patterns, produce rated findings, then modernize it lever by lever with atomic commits and before/after screenshots. Preserves navigation, route names, and form semantics. Use when asked to redesign, refresh, modernize, or "make nicer" a specific existing screen. For whole-app redesigns use mobile-redesign-app; for a report without changes use mobile-design-review; for brand-new screens use mobile-taste.

Overview

Publisherdraftbit
Repositorymobile-taste-skill
Skill namemobile-redesign-screen
Stars
8
Forks
1
Bundled files
Instructions only
Links
Skill sourceRepository
  • 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 Redesign Screen 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/draftbit/mobile-taste-skill/tree/main/skills/mobile-redesign-screen
  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/draftbit/mobile-taste-skill.git /tmp/mobile-taste-skill
mkdir -p .claude/skills
cp -r /tmp/mobile-taste-skill/skills/mobile-redesign-screen .claude/skills/mobile-redesign-screen
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Mobile Redesign Screen 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 Redesign Screen 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 Redesign Screen 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-redesign-screen: One Screen, Audit First

Scope: one screen, or one tight flow (2-3 screens sharing a job). More than that is mobile-redesign-app.

Method files, read in full first: ../_shared/references/redesign-protocol.md (audit, levers, fix loop, risk governor) and ../_shared/references/review-rubric.md (finding format). ../_shared/references/tells.md supplies the findings vocabulary.

Flow

  1. Stack sniff + audit (redesign-protocol.md): the screen's current tokens or inline styles, its dial reading, its place in the route tree, signature interactions, accessibility wins. Screenshot the BEFORE state if a device/preview is reachable.
  2. Mode. Preserve vs overhaul - ask once if ambiguous.
  3. Findings for this screen only, rated high/medium/polish.
  4. Propose the pass. Which levers (type/spacing → color-to-tokens → states → feedback/motion → recomposition), which findings each closes, what will NOT change. One short message; proceed on approval or if the user already said "just do it".
  5. Fix loop (redesign-protocol.md): one finding per atomic commit, before/after pair per visual change, risk governor (stop > 20%, cap 20 fixes).
  6. Close out. Findings closed vs remaining, the before/after pairs, and - if design-baseline.json or MOBILE-DESIGN.md exist - refresh them (deltas noted).

Hard boundaries

  • Never changes: route name, deep link, position in the nav tree, form field semantics, learned gestures. If a finding requires one of those, report it as OUT-OF-SCOPE with a pointer to mobile-redesign-app.
  • Blocks-first: if the screen is an archetype (settings, feed, auth, paywall, empty state), diff it against the matching ../_shared/blocks/ block and prefer converging toward the block over inventing a third pattern.
  • No scope creep: components shared with other screens get changed only when the change is invisible elsewhere or the user approves the blast radius; the risk governor's +5%/file makes this expensive on purpose.
  • The screen must still pass the mobile-taste Section 14 pre-flight when done - a redesigned screen that fails pre-flight is not done.

Frequently asked questions

What does the Mobile Redesign Screen AI skill do?

Audit-first redesign of ONE React Native screen (or one flow of 2-3 screens) - extract its current tokens and patterns, produce rated findings, then modernize it lever by lever with atomic commits and before/after screenshots. Preserves navigation, route names, and form semantics. Use when asked to redesign, refresh, modernize, or "make nicer" a specific existing screen. For whole-app redesigns use mobile-redesign-app; for a report without changes use mobile-design-review; for brand-new screens use mobile-taste.

Why use Mobile Redesign Screen on TypingMind?

Because you install it once and use it with any model. Mobile Redesign Screen 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 Redesign Screen in TypingMind?

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

Which AI models can use Mobile Redesign Screen?

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 Redesign Screen?

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

Is the Mobile Redesign Screen 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.

Related AI Skills

View all
NousResearch logo

Auteur

NousResearch
OrganizationPopular

Design and build cinematic, award-level web pages.

53.5K
250.4K
25 files
View
NousResearch logo

Concept Diagrams

NousResearch
OrganizationPopular

Generate flat, minimal educational SVG visuals as HTML.

53.5K
250.4K
19 files
View
NousResearch logo

Hyperframes

NousResearch
OrganizationPopular

Render MP4/WebM videos from HTML compositions.

53.5K
250.4K
7 files
View
NousResearch logo

Ip As Logo

NousResearch
OrganizationPopular

Design minimal cute IP mascot marks readable at 32px.

53.5K
250.4K
Instructions
View

Set up your own AI workspace now

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