design-polish

design-polish is a skill for Claude Code, Codex from ChunkyTofuStudios/flutter-skills. It costs 204 tokens per session (3,490 once invoked), scanned A, original, MIT.

A workflow for improving the visual design of Flutter app screens, including layout hierarchy, text, colors, contrast, spacing, and section clarity. It uses a reference screen and an Android emulator to guide and check changes.

In plain words
What is it for?
Use it to refine named Flutter screens or components, compare before-and-after emulator screenshots, and improve how clearly users can read and navigate the interface.
Why use it?
It helps keep improvements consistent with the app's existing visual style and evaluates each round using screenshots and an independent review instead of relying only on the developer's opinion.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit Use it to refine named Flutter screens or components, compare before-and-after emulator screenshots, and improve how clearly users can read and navigate the interface.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/chunkytofustudios/flutter-skills/design-polish
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add ChunkyTofuStudios/flutter-skills --skill design-polish
Clone the repo
git clone --depth 1 https://github.com/ChunkyTofuStudios/flutter-skills

Made for: Claude Code, Codex.

Its marketplace also offers this one on its own, as the plugin design-polish/plugin install design-polish after adding the marketplace above.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for design-polish

README.md
[![agentmods](https://agentmods.dev/badge/skills/chunkytofustudios/flutter-skills/design-polish/github.svg)](https://agentmods.dev/skills/chunkytofustudios/flutter-skills/design-polish)
Your own site
<a href="https://agentmods.dev/skills/chunkytofustudios/flutter-skills/design-polish"><img src="https://agentmods.dev/badge/skills/chunkytofustudios/flutter-skills/design-polish/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for design-polish

Your own site · 80×15
<a href="https://agentmods.dev/skills/chunkytofustudios/flutter-skills/design-polish"><img src="https://agentmods.dev/badge/skills/chunkytofustudios/flutter-skills/design-polish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 204 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,490 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00204 $0.03490
Opus 5 $0.00102 $0.01745
Sonnet 5 $0.00041 $0.00698
Haiku 4.5 $0.00020 $0.00349

Measured 11d ago against content hash 9273255ef417, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

design-polish scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/design-polish/SKILL.md · 210 lines

How it starts

The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design polish (Flutter)

You polish screens in a Flutter mobile app — improving visual hierarchy, readability, and section clarity so a user instantly knows how to use the app. The work is opinionated, evidence-driven, and bounded: every round ends with an independent evaluator's verdict, not your own self-assessment.

Setup

If the user didn't specify screens, ask:

  • "Which screens should I polish? Provide route names (e.g. /settings, /profile) or component file paths under lib/."

The app must be running on an Android emulator. Use the android-emulator skill — every screenshot, tap, swipe, and accessibility-tree dump in this workflow goes through it:

scripts/emu.sh health        # confirm device, AVD, foreground app
scripts/emu.sh boot          # if not running
scripts/emu.sh run           # build & install in background
scripts/emu.sh wait-run      # block until attached

Establish design tone

Do this once before touching any screen. Skipping it is the single biggest source of inconsistency — your changes will look right in isolation and wrong next to the rest of the app.

  1. Find a reference screen. Try in this order:
    • The user named a polished screen ("settings looks great, polish the rest to match"). Use that.
    • The home page: MaterialApp.home, initialRoute, or the first tab of a BottomNavigationBar in lib/main.dart or the router config (GoRouter, AutoRoute, etc.).
    • Files named home_page.dart, home_screen.dart, dashboard.dart.
  2. Read its source. Open the screen's widget file plus everything it imports from lib/theme/, lib/widgets/, and any custom ThemeExtensions. Note ColorScheme, TextTheme, spacing constants, radius values, and any shared layout primitives.
  3. Screenshot it on the emulator. Navigate with tap-label if needed, then scripts/emu.sh screenshot and read the printed path. Scroll and capture each state.
  4. Write the design tone in 3–5 specific bullets. What makes this app's screens feel like this app and not a generic Material default. Pick the axes that actually distinguish the reference screen — describe what's there, not what you wish were there:
    • Mood — e.g. calm/restrained, playful/energetic, bold/arcade, soft/cozy, retro, neon.
    • Fonts — which families and weights, where each is applied. Lock the list.
    • Color — the full ColorScheme story: restrained palette vs. expressive, flat vs. gradient, saturation level, semantic tokens, any ThemeExtensions.
    • Surfaces — card backgrounds, borders, corner radius, elevation/shadow, blur.
    • Hierarchy lever — how the app signals importance: weight, color, spacing, border, accent, illustration, or a mix.
    • Motion — none, subtle Material defaults, or expressive (custom curves, hero transitions, Lottie/Rive).

Read the full file on GitHub · 210 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 210 lines · 204 tokens per session scan A 9273255ef417

Subscribe to this mod's changes

design-polish is a skill published in the GitHub repository ChunkyTofuStudios/flutter-skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 204 tokens to every session and 3,490 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

display-glasses-with-jetpack-compose-glimmer

Provides guidelines for developing projected Android XR apps for display glasses using the Jetpack Compose Glimmer UI toolkit. This skill covers foundational Glimmer design principles, workflows for implementing Jetpack Compose Glimmer, and interaction models for the glasses form factor. Use this skill to build an…

android/skills · 91 tokens

expo-design-system

Framework (OSS). Build and maintain a design system inside an Expo app - a reusable theme of design tokens (color, spacing, typography, radius, shadow, motion), reusable component structure with variant/size/state prop conventions, and rules for when to extract a repeated view into a shared component. Use when…

expo/skills · 201 tokens

flutter-build-responsive-layout

Use LayoutBuilder, MediaQuery, or Expanded/Flexible to create a layout that adapts to different screen sizes. Use when you need the UI to look good on both mobile and tablet/desktop form factors.

flutter/agent-plugins · 51 tokens

omh-apple-design

This is a Hermes-native apple-design workflow skill.

rlaope/oh-my-hermes · 73 tokens

axiom-audit-liquid-glass

Use when the user mentions Liquid Glass review, iOS 26 UI updates, toolbar improvements, or visual effect migration.

CharlesWiltgen/Axiom · 32 tokens

axiom-audit-ux-flow

Use when the user mentions UX flow issues, dead-end views, dismiss traps, missing empty states, broken user journeys, or wants a UX audit of their iOS app.

CharlesWiltgen/Axiom · 43 tokens