Agent skill

UI Aesthetics Judgment

by kasonye in kasonye/ui-aesthetics-skill

Sets rules for web UI work that favor hierarchy, spacing and restrained styling, with routes for generating, reviewing and polishing interfaces.

No licenceAuto-check passedFrontend & Design

Install UI Aesthetics Judgment

skills CLI
$ npx skills add kasonye/ui-aesthetics-skill --skill ui-aesthetics -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install kasonye/ui-aesthetics-skill ui-aesthetics --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
ui-aesthetics
GitHub stars
383
Token cost
~3.2k tokens
SKILL.md length
1,663 words
Files
55 (incl. references, assets)
Skills in repo
1
Repo updated
First seen
Licence
None found

At a glance

Sets rules for web UI work that favor hierarchy, spacing and restrained styling, with routes for generating, reviewing and polishing interfaces.

  • Works in 6 steps: Generation → Review → Refactor → …
  • Reviewing a web interface that feels cluttered or generic
  • SKILL.md covers Intent, Task Routing, Non-Negotiables and Priority Order, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Aimed at web interfaces that look generic, cluttered, flat, over-styled or machine-made, the skill sets a few operating rules. Keep the scope and information density the user asked for, fix hierarchy, spacing and typography before decoration, prefer restrained neutrals with disciplined accents and consistent state behavior, and use depth, blur, glow or motion only when they clarify structure or interaction.

Work is routed into six kinds: generation, review, refactor, component polish, state and motion refinement, and depth and lighting refinement. When a request mixes critique and rewrite, it diagnoses first. Shared files core.md, reference-map.md and usage.md are read first, and detailed reference files are opened only when the task calls for them.

Output follows a contract: state the chosen route and the visual idea early, keep critique actionable and tied to hierarchy, trust, clarity or interaction quality, say whether a rewrite is light polish, a medium restructure or a full rebuild, and keep solutions shippable and maintainable.

When your agent uses it

  • Reviewing a web interface that feels cluttered or generic
  • Polishing a single component's states, spacing and typography
  • Toning down heavy motion, glow or blur on an over-styled page
  • Generating a new page with a clear visual hierarchy

Example prompts

  • “Review this dashboard layout and tell me what makes it feel cluttered.”
  • “Polish the pricing card component: spacing, hover and focus states, nothing flashy.”
  • “This landing page looks AI-generated. Diagnose it first, then do a light polish.”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Generation
  2. Review
  3. Refactor
  4. Component Polish
  5. State / Motion Refinement
  6. Depth / Lighting Refinement

What it can do on your machine

Read from SKILL.md and the folder at commit b40c8c6. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

UI Aesthetics Judgment loads about 3.2k tokens when it runs, and up to ~22k if it reads all its reference files. Until then it costs about 137 tokens; SKILL.md has 1,663 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~137
When it runs · the whole SKILL.md, loaded when a task matches
~3.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~22k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 1,663 words (~3,234 tokens).

“Use this skill to make web UI output feel more professional, stable, and product-grade.”

— opening of SKILL.md by kasonye
name
ui-aesthetics

Read the full SKILL.md on GitHub

Files

SKILL.md and 54 other files (references, assets) in the repository root of kasonye/ui-aesthetics-skill.

  • SKILL.md
  • .agent/workflows/ui-aesthetics.md
  • .agents/skills
  • .claude/skills
  • .codebuddy/commands/ui-aesthetics.md
  • .codex/skills
  • .cursor/rules/ui-aesthetics.mdc
  • .gemini/skills
  • .github/prompts/ui-aesthetics.prompt.md
  • … and 46 more

Open the folder on GitHubat commit b40c8c6

Compare with similar skills

UI Aesthetics Judgment next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

UI Aesthetics Judgment compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
UI Aesthetics Judgment this skillkasonye/ui-aesthetics-skill383—~3.2kAutomated safety check: PassNone
UI Design Reviewjayminwest/warren481—~1.9kAutomated safety check: PassMIT
Frontend DesignYYH211/Claude-meta-skill2821 repos~2.2kAutomated safety check: PassMIT
Frontend DesignJetBrains/skills366129 repos~1.2kAutomated safety check: PassApache-2.0
Interface Design for Dashboards and Appsholaboss-ai/holaOS11k3 repos~6kAutomated safety check: PassMIT
Senior FrontendOhh-889/skyroc7952 repos~1.1kAutomated safety check: NotesMIT

Similar skills

  • UI Design Review

    jayminwest/warren

    Independent design review of a warren web-UI change. An agent skill from jayminwest/warren.

    481 GitHub stars~1.9k tokensUpdated yesterday
    Frontend & DesignAuto-check passed
  • Frontend Design

    YYH211/Claude-meta-skill

    Creates unique, production-grade frontend interfaces with exceptional design quality.

    282 GitHub starsUsed in 1 repo~2.2k tokens
    Frontend & DesignAuto-check passed
  • Frontend Design

    JetBrains/skills

    Official

    Create distinctive, production-grade frontend interfaces with high design quality.

    366 GitHub starsUsed in 129 repos~1.2k tokens
    Frontend & DesignAuto-check passed
  • Pushes an agent past generic defaults when designing dashboards, admin panels, SaaS apps and tools, with attention to structure, type, navigation and how data is shown.

    11k GitHub starsUsed in 3 repos~6k tokens
    Frontend & DesignAuto-check passed
  • Senior Frontend

    Ohh-889/skyroc

    Comprehensive frontend development skill for building modern, performant web applications using ReactJS, NextJS, TypeScript, Tailwind CSS.

    795 GitHub starsUsed in 2 repos~1.1k tokens
    Frontend & DesignAuto-check: notes
  • Userinterface Wiki

    raphaelsalaja/userinterface-wiki

    UI/UX best practices for web interfaces. An agent skill from raphaelsalaja/userinterface-wiki.

    907 GitHub stars~3.5k tokensUpdated 2 mo ago
    Frontend & DesignAuto-check passed

Questions about UI Aesthetics Judgment

What does UI Aesthetics Judgment do?

Sets rules for web UI work that favor hierarchy, spacing and restrained styling, with routes for generating, reviewing and polishing interfaces. Aimed at web interfaces that look generic, cluttered, flat, over-styled or machine-made, the skill sets a few operating rules. Keep the scope and information density the user asked for, fix hierarchy, spacing and typography before decoration, prefer restrained neutrals with disciplined accents and consistent state behavior, and use depth, blur, glow or motion only when they clarify structure or interaction.

When should I use UI Aesthetics Judgment?

UI Aesthetics Judgment fits situations like: reviewing a web interface that feels cluttered or generic; polishing a single component's states, spacing and typography; toning down heavy motion, glow or blur on an over-styled page; generating a new page with a clear visual hierarchy.

How do I install UI Aesthetics Judgment in Claude Code?

Run `npx skills add kasonye/ui-aesthetics-skill --skill ui-aesthetics -a claude-code`. Or copy the skill folder (the kasonye/ui-aesthetics-skill repository) into .claude/skills/ui-aesthetics in your project. Claude Code loads it when a task matches its description.

How do I install UI Aesthetics Judgment in Codex?

Run `npx skills add kasonye/ui-aesthetics-skill --skill ui-aesthetics -a codex`. Or copy the skill folder (the kasonye/ui-aesthetics-skill repository) into .agents/skills/ui-aesthetics in your project. Codex loads it when a task matches its description.

Can I use UI Aesthetics Judgment in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add kasonye/ui-aesthetics-skill --skill ui-aesthetics -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ui-aesthetics, .gemini/skills/ui-aesthetics, .github/skills/ui-aesthetics and .opencode/skills/ui-aesthetics in your project.

What does UI Aesthetics Judgment need to run?

SKILL.md names no scripts, command-line tools or credentials: UI Aesthetics Judgment is instructions for the agent only.

Does UI Aesthetics Judgment access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is UI Aesthetics Judgment safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does UI Aesthetics Judgment use?

No licence was found for UI Aesthetics Judgment or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does UI Aesthetics Judgment use?

About 3.2k tokens (SKILL.md is roughly 13k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 19k tokens, read only when the agent opens those files.

What are the alternatives to UI Aesthetics Judgment?

Skills that share tags, products or a category with UI Aesthetics Judgment: UI Design Review (jayminwest/warren, 481 stars), Frontend Design (YYH211/Claude-meta-skill, 282 stars), Frontend Design (JetBrains/skills, 366 stars) and Interface Design for Dashboards and Apps (holaboss-ai/holaOS, 11k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains UI Aesthetics Judgment?

kasonye (a GitHub user) maintains it in kasonye/ui-aesthetics-skill, which has 383 GitHub stars. The repository was last updated on April 14, 2026.

Source: kasonye/ui-aesthetics-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.