sova: Skill for Claude Code

.agents/skills/design-taste/SKILL.md

design-taste is a skill for Claude Code, Codex from xsovad06/sova. It costs 34 tokens per session (1,046 once invoked), scanned A, original, Apache-2.0.

A checklist for reviewing the visual quality of user interfaces. It covers layout, text, spacing, colour contrast, responsive behaviour, and consistency with a project's design system.

In plain words
What is it for?
Use it when reviewing or validating UI changes, adapting general design rules to a project's documented components, or checking visual quality across screen sizes.
Why use it?
It provides a common way to spot unclear or inconsistent interface changes when no more specific project guidance applies.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is xsovad06/sova's own configuration. It tells Claude Code and Codex how to work on sova itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything sova configures →

Reuse

Borrowing it

Nothing to install: this file belongs to xsovad06/sova. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/xsovad06/sova/main/.agents/skills/design-taste/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/xsovad06/sova

Made for: Claude Code, Codex.

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-taste

README.md
[![agentmods](https://agentmods.dev/badge/skills/xsovad06/sova/design-taste/github.svg)](https://agentmods.dev/skills/xsovad06/sova/design-taste)
Your own site
<a href="https://agentmods.dev/skills/xsovad06/sova/design-taste"><img src="https://agentmods.dev/badge/skills/xsovad06/sova/design-taste/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-taste

Your own site · 80×15
<a href="https://agentmods.dev/skills/xsovad06/sova/design-taste"><img src="https://agentmods.dev/badge/skills/xsovad06/sova/design-taste.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,046 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 $0.00034 $0.01046
Opus 5.5 $0.00014 $0.00418
Sonnet 5.5 $0.00007 $0.00209
Haiku 4.5 $0.00003 $0.00105

Measured 21d ago against content hash 38e431413137, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

design-taste 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 21d 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.

.agents/skills/design-taste/SKILL.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design Taste

Use this checklist when creating, modifying, or reviewing UI elements on a project whose own design system isn't already covered by a more specific skill. It is generic by design: before applying it, read the project's own design system documentation (for example docs/design-system.md or a style guide), identify its component library (Bootstrap, Material, DaisyUI, custom, etc.) and how colors are defined, named, and applied, then map each category below onto that project's actual tokens, components, and conventions rather than applying the generic names literally.

Before You Start

  1. Read the project's design system documentation.
  2. Identify the component library in use.
  3. Understand how the color system is defined, named, and applied.
  4. Check existing components before building anything new.

Areas to Review

Colors

  • Use only colors from the project's defined palette
  • Use CSS variables / tokens, not hardcoded values
  • Test in both light and dark modes, if applicable
  • Avoid arbitrary color choices; ask "why this shade?"
  • No semantic color abuse (red/green for non-semantic data)

Buttons

  • Follow the project's button variants (primary, secondary, tertiary, etc.)
  • Clear, action-oriented labels
  • Don't create new button variants without a design review
  • Hover/active/disabled states are visible
  • One primary CTA per form or section, when applicable

Icons

  • Check the existing icon library before creating new icons
  • Consistent sizing for similar use cases
  • Use the component system if available; don't inline raw SVGs
  • Decorative icons are hidden from screen readers
  • Action icons are clearly labeled

Typography

  • Follow the project's type scale (headings, body, small, etc.)
  • Consistent font weights for hierarchy
  • Adequate line height for readability
  • Responsive sizing on mobile
  • Monetary/data values use appropriate styling

Forms

  • All inputs have associated labels
  • Focus states are clearly visible and accessible
  • Error states are clearly indicated
  • Consistent spacing and padding
  • Validation messages are clear and helpful

Read the full file on GitHub · 114 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 21d ago Changed · +99 lines 38e431413137
  2. 23d ago First seen · 15 lines · 34 tokens per session scan A b1f95c546584

Subscribe to this mod's changes

design-taste is a skill published in the GitHub repository xsovad06/sova (2 stars, last pushed today), licensed Apache-2.0. It adds 34 tokens to every session and 1,046 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-07.

Related

Other skills, from other repositories

beautify-with-pingfusi

Beautify or redesign an existing website through iterative pingfusi review rounds with a real human reviewer. Use when asked to "beautify this website," "make this page look professional," "polish this UI/design," "improve the visual design," or finish an AI-built page when there is no reference site to match. Do not…

alex-durango/pingfusi · 95 tokens

frontend-design

Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.

vraj-ai/skills · 40 tokens

frontend-design

Produce intentional, responsive, accessible UI work and perform visual QA instead of generic component assembly.

Hmbown/CodeWhale · 21 tokens

ambience-skill

Layer A ambience-and-typographic-motion reference anchored to the react-bits catalog (reactbits.dev). Stacks on any style skill whenever work adds a hero atmosphere, an animated or shader background, a typographic reveal (split, blur, shimmer, typewriter, count-up, marquee), scroll storytelling, or card surface…

code-yeongyu/lazycodex · 132 tokens

interaction-skill

Layer A interaction-mechanics reference anchored to the beui.dev catalog. Stacks on any style skill whenever work adds or changes motion or interaction — micro-interactions, animated components, transitions, gestures, hover/press/state feedback, loading/success/error morphs, 'make it feel alive'. Mandates reading the…

code-yeongyu/lazycodex · 104 tokens

designlang-tokens

Use when styling UI for cal.com — references the extracted design system tokens instead of inventing colors, spacing, or typography.

Manavarya09/design-extract · 30 tokens