gradio: Skill for Claude Code

.agents/skills/gradio-themes/SKILL.md

gradio-themes is a skill for Claude Code, Codex from gradio-app/gradio. It costs 39 tokens per session (3,558 once invoked), scanned A, original, Apache-2.0.

A tool for creating and customising Gradio themes, which control the appearance of Python web apps. Themes can set colours, fonts, spacing, shadows, and light or dark mode.

In plain words
What is it for?
Use it to build or edit the visual style of a Gradio app, including typography, colour palettes, spacing, shadows, contrast, and dark-mode settings.
Why use it?
It gives the app’s visual rules one place to manage and helps keep text readable against its backgrounds. It also makes dark mode an intentional design rather than a simple colour inversion.

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 gradio-app/gradio's own configuration. It tells Claude Code and Codex how to work on gradio 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 gradio configures →

About the project

Gradio is a Python package for building web interfaces around machine learning models, APIs, or ordinary Python functions. It is used by developers and data scientists to create and share interactive demos without writing frontend code.

gradio-app/gradio · 43,507 stars · on GitHub · gradio.app

Reuse

Borrowing it

Nothing to install: this file belongs to gradio-app/gradio. 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/gradio-app/gradio/main/.agents/skills/gradio-themes/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/gradio-app/gradio

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 gradio-themes

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/gradio-app/gradio/gradio-themes"><img src="https://agentmods.dev/badge/skills/gradio-app/gradio/gradio-themes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,558 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. Third-party audits
  • Snyk pass 7 Sept 2026
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00039 $0.03558
Opus 5 $0.00019 $0.01779
Sonnet 5 $0.00008 $0.00712
Haiku 4.5 $0.00004 $0.00356

Measured 11d ago against content hash b6d63cc3fbc0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

gradio-themes 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.

.agents/skills/gradio-themes/SKILL.md · 266 lines

How it starts

The opening of the file, as written. The whole thing — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gradio Theme Building

You are an expert at building Gradio themes. Themes control the entire visual identity of a Gradio app — colours, typography, spacing, shadows, and dark mode — through Python classes that compile to CSS custom properties.

Core Principles

  1. Text contrast is non-negotiable. Every text element must be readable against its actual background — body text, label text on coloured label fills, button text on button fills, placeholder text, selected checkbox text, error text, link text. A beautiful theme that can't be read is useless. Audit every text/background pair before shipping.

  2. Dark mode is independently designed. Never auto-invert light values. Every _dark variable should be intentionally chosen for contrast and readability on dark backgrounds. Specifically:

    • Reduce font weight slightly on dark (350 instead of 400) — light text on dark reads heavier
    • Desaturate accents — high chroma at high lightness looks garish
    • Use lighter surfaces for elevation, not heavier shadows
    • Never use pure black #000 — use #0a0a14-ish dark with a subtle hue cast
  3. Commit to an aesthetic direction. Bold maximalism and refined minimalism both work — what fails is half-commitment. Pick one tone (editorial, brutal, glass, retro, organic, playful, industrial...) and execute every variable in service of it.

  4. Use variable references (*name) for consistency. When one value should track another, reference it. This keeps themes maintainable and lets users customise constructor params (hues, sizes) and have changes cascade.

  5. Test both modes. Always verify light AND dark for body, blocks, inputs, buttons, labels, checkboxes, tables, focus states, hover states, selected states.

Aesthetic Quality

Technical correctness isn't enough. A theme can have every variable set perfectly and still look generic. Apply these checks:

The "AI Slop" Test

If you showed this theme to someone and said "AI made this," would they immediately believe you? If yes, that's the problem. A distinctive theme makes someone ask "how was this made?" not "which AI made this?"

Read the full file on GitHub · 266 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 · 266 lines · 39 tokens per session scan A b6d63cc3fbc0

Subscribe to this mod's changes

gradio-themes is a skill published in the GitHub repository gradio-app/gradio (43,507 stars, last pushed today), licensed Apache-2.0. It adds 39 tokens to every session and 3,558 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

popular-web-designs

54 real design systems (Stripe, Linear, Vercel) as HTML/CSS.

NousResearch/hermes-agent · 23 tokens

ui-web

Web UI - glassmorphism, Tailwind, dark mode, accessibility.

alinaqi/maggy · 17 tokens

ui-components

UI component library patterns for shadcn/ui and Radix Primitives. Use when building accessible component libraries, customizing shadcn components, using Radix unstyled primitives, or creating design system foundations.

yonatangross/orchestkit · 44 tokens

component-search

Search 21st.dev component registry for production-ready React components. Finds components by natural language description, filters by framework and style system, returns ranked results with install instructions. Use when looking for UI components, finding alternatives to existing components, or sourcing design system…

yonatangross/orchestkit · 57 tokens

quill-code

Edit the @posthog/quill design system locally and consume the change in products/desktop before it is published to npm. Use when changing quill components/primitives/tokens, when a quill change must be tested inside the Code app, or when the user mentions quill, the design system, the .local-quill tarball, or the…

PostHog/posthog · 84 tokens

ui-design

Unify product UI design, frontend implementation, and verification. Use when asked to design, redesign, build, or fix a web, desktop, or mobile interface; a page, dashboard, form, component, design system, responsive layout, accessibility, interface animation, or editable hero/banner/infographic within a product…

AnastasiyaW/codex-claude-code-config · 97 tokens