gemini-visual

gemini-visual is a skill for Claude Code from ckorhonen/claude-skills. It costs 52 tokens per session (4,554 once invoked), scanned A, original, MIT.

A visual development assistant that uses Google's Gemini models to understand images and design instructions. It helps inspect interfaces, compare designs, extract colours, and turn screenshots or briefs into front-end work.

In plain words
What is it for?
Use it for UI reviews, accessibility checks, screenshot-to-code work, responsive design checks, colour extraction, visual debugging, and creating interface graphics.
Why use it?
It helps developers find visual and accessibility problems without relying only on written descriptions. It also reduces the effort needed to translate a screenshot or design idea into code and assets.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the claude-skills plugin — 62 skills, 4 commands, 7 agents shipped together

Good fit Use it for UI reviews, accessibility checks, screenshot-to-code work, responsive design checks, colour extraction, visual debugging, and creating interface graphics.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ckorhonen/claude-skills/gemini-visual
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 ckorhonen/claude-skills --skill gemini-visual
Clone the repo
git clone --depth 1 https://github.com/ckorhonen/claude-skills

Made for: Claude Code.

Or install claude-skills, the plugin that ships this one along with the rest of its 62 skills, 4 commands, 7 agents.

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 gemini-visual

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/ckorhonen/claude-skills/gemini-visual"><img src="https://agentmods.dev/badge/skills/ckorhonen/claude-skills/gemini-visual.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,554 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 $0.00052 $0.04554
Opus 5 $0.00026 $0.02277
Sonnet 5 $0.00010 $0.00911
Haiku 4.5 $0.00005 $0.00455

Measured 11d ago against content hash a05e8a1eed4a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

gemini-visual 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.

The scan reads SKILL.md. This mod also ships 6 executable files (scripts/analyze_ui.py, scripts/compare_designs.py, scripts/design_from_brief.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/gemini-visual/SKILL.md · 565 lines

How it starts

The opening of the file, as written. The whole thing — 565 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gemini Visual - Front-End & Visual Development Assistant

Overview

A comprehensive toolkit leveraging Google Gemini's advanced visual reasoning capabilities for front-end development and design tasks. Gemini provides state-of-the-art multimodal understanding with spatial reasoning, document understanding, and high-resolution image processing.

When to Use

  • UI/UX Analysis: Analyze screenshots for layout issues, visual hierarchy, and design patterns
  • Accessibility Audits: Check contrast ratios, text readability, and WCAG compliance
  • Design Comparison: Compare mockups, before/after screenshots, or different design variations
  • Color Palette Extraction: Extract colors from images with HEX, RGB, and HSL values
  • Screenshot to Code: Generate HTML/CSS from design screenshots
  • UI Asset Generation: Create icons, backgrounds, gradients, and UI graphics
  • Responsive Design Review: Analyze multi-device screenshots for consistency
  • Visual Debugging: Identify rendering issues, broken layouts, or visual bugs
  • Design from Brief: Generate designs, code, and components from text descriptions
  • Interactive Design Sessions: Multi-turn conversations for iterative design refinement

Prerequisites

  • Python 3.9+
  • google-genai package
  • GEMINI_API_KEY environment variable

Installation

pip install google-genai

Getting an API Key

  1. Go to Google AI Studio
  2. Sign in with your Google account
  3. Click "Create API Key"
  4. Copy the key and set it as an environment variable:
export GEMINI_API_KEY="your-api-key"

Add to your shell profile (~/.zshrc or ~/.bashrc) for persistence:

echo 'export GEMINI_API_KEY="your-api-key"' >> ~/.zshrc

Scripts Overview

Script Purpose
analyze_ui.py Analyze UI screenshots for issues, patterns, and suggestions
generate_ui_assets.py Generate icons, backgrounds, and UI graphics
compare_designs.py Compare two designs and highlight differences
extract_colors.py Extract color palettes from images
screenshot_to_code.py Convert screenshots to HTML/CSS code
design_from_brief.py Generate designs and code from text briefs (no image required)

Read the full file on GitHub · 565 lines

Files

What ships with it

6 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. 11d ago First seen · 565 lines · 52 tokens per session scan A a05e8a1eed4a

Subscribe to this mod's changes

gemini-visual is a skill published in the GitHub repository ckorhonen/claude-skills (14 stars, last pushed 2mo ago), licensed MIT. It adds 52 tokens to every session and 4,554 once invoked, about $0.0003 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