# gemini-image

A skill that runs images through Gemini: pulls text out of screenshots, reads code off a picture, explains diagrams and error messages.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 1200 installs · ★ 26
- Author: johnlindquist
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/johnlindquist/claude/tree/HEAD/skills/gemini-image/SKILL.md
- Updated: 2025-12-19
- HTML: https://affpapa.org/en/nevibecode/skills/gemini-image

## What it does

The skill hands your agent ready-made prompts for Gemini Pro vision work. A call like `gemini -m pro -f image.png "..."` describes a picture, extracts text from a screenshot, reads code, breaks down a UI, explains a diagram, or compares two images side by side. PNG, JPEG, GIF and WebP all work, along with photos, charts and interface mockups.

Inside are prompts tuned to specific jobs: OCR that keeps the layout, code extraction with indentation, error-message triage, design feedback, pulling values out of a chart. There are workflow recipes too. Capture a screen with `screencapture -i /tmp/bug.png` and turn it straight into a bug report, or generate a React component with Tailwind CSS from a mockup.

Two things have to be in place first: `pip install google-generativeai` and a key in `GEMINI_API_KEY`. No key, no request. Treat extracted text with suspicion — the skill itself warns that OCR gets things wrong, and blurry or cropped images make the answer worse. Sharper image, narrower question, better result.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add johnlindquist/claude --skill gemini-image -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/gemini-image/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/gemini-image/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add johnlindquist/claude --skill gemini-image -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/gemini-image/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add johnlindquist/claude --skill gemini-image -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/gemini-image/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install johnlindquist/claude gemini-image
```

2. **Manually: put the files in place**
- File: `.github/skills/gemini-image/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add johnlindquist/claude --skill gemini-image -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/johnlindquist/claude --path skills/gemini-image
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/gemini-image/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add johnlindquist/claude --skill gemini-image -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/johnlindquist/claude/tree/HEAD/skills/gemini-image/SKILL.md

## When to use it
- pull text out of a screenshot while keeping the layout
- read code off an image and return it indented
- triage an error message captured in a screenshot
- compare before and after images of a UI change
- turn a screen capture into a bug report

## Example prompts
- Extract all the visible text from this screenshot
- What is this error and how do I fix it?
- Generate a React component with Tailwind CSS from this mockup

## Similar
- [vision-analysis](https://affpapa.org/en/nevibecode/skills/vision-analysis.md) — skill · 2700 installs
- [modlens](https://affpapa.org/en/nevibecode/skills/modlens.md) — skill · 902 installs
- [baoyu-danger-gemini-web](https://affpapa.org/en/nevibecode/skills/baoyu-danger-gemini-web.md) — skill · 27900 installs
- [scenario-gemini-image](https://affpapa.org/en/nevibecode/skills/scenario-gemini-image.md) — skill · 392 installs
- [vision](https://affpapa.org/en/nevibecode/skills/vision.md) — skill · 13400 installs
- [qianwen-vision](https://affpapa.org/en/nevibecode/skills/qianwen-vision.md) — skill · 5700 installs

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md