gemini-image — Claude Code skill: image analysis with Gemini
A skill that runs images through Gemini: pulls text out of screenshots, reads code off a picture, explains diagrams and error messages.
npx skills add johnlindquist/claude --skill gemini-image -a claude-codeWhat gemini-image 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.
What it helps with
- 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 for the agent
- 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
How to install gemini-image
1Skills CLI (Vercel)
npx skills add johnlindquist/claude --skill gemini-image -a claude-code2Manually: put the files in place
~/.claude/skills/gemini-image/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/gemini-image/
1Skills CLI (Vercel)
npx skills add johnlindquist/claude --skill gemini-image -a codex2Manually: put the files in place
.agents/skills/gemini-image/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add johnlindquist/claude --skill gemini-image -a cursor2Manually: put the files in place
.cursor/skills/gemini-image/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install johnlindquist/claude gemini-image2Manually: put the files in place
.github/skills/gemini-image/SKILL.md1Skills CLI (Vercel)
npx skills add johnlindquist/claude --skill gemini-image -a gemini-cli2Platform CLI
gemini skills install https://github.com/johnlindquist/claude --path skills/gemini-imageManually: put the files in place
.devin/skills/gemini-image/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add johnlindquist/claude --skill gemini-image -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about gemini-image
How do I install gemini-image in Claude?
Run npx skills add johnlindquist/claude --skill gemini-image -a claude-code. The skill then lands at ~/.claude/skills/gemini-image/SKILL.md.
What does gemini-image do?
It sends images to Gemini Pro to describe content, extract text and code from screenshots, explain diagrams and errors, and give design feedback.
What do I need before using it?
The google-generativeai package and a key in GEMINI_API_KEY. Without the key the Gemini calls fail.
