nano-banana-pro · hoodini — Claude Code skill: Gemini 3 Pro image generation
nano-banana-pro — a skill that hands your agent working recipes for gemini-3-pro-image-preview: posters, infographics, product shots.
no license ★ 301 updated 2026-10-23
npx skills add hoodini/ai-agents-skills --skill nano-banana-pro -a claude-codeWhat nano-banana-pro does
The skill gives an agent ready-made ways to call Google's Nano Banana Pro, the gemini-3-pro-image-preview model. Inside SKILL.md: a Python sample on google-genai, a cURL request, a TypeScript helper with a Next.js route handler. Chat sessions are covered too, so a follow-up edit lands on the image you already have instead of a fresh generation.
Shape comes from aspect_ratio (1:1, 3:2, 16:9, 9:16, 21:9) and image_size (1K, 2K, 4K). Switch on google_search and an infographic can quote figures from search results. For edits, the reference picture travels as base64 in inline_data; the same route keeps up to five characters recognizable across frames.
You need a Gemini API key from Google AI Studio in an environment variable. Without it the first call fails. The Python path also needs the google-genai package. The skill's own comparison table puts Flash ahead on speed and cost, Pro ahead on quality, and files Flash under previews and high-volume runs.
What it helps with
- render a poster whose title and date read cleanly
- retitle an infographic in another language without redrawing it
- get a 16:9 product shot at 2K
- wire image generation into a Next.js route
- keep one character recognizable across several frames
Example prompts for the agent
- Generate an infographic about photosynthesis at 16:9 and write the PNG to
output.png - Send
character.pngwith the prompt and put this person at a tech conference - Make a poster with the title and date, the text has to be spelled right
How to install nano-banana-pro
1Skills CLI (Vercel)
npx skills add hoodini/ai-agents-skills --skill nano-banana-pro -a claude-code2Manually: put the files in place
~/.claude/skills/nano-banana-pro/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/nano-banana-pro/
1Skills CLI (Vercel)
npx skills add hoodini/ai-agents-skills --skill nano-banana-pro -a codex2Manually: put the files in place
.agents/skills/nano-banana-pro/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add hoodini/ai-agents-skills --skill nano-banana-pro -a cursor2Manually: put the files in place
.cursor/skills/nano-banana-pro/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install hoodini/ai-agents-skills skills/nano-banana-pro2Manually: put the files in place
.github/skills/nano-banana-pro/SKILL.md1Skills CLI (Vercel)
npx skills add hoodini/ai-agents-skills --skill nano-banana-pro -a gemini-cli2Platform CLI
gemini skills install https://github.com/hoodini/ai-agents-skills --path skills/nano-banana-proManually: put the files in place
.devin/skills/nano-banana-pro/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.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 nano-banana-pro
How do I install nano-banana-pro in Claude Code?
Run npx skills add hoodini/ai-agents-skills --skill nano-banana-pro -a claude-code. The skill file lands at ~/.claude/skills/nano-banana-pro/SKILL.md.
What does nano-banana-pro do?
It shows the agent how to call Gemini 3 Pro Image: build the request, get a picture back, then refine it in the same chat.
What do I need before it works?
A Gemini API key from Google AI Studio stored in an environment variable, plus the google-genai package for the Python examples.
Similar skills
All skills for AI and ML →nano-banana-pro by other authors comes first.