nano-banana-pro (intellectronica/agent-skills)
Leading#1 in Skillsmedium confidence
The most-cited image Agent Skill — generate/edit images up to 4K with Nano Banana Pro (Gemini 3 Pro Image), strong on legible in-image text.Our read
Why it ranks #1
The skill is repeatedly indexed by the cited skill directories and benefits from adoption of the broader intellectronica/agent-skills collection, but lacks a clean standalone usage count.Here is the catch
requires a Gemini API key and external billing
inherits model rate limits and regional availability
adoption signal is mostly from the parent collection
Does this well
simple agent workflow for generation and editing
strong in-image text and instruction following
portable skill with inspectable instructions
Pricing
Checked by hand on 2026-07-23. Prices in this category change often — if this looks wrong, it probably is.
Key features
Prompt-based image generationImage editing with referencesUp-to-4K output workflowGemini API setup and file handling
Quick facts
More in this area
The rest of the Skills column.- 2ccskill-nanobanana (feedtailor)Claude Code image-generation skill on the Gemini 3 Pro Image (Nano Banana Pro) model. Clean, well-documented but single-author.
- 3wuyoscar/GPT-Image2-SkillA CLI and agent skill for OpenAI's gpt-image-2 generation and edit endpoints, shipped with a categorised gallery of worked example prompts.
- 4guinacio/claude-image-genClaude Code skill plus MCP server routing prompts to Gemini or gpt-image-2, saving files locally with up to five reference images.
- 5shinpr/mcp-imageMCP server for Gemini, GPT Image and Seedream that rewrites short requests into detailed photographic prompts and offers speed-versus-quality presets.
- 6hassancs91/claude-image-generation
- 7wanshuiyin/ARIS-Movie-DirectorAgent pipeline that turns a rough story into a storyboarded image sequence, with separate models blind-reviewing each frame before it ships.