roasbeef/nano-banana
skills/nano-banana/SKILL.md
Generate and edit images using Gemini's image generation API (Imagen 3). This skill should be used when creating images, illustrations, diagrams, editing existing images, or iteratively refining visual content through multi-turn conversations.
$ install --global
skillsauthnpx skillsauth add roasbeef/claude-files nano-bananaInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 15, 2026, 5:10 AM141.9s8 files scanned
SKILL.md
- name:
- nano-banana
- description:
- Generate and edit images using Gemini's image generation API (Imagen 3). This skill should be used when creating images, illustrations, diagrams, editing existing images, or iteratively refining visual content through multi-turn conversations.
- allowed-tools:
- Bash(python:*), Read, Write
Nano Banana - Gemini Image Generation
This skill provides comprehensive access to Gemini's image generation capabilities, including text-to-image generation, image editing, multi-turn refinement, batch processing, and high-resolution output.
Prerequisites
- API key set as
GOOGLE_API_KEYorGEMINI_API_KEYenvironment variable - The scripts include a bundled virtual environment (
.venv/) withgoogle-genaipre-installed - Scripts can be called directly:
~/.claude/skills/nano-banana/scripts/generate_image.py
Available Models
| Model | ID | Best For |
|-------|----|----------|
| Flash | gemini-2.5-flash-image | Fast generation, high volume, low latency |
| Pro | gemini-3-pro-image-preview | Professional quality, 4K, advanced reasoning |
Capabilities Overview
| Capability | Script | Description |
|------------|--------|-------------|
| Image Generation | generate_image.py | Create images from text prompts |
| Image Editing | edit_image.py | Modify existing images with instructions |
| Batch Generation | batch_generate.py | Generate multiple images in parallel |
| Multi-turn Editing | chat_session.py | Iterative refinement via conversation |
Quick Start
Generate a Single Image
python scripts/generate_image.py "a sunset over mountains" sunset.png
With options:
python scripts/generate_image.py "modern office" office.png --model pro --aspect 16:9 --size 4K
Edit an Existing Image
python scripts/edit_image.py photo.png "remove the background" result.png
Batch Generation
Create a prompts file (prompts.json):
[
{"prompt": "slide 1: intro graphic", "filename": "slide_01.png", "aspect": "16:9"},
{"prompt": "slide 2: data visualization", "filename": "slide_02.png", "aspect": "16:9"}
]
Generate all:
python scripts/batch_generate.py prompts.json ./output/ --parallel 3
Or use a simple text file (one prompt per line):
python scripts/batch_generate.py prompts.txt ./output/ --aspect 16:9
Multi-turn Editing Session
Start an interactive session:
python scripts/chat_session.py --output-dir ./images/
Resume a previous session:
python scripts/chat_session.py --session-file session.json
Send a single refinement:
python scripts/chat_session.py --session-file session.json --message "make it more vibrant"
Script Reference
generate_image.py
Generate a single image from a text prompt.
Usage: python scripts/generate_image.py "prompt" output.png [options]
Options:
--model, -m Model: flash (default) or pro
--aspect, -a Aspect ratio: 1:1 (default), 16:9, 9:16, 21:9, 4:3, 3:4
--size, -s Resolution (pro only): 1K, 2K, 4K
edit_image.py
Edit an existing image using text instructions.
Usage: python scripts/edit_image.py input.png "instructions" output.png [options]
Options:
--model, -m Model: flash (default) or pro
batch_generate.py
Generate multiple images from a prompts file.
Usage: python scripts/batch_generate.py prompts.json output_dir/ [options]
Options:
--model, -m Model: flash (default) or pro
--aspect, -a Default aspect ratio: 1:1 (default)
--parallel, -p Number of parallel workers: 1 (default)
--json Output results as JSON
chat_session.py
Multi-turn image generation/editing session.
Usage: python scripts/chat_session.py [options]
Options:
--model, -m Model: flash (default) or pro
--session-file, -s Path to session state file (JSON)
--output-dir, -o Directory for output images: . (default)
--initial, -i Initial prompt to start with
--message Send single message (non-interactive)
Best Practices
Prompting Tips
- Be specific: "A red sports car on a mountain road at sunset" works better than "a car".
- Describe style: Include art style, mood, lighting, and camera angle.
- Use negative space: Describe what should NOT be in the image when needed.
Editing Tips
- Target specific elements: "Change only the sky to purple" is better than "make it purple".
- Reference the original: "Keep the composition but change the color scheme".
- Iterative refinement: Use multi-turn sessions for complex edits.
Performance
- Use
flashmodel for quick iterations and high volume. - Use
promodel for final production assets and 4K output. - Use batch generation with
--parallelfor multiple images.
Additional Resources
For detailed API documentation, see references/gemini-api.md. For prompting techniques, see references/prompt-guide.md. For common editing patterns, see references/editing-patterns.md.
Related Skills
roasbeef/review-loop
development
VerifiedTrustedCommunity
Adversarial review→triage→fix loop until a cold verifier signs off. Fans out lens-specific reviewer subagents, verifies every finding against the code (killing false positives), auto-applies confirmed fixes as fixup commits, and repeats until a fresh verifier approves. Prefers a deterministic dynamic workflow when available; falls back to in-instance Task dispatch. Use when the user types /review-loop or asks to adversarially review-and-fix a change set, branch, or commit range until clean.
19SKILL.mdUpdated Jun 9, 2026
roasbeef/agent-ci
development
VerifiedTrustedCommunity
Run GitHub Actions CI locally with Agent CI to validate changes before pushing. Use when testing, running checks, or validating code changes.
19SKILL.mdUpdated Jun 9, 2026
roasbeef/technical-writing
development
VerifiedTrustedCommunity
Clear-writing guide distilled from Steven Pinker's "The Sense of Style." Use when writing or revising prose that must be clear to a reader — documentation, design docs, specs, explanations, essays, emails, reports, RFCs, release notes — or when asked to make writing clearer, tighter, less academic, or less jargon-laden. Activate for "make this clearer", "tighten this", "why is this hard to read", "edit this for clarity", or any prose-quality pass.
19SKILL.mdUpdated Jun 2, 2026
roasbeef/go-debug
development
VerifiedTrustedCommunity
Interactively debug Go programs in a single context using Delve (dlv) driven through tmux. Use when a bug requires runtime inspection — stepping through code, examining variables, walking goroutines, attaching to a live process, or debugging a hanging integration test — rather than just reading the source. Triggers include "step through this", "set a breakpoint", "attach to the running server", "why is this goroutine stuck", "debug this failing test".
19SKILL.mdUpdated May 20, 2026