Install
$ agentstack add skill-marchatton-agent-skills-nano-banana-pro ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Nano Banana Pro Image Generation & Editing
Quick Start
Generate:
uv run ~/.codex/skills/nano-banana-pro/scripts/generate_image.py --prompt "A serene Japanese garden" --filename "2025-11-23-14-23-05-japanese-garden.png" --resolution 1K
Edit:
uv run ~/.codex/skills/nano-banana-pro/scripts/generate_image.py --prompt "make the sky dramatic" --filename "2025-11-23-14-25-30-dramatic-sky.png" --input-image "original.png" --resolution 2K
Compose:
uv run ~/.codex/skills/nano-banana-pro/scripts/compose_images.py "Create a group photo" group.png person1.png person2.png
Multi-turn chat:
uv run ~/.codex/skills/nano-banana-pro/scripts/multi_turn_chat.py --model gemini-3-pro-image-preview --output-dir .
Scripts
generate_image.py: text-to-image + edit via--input-image, resolution 1K/2K/4K, optional--aspect, auto-detect resolution on edit.edit_image.py: explicit edit CLI (input, instruction, output).compose_images.py: combine up to 14 reference images.multi_turn_chat.py: interactive refine session (/save,/load,/clear,/quit).gemini_images.py: Python helper class.
Model
- Default:
gemini-3-pro-image-preview. - Only use other models if user asks.
Resolution + Aspect
- Resolution:
1Kdefault,2K,4K. - Aspect ratios (where supported):
1:1,2:3,3:2,3:4,4:3,4:5,5:4,9:16,16:9,21:9. - Map words: "1080/low/1K"->1K, "2K/2048/medium"->2K, "4K/high/ultra"->4K.
Workflow
- Draft 1K, iterate small prompt diffs, final 4K.
- For edits, keep same
--input-imageuntil final.
API Key
GEMINI_API_KEYrequired.generate_image.pyalso supports--api-key.
Filenames
- Pattern:
yyyy-mm-dd-hh-mm-ss-name.png. - Lowercase, hyphenated, 1-5 words.
Output
- Run from user cwd so files save there.
generate_image.pyconverts output to PNG.- Do not open/read images; report saved path.
Preflight
command -v uvtest -n "$GEMINI_API_KEY"- If editing:
test -f "path/to/input.png"
Common Failures
- No API key.
- Input image missing/unreadable.
- Quota/permission/403 errors.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: marchatton
- Source: marchatton/agent-skills
- License: MIT
- Homepage: https://www.marchatton.com
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.