Nano Banana Pro
Designnano-banana-proNano Banana Pro is an Agent Skill for design published in the opensquilla/opensquilla repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Generate or edit a single image via OpenRouter (google/gemini-3.1-flash-image-preview by default). Accepts a text prompt and optional --input-image for image-to-image editing. Trigger when the user asks for an AI image, illustration, concept art, product render, or wants to modify an existing image.
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Inspect the Agent Skill at https://github.com/opensquilla/opensquilla/blob/HEAD/src/opensquilla/skills/bundled/nano-banana-pro/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/nano-banana-pro, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
nano-banana-pro — single-image generator via OpenRouter
Generates one PNG from a text prompt (optionally seeded with an input
image for editing). Used by meta-short-drama for per-shot first-frame
generation, but standalone for any single-image request.
Inputs (with:)
| key | required | default | notes |
|---|---|---|---|
prompt | yes | — | Plain English prompt. Append --ar 9:16 etc. as text. |
filename | yes | — | Output path. Relative resolves against process cwd. |
aspect_ratio | no | 1:1 | One of 1:1, 3:2, 2:3, 4:3, 3:4, 16:9, 9:16. |
image_size | no | 1K | 1K, 2K, 4K. Higher = slower + costlier. |
model | no | google/gemini-3.1-flash-image-preview | Any OpenRouter image-capable model. |
max_retries | no | 0 | Extra retries on the primary model before moving on to fallback_model. |
fallback_model | no | "" | Tried ONCE after the primary exhausts retries. Empty disables it. Common pick: google/gemini-3-pro-image-preview. |
placeholder_on_fail | no | no | yes / no. When every model refuses, write a 720x1280 solid-colour PNG with a "Scene placeholder" label so a downstream merge step still has a file in this slot. |
To pass an input image for edit mode, invoke the script directly with
--input-image PATH. The meta-skill engine does not route input images
through with: by convention; for edit workflows call the script.
Auth
API-key resolution order (first hit wins):
--api-keyCLI argument (rarely used; meta-skills don't pass it)OPENROUTER_API_KEYenvironment variable (gateway injects from.env)OPENSQUILLA_LLM_API_KEYenvironment variable, only when the effective OpenSquilla LLM provider resolves toopenrouter.llm.api_keyorllm.api_key_envfrom the selected OpenSquilla TOML config file. Config discovery matchesGatewayConfig.load: explicitOPENSQUILLA_GATEWAY_CONFIG_PATHfirst; otherwise./opensquilla.toml, thendefault_opensquilla_home()/config.toml.OPENSQUILLA_STATE_DIRchangesdefault_opensquilla_home(), so a state-dir profile does not fall through to~/.opensquilla. Config-file credentials are consumed only when the selected config'sllm.providerisopenrouteror omitted.
No Google Gemini key needed — OpenRouter routes the request to the Gemini image model on the user's behalf.
Output
Prints the absolute path of the saved PNG on stdout. Non-zero exit on any error; stderr carries the diagnostic.
Cost / latency
- 1K ~ 4-8s
- 2K ~ 8-15s
- 4K ~ 20-40s
- Use 1K for draft, 4K only when the prompt is locked.
Common failures
no OpenRouter API key found→ setOPENROUTER_API_KEY, pass--api-key, or configure[llm] provider = "openrouter"withapi_key/api_key_envin the selected OpenSquilla config.OpenRouter returned no image→ the model rejected the prompt (content moderation or unsupported request). Rewrite prompt; check IP-safety rules inai-video-script.OpenRouter HTTP 402 / 429→ out of credits / rate-limited.