← Back to Skills Marketplace
yummysource

Yummy Gen Image

by yummysource · GitHub ↗ · v1.1.0 · MIT-0
cross-platform ✓ Security Clean
143
Downloads
1
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install yummy-gen-image
Description
Use when the user wants to generate or edit raster images with Gemini through yummycli, including prompt-only generation, single-image editing, and multi-ima...
README (SKILL.md)

Generate Image

Create or edit images with yummycli gemini nanobanana.

When to Use

Load this skill when the user asks to generate, create, or edit an image using AI — including text-to-image generation, style transfer, image editing with a reference photo, or multi-image compositing.

Prerequisite: Apply the yummy-shared skill first.

This skill uses one command for all Gemini image flows:

  • Prompt-only generation
  • Single-image editing
  • Multi-image reference editing

Command Contract

Two equivalent entry points are available:

Entry point When to use
yummycli gemini nanobanana Default — human-friendly, Gemini presets applied
yummycli image generate --provider gemini Scripting / automation — explicit, provider-agnostic form

Both share the same flags and the same Gemini defaults. Prefer gemini nanobanana unless the task explicitly requires the provider-agnostic form.

Basic usage:

yummycli gemini nanobanana --prompt "\x3Cprompt>"

Add one or more reference images when needed:

yummycli gemini nanobanana \
  --prompt "\x3Cprompt>" \
  --input-image ./source-a.png \
  --input-image ./source-b.png

Optional output controls:

--output \x3Cfile>
--model \x3Cmodel>
--aspect-ratio \x3Cratio>
--image-size \x3Csize>

Default values when omitted: --aspect-ratio 16:9, --image-size 1K, --model gemini-3.1-flash-image-preview.

Execution Rules

  • Use prompt-only generation when no reference images are provided.
  • Use one --input-image flag per local image file.
  • Preserve the user-provided order of reference images.
  • Prefer the default model unless the user asks for a specific model.

Model Selection

Use the following model mapping rules:

  • If the user explicitly says gemini pro, pro model, or simply pro in the model-selection context, use:
--model gemini-3-pro-image-preview
  • If the user explicitly says gemini flash, flash model, or simply flash in the model-selection context, use:
--model gemini-3.1-flash-image-preview
  • If the user does not explicitly request a model, omit --model and let yummycli use its default model.

Do not switch models implicitly from vague quality words alone. Only apply the pro or flash mapping when the user's wording clearly refers to model choice.

Model Compatibility

Aspect ratio

Model Supported values
gemini-3.1-flash-image-preview 1:1 1:4 1:8 2:3 3:2 3:4 4:1 4:3 4:5 5:4 8:1 9:16 16:9 21:9
gemini-3-pro-image-preview 1:1 2:3 3:2 3:4 4:3 4:5 5:4 9:16 16:9 21:9
(default / other) 1:1 3:4 4:3 9:16 16:9

1:4, 1:8, 4:1, 8:1 are flash-only. Do not use them with the pro model.

Image size

Model Supported values
gemini-3.1-flash-image-preview 512 0.5K 1K 2K 4K
gemini-3-pro-image-preview 1K 2K 4K
(default / other) 1K 2K 4K

512 and 0.5K are flash-only. Do not use them with the pro model.

Intent to Parameters

Translate clear user intent into CLI flags when the mapping is obvious.

Aspect-ratio guidance:

  • Use --aspect-ratio 9:16 for requests such as phone wallpaper, vertical poster, story format, or other clearly vertical mobile outputs.
  • Use --aspect-ratio 16:9 for requests such as desktop wallpaper, presentation cover, horizontal banner, or other clearly widescreen outputs.
  • Use --aspect-ratio 1:1 for square social images, avatars, or other explicitly square outputs.
  • If the user already provides a specific ratio, pass it through directly.
  • If the output shape is unclear, omit --aspect-ratio and let yummycli use its default.

Image-size guidance:

  • Use --image-size 4K when the user explicitly asks for 4K or a clearly print-grade / high-resolution deliverable.
  • Use --image-size 2K when the user explicitly asks for 2K or a medium-resolution deliverable.
  • Use --image-size 1K when the user explicitly asks for 1K or a lightweight preview-sized result.
  • Use --image-size 512 or --image-size 0.5K only when the user explicitly asks for a minimal-size output and the flash model is in use.
  • If the user does not explicitly request output size, omit --image-size and let yummycli use its default (1K).

Do not guess --image-size from general quality adjectives alone.

Output path guidance:

  • If --output is omitted, yummycli generates a default filename in the current working directory. Do not invent your own output filename unless the user explicitly provides one.

Examples

Prompt-only generation:

yummycli gemini nanobanana \
  --prompt "A single ripe banana on a white plate, studio lighting, realistic photo"

Single-image edit:

yummycli gemini nanobanana \
  --prompt "Turn this into a watercolor illustration" \
  --input-image ./source.png

Multi-image reference edit:

yummycli gemini nanobanana \
  --prompt "Blend these references into one polished poster illustration" \
  --input-image ./subject.png \
  --input-image ./background.jpg
Usage Guidance
This skill appears to do what it says: call yummycli to generate/edit images via Gemini using your GEMINI_API_KEY. Before installing: (1) verify the npm package @yummysource/yummycli is from a trusted publisher and inspect its README/repo if possible; (2) check the related yummy-shared skill for any additional environment variables or behaviors; (3) confirm the GEMINI_API_KEY you provide has limited scope and can be rotated/revoked; (4) be aware that running the CLI will upload any referenced local images to the provider—do not pass sensitive images. If you are uncomfortable, install yummycli yourself and run it manually rather than granting the skill automatic install rights.
Capability Analysis
Type: OpenClaw Skill Name: yummy-gen-image Version: 1.1.0 The skill bundle provides instructions for an AI agent to interface with a CLI tool named `yummycli` (installed via `@yummysource/yummycli`) for image generation and editing using Gemini models. The documentation in `SKILL.md` defines standard command-line parameters, model compatibility rules, and usage examples without any evidence of malicious intent, data exfiltration, or unauthorized execution.
Capability Tags
requires-sensitive-credentials
Capability Assessment
Purpose & Capability
Name/description match the declared binaries and primary credential: yummycli + GEMINI_API_KEY are appropriate for a Gemini image-generation CLI wrapper.
Instruction Scope
SKILL.md only instructs the agent to run yummycli with user-provided prompts and local image paths. It does not ask for unrelated system files, broad environment variables, or unexpected network endpoints beyond the Gemini provider implied by GEMINI_API_KEY.
Install Mechanism
SKILL.md includes an npm install spec (package: "@yummysource/yummycli") which is a moderate-risk, registry-hosted install. The registry metadata elsewhere said "No install spec", creating an inconsistency. Installing from npm is expected for this kind of CLI, but you should verify the package's publisher and trustworthiness before allowing automatic installation.
Credentials
Only GEMINI_API_KEY is declared as the primary credential, which is proportionate for Gemini image generation. However the skill references a related skill (yummy-shared) which may introduce additional requirements—check that skill for extra env vars or permissions.
Persistence & Privilege
always is false and the skill does not request elevated or persistent privileges or alter other skills' configurations. Autonomous invocation is allowed by default (not flagged alone).
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install yummy-gen-image
  3. After installation, invoke the skill by name or use /yummy-gen-image
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.1.0
- Version bumped to 1.1.0 with no user-visible changes. - No updates to files or functionality detected.
v1.0.0
- Initial release of yummy-gen-image skill. - Enables AI-driven image generation and editing with Gemini via yummycli, supporting prompt-only and reference-image workflows. - Unified CLI entry point for all flows: prompt-only, single-image editing, multi-image compositing. - Follows user intent for model, aspect ratio, image size, and output path using clear mapping rules. - Includes detailed contract for safe parameter selection and model compatibility.
Metadata
Slug yummy-gen-image
Version 1.1.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 2
Frequently Asked Questions

What is Yummy Gen Image?

Use when the user wants to generate or edit raster images with Gemini through yummycli, including prompt-only generation, single-image editing, and multi-ima... It is an AI Agent Skill for Claude Code / OpenClaw, with 143 downloads so far.

How do I install Yummy Gen Image?

Run "/install yummy-gen-image" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Yummy Gen Image free?

Yes, Yummy Gen Image is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Yummy Gen Image support?

Yummy Gen Image is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Yummy Gen Image?

It is built and maintained by yummysource (@yummysource); the current version is v1.1.0.

💬 Comments