Individual skill

image-lab

Turn one image prompt into several strong alternatives at once — the Model Advisor spreads them across the 2-3 image models that best fit the brief, shows the estimated total before any spend, generates them in parallel, then builds a shareable gallery you pick the winner from. Use when someone wants several options of one image prompt, wants to try more than one image model without pricing anxiety, wants a cost estimate before generating an image, or wants to compare specific models on a brief. Triggers include "generate that with Image Lab", "8 options of this with Image Lab", "run Image Lab on this prompt", "with Image Lab, compare Nano Banana Pro and GPT Image 2". It needs to be named — a bare "generate an image" belongs to native image generation, not here. This skill only turns one finished prompt into several alternatives. For controlled variations, creative directions, a reference photo, a workbook of options, or when the user says "Image Lab 2", use the image-lab-2 skill instead.

examples/community/image-lab/SKILL.md

Read pinned source

Source commit d9efb25f4a1f7941edfd42961769e0836fb0565e

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
No
Repository scan complete
No
Skill scan complete
No
Observed behavior
Not checked yet
Last checked
Nov 5, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
16
Repository last updated
Nov 5, 2026
License
Apache-2.0

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# Image Lab

**One prompt. Several strong possibilities. Pick the image you want.**
See the price. Approve once. Generate in parallel.

Image Lab helps you **pick an image, not pick a model**. It does not write
prompts and is not tied to any prompt source — it takes a finished prompt, and
its Model Advisor spreads your requested number of alternatives across the
models that best fit the brief. Pair it with `ai-image-prompts-skill`, any other
prompt skill, or use your own prompt.

## The five user-facing steps

```
Back to top