Gemini Image Generator
Genererar bilder med Google Gemini från en prompt eller en referensbild
Tested · Didn't pass
Vad den gör
Ett litet Python CLI som anropar Googles gemini-3-pro-image-preview model för att generera en bild från en text prompt, optionally guided by one or more reference images, at 1K, 2K or 4K och saved to a path you choose. Utlöses när du ber Claude att generate, create eller edit an image file rather than describe one. Kräver en Google AI Studio API key och en one-time virtualenv setup.
Testrapport
The 111-line script is honest about what it does — build the request, save the returned image, no telemetry — and it wires up correctly: after the documented venv setup it reached generativelanguage.googleapis.com and came back with a real 400 API_KEY_INVALID, so the plumbing is sound but the actual image is unverifiable without a paid Google AI Studio key. Two rough edges cost it points. Run it with no key and it tells you to `export GOOGLE_API_KEY`, while the code only ever reads GEMINI_API_KEY, so a first-time user follows the error message into a dead end. The README's own install snippet clones a repo name that no longer matches and omits `mkdir -p ~/.claude/skills`, which we confirmed installs nothing at all on a fresh machine.
Testad: 2026-07-30 · Claude Code 2.x (agent harness)
Installation
git clone https://github.com/mkdev-me/agent-skills.git mkdir -p ~/.claude/skills cd agent-skills && cp -r gemini-image-generator ~/.claude/skills/gemini-image-generator
Kommandon och exempelprompter
/gemini-image-generatorGenererar bilder med Google Gemini från en prompt eller en referensbild
Skills triggas av vanliga förfrågningar — inga kommandon att memorera. Efter installationen aktiverar prompter som dessa skillen (på engelska):
Generate a 4K image of a mountain landscape at sunset using GeminiCreate a product shot guided by this reference photo with Gemini's modelMake a PNG illustration for my blog header at 2K and save it to assets/