What is generate-image-gemini?

A skill that uses Google's Gemini or Imagen 3 services to create AI-generated images from text descriptions. It rewrites prompts and selects common output defaults before calling the image-generation tool.

Creating pictures, artwork, icons, avatars, logos, landscapes, banners, portraits, and other images described by the user.

It gives an agent a defined process for turning a user's idea into an image request without requiring the user to write a detailed prompt.

generate-image-gemini — Skill for Claude Code by tadeukaiba

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add tadeukaiba/mcp-media-toolkit --skill generate-image-gemini

Clone the repo

git clone --depth 1 https://github.com/tadeukaiba/mcp-media-toolkit

Made for: Claude Code.

Or install mcp-media-toolkit, the plugin that ships this one along with the rest of its 3 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/tadeukaiba/mcp-media-toolkit/generate-image-gemini/github.svg)](https://agentmods.dev/skills/tadeukaiba/mcp-media-toolkit/generate-image-gemini)

Your own site

<a href="https://agentmods.dev/skills/tadeukaiba/mcp-media-toolkit/generate-image-gemini"><img src="https://agentmods.dev/badge/skills/tadeukaiba/mcp-media-toolkit/generate-image-gemini/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/tadeukaiba/mcp-media-toolkit/generate-image-gemini"><img src="https://agentmods.dev/badge/skills/tadeukaiba/mcp-media-toolkit/generate-image-gemini.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 109 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,356 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00109	$0.01356
Opus 5	$0.00055	$0.00678
Sonnet 5	$0.00022	$0.00271
Haiku 4.5	$0.00011	$0.00136

Measured 10d ago against content hash 6ed01cea51db, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

generate-image-gemini scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/generate-image-gemini/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Generate Image with Gemini

Generate an AI image using the generate_image_gemini MCP tool. Before calling the tool, rewrite the user's prompt into a detailed, well-structured image description so the model produces a high-quality result.

Workflow

Understand what the user wants. If the request is vague ("make me an image"), ask one focused question to capture the subject. Otherwise proceed.
Optimize the prompt. Rewrite the user's description into a detailed image prompt following the structure below. Do this silently — don't show the user a wall of technical prompt engineering unless they ask.
Choose sensible defaults. Unless the user specified otherwise:
- quality: fast (Nano Banana, ~1K output) — cheap and quick, good enough for most requests. Only move up when the user signals they care about fidelity.
- aspect_ratio: 1:1 for icons/avatars/logos, 16:9 for landscapes/banners, 9:16 for portraits/phone wallpapers, 4:3 for photos
- format: png (lossless, safest default)
Call the tool. Use mcp__mcp-media-toolkit__generate_image_gemini with the optimized prompt. Only bump quality above fast when the user explicitly asks for higher fidelity, mentions production use, or asks for photorealistic/print-quality work — higher presets are much slower.
Show the result. The tool returns a thumbnail preview and the local file path. Report both to the user, plus confirm what aspect ratio and quality preset were used.
Offer upload. After generation, ask if they want a public URL. If yes, call mcp__mcp-media-toolkit__upload_image_s3 with the returned file path. Skip this step if the user already said they only want the local file.

Prompt Optimization

Short casual prompts produce generic output. A good image prompt describes subject, context, and style with enough specificity that two people reading it would imagine roughly the same image.

Checklist

Before sending a prompt to the model, make sure it covers these dimensions (skip any that don't apply — e.g. a logo doesn't need lighting):

Read the full file on GitHub · 75 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

10d ago First seen · 75 lines · 109 tokens per session scan A 6ed01cea51db

Subscribe to this mod's changes

generate-image-gemini is a skill published in the GitHub repository tadeukaiba/mcp-media-toolkit (0 stars, last pushed 5mo ago), licensed MIT. It adds 109 tokens to every session and 1,356 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude Code Creative and media agent-skills ai-tools cloudflare-r2 codex cursor

wave-ask

Propose a WAVE media pipeline (captions/clips/dub/realtime/identity) for a goal stated in plain language. Never executes — returns a proposal to call yourself.

wave-av/mcp-server · 41 tokens

mosaic-scene

Max — Mosaic Bridge scene builder. Use for complete scene construction workflows — objects, materials, lighting, particles, physics, audio, and UI. Use when the user says "build a scene", "create a level", "add rain", "set up physics", or describes building any environment.

MosaicXR-AI/mosaic-bridge · 64 tokens

vfx-text-cursor

Cursor light trail, chromatic rays, and directional flares for word-by-word quote reveals in video intros.

wolfenazz/YzPzCode · 28 tokens

deapi

AI media generation via deAPI. Transcribe YouTube/audio/video, generate images from text, text-to-speech, OCR, remove backgrounds, upscale images, create videos, generate embeddings. 10-20x cheaper than OpenAI/Replicate.

deapi-ai/claude-code-skills · 54 tokens

youtube-shorts-generator

Generate viral 9:16 YouTube Shorts (or TikTok/Reels clips) from a long-form YouTube URL or local video. Triggers on requests like "make shorts from this video", "extract viral clips from this YouTube link", "auto-clip this podcast", "find the best moments and crop vertical". Pipeline downloads the source, transcribes…

Anil-matcha/awesome-generative-ai-apps · 135 tokens

omh-image-cards

This is a Hermes-native img-summary workflow skill.

rlaope/oh-my-hermes · 66 tokens