From mcp-media-toolkit
Generate AI images using Google Gemini (Nano Banana) or Imagen 3. Use whenever the user asks to "generate an image", "create a picture", "make artwork", "draw something", "I need an image of X", "create a visual", or any request involving AI image generation. Optimizes the user's prompt automatically before calling the generation tool so output quality is high even from short casual descriptions. Does NOT upload — use /image-gemini-s3 if the user also needs a public URL.
How this skill is triggered — by the user, by Claude, or both
Slash command
/mcp-media-toolkit:generate-image-geminiThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
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.
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.
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 photosformat: 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.
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.
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):
Keep the final prompt to 1-3 dense sentences. Don't write paragraphs — the model responds better to information-dense phrasing than to long narratives.
Example 1 — vague request
Example 2 — product shot
Example 3 — abstract / logo
If the user gives a very specific prompt already ("photorealistic portrait of a 40-year-old blacksmith with a leather apron, forge in the background, Rembrandt lighting"), don't add fluff — they know what they want. Your job in that case is just to pass it through and maybe tighten the wording. Only expand prompts that are genuinely underspecified.
gemini-2.5-flash-image) at 1K. Cheap, quick, good enough for most drafts, sketches, and casual requests. Start here unless the user signals otherwise.gemini-3.1-flash-image-preview) at 2K. Better detail, slower. Use when the user cares about quality — "this is for a blog post", "for my landing page", etc.gemini-3-pro-image-preview) at 4K. Maximum fidelity but significantly slower (can take several minutes). Reserve for when the user explicitly asks for photorealistic output, print-quality assets, or mentions maximum quality. Warn them about the wait.If the tool returns an error:
GEMINI_API_KEY, or quota exhaustion. Tell the user to check https://aistudio.google.com/apikey.output_dir with an absolute path the user controls.Guides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.
npx claudepluginhub tadeukaiba/mcp-media-toolkit --plugin mcp-media-toolkit