Agent skill
gemini-gen
Generates images using Google's Gemini model. Prioritizes standard resolution to save quota. Automatically opens images on macOS.
Install this agent skill to your Project
npx add-skill https://github.com/ttmouse/skills/tree/main/gemini-gen
SKILL.md
Gemini Image Generator
This skill generates images using Google's Gemini model. It is configured to be cost-efficient by defaulting to standard resolution models.
Usage
python3 {script_path} "Prompt" [--model model_name] [--output filename.png] [--no-open]
IMPORTANT: Model Selection Policy (Quota Saving)
Always default to standard resolution models. Do NOT use 4K models unless the user explicitly mentions "4K", "Ultra HD", or "High Definition".
Available Models
| Model Name | Aspect Ratio | Resolution | Cost Category |
|---|---|---|---|
gemini-3-pro-image (Default) |
1:1 | Standard | Low (Recommended) |
gemini-3-pro-image-16x9 |
16:9 | Standard | Low (Recommended) |
gemini-3-pro-image-9x16 |
9:16 | Standard | Low (Recommended) |
gemini-3-pro-image-4k |
1:1 | 4K | High |
gemini-3-pro-image-4k-16x9 |
16:9 | 4K | High |
gemini-3-pro-image-4k-9x16 |
9:16 | 4K | High |
Decision Logic for Alma
- Default: Use
gemini-3-pro-image. - Aspect Ratio:
- If "landscape/widescreen/16:9", use
gemini-3-pro-image-16x9. - If "portrait/mobile/9:16", use
gemini-3-pro-image-9x16.
- If "landscape/widescreen/16:9", use
- 4K (Only if explicitly requested):
- Only upgrade to a
-4kmodel if the user explicitly says "4K" or equivalent high-res keywords.
- Only upgrade to a
Note on Display
Alma's chat UI does not render local images. The skill uses open to show the image in the system viewer.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
ttmouse/skills
template-skill
Replace with description of the skill and when Claude should use it.
ttmouse/skills
prompt-analyzer
提示词分析与洞察 - 查看Prompt详情、对比差异、推荐相似提示词、元素库统计
ttmouse/skills
meta-skill
元技能 - 对话复盘与技能进化。在对话结束后分析：已用技能是否可优化、未形成技能的流程是否值得沉淀。当用户说"复盘"、"回顾对话"、"优化技能"、"沉淀经验"、"这个流程可以复用吗"、"技能体系复盘"、"技能健康检查"等关键词时触发，或用户显式调用 /meta-skill。
ttmouse/skills
doc-coauthoring
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.
ttmouse/skills
downloads-organizer
Automatically organize and clean up downloads folder by categorizing files, removing duplicates, and optimizing storage space
ttmouse/skills
universal-writer
通用写作技能：从数据到文章的自动化写作工作流。 支持多种写作模板（专题、教程、分析、总结、文档），可根据数据源或交互式生成文章。 当用户说"写作"、"生成文章"、"写文档"、"universal-writer"时触发。
Didn't find tool you were looking for?