image-generation
Image Generation with Gemini
Gemini の画像生成 API を使って、ブログ記事やドキュメント用の図・イラストを生成するスキル。
Prerequisites
- google-genai:
python3 -c "from google import genai; print('OK')"— if missing:pip install google-genai - Pillow:
python3 -c "from PIL import Image; print('OK')"— if missing:pip install Pillow(JPEG→PNG変換に必要) - GEMINI_API_KEY: 環境変数に設定されていること
Usage
スクリプト実行
scripts/generate_image.py を使って画像を生成する。
# 基本
python3 scripts/generate_image.py "prompt text" /path/to/output.png
More from nyosegawa/skills
skill-auditor
>
22anti-human-bottleneck
Load this skill BEFORE asking the user any question, requesting confirmation, seeking approval, asking what to do next, or stopping to wait for human input. Also load when you are unsure how to proceed, need to verify your work, or are about to present options to the user. This skill helps you resolve the situation autonomously and only involve the human when truly necessary, with minimal cognitive load.
18docs-auditor
>
4mcp-light-generator
MCPサーバーの「Light版」を生成する。descriptionを1行に圧縮し、ベストプラクティスをAgent Skillとして分離する。Use when user asks to "MCP Light版を作って", "MCPを軽量化", "Light MCP", "mcp-light", "create light mcp", "compress mcp descriptions", "MCP description圧縮", or wants to reduce MCP tool definition token usage.
3remotion-promo-video-factory
Build high-quality Remotion promo and intro videos for any app type (web, mobile, API/SDK, developer tool, AI product) using app-type blueprints, timeline patterns, and frame-capture QA. Use when users ask to create a product promo, teaser, app intro, UX flow video, or Remotion-based demo video.
3