メニュー
Generate images using AI. Use when the user asks to create, generate, or make images, pictures, graphics, illustrations, visuals, or artwork. Also use for image editing with reference images.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
Access and navigate https://javbus.com using agent-browser, handling age verification checks with AI assistance if present, and extract video links. Use when user wants to: 1) Access javbus.com and pass age verification, 2) Extract video links from the site, 3) Navigate and interact with the website programmatically.
JavBus 演员作品搜索。当用户需要搜索演员作品（如"安野由美"）并获取磁力链接时使用。
Calculate weighted PE ratio for KWEB ETF by fetching top 10 holdings from Yahoo Finance, retrieving individual stock PEs, and computing the weighted average including remaining holdings (assumed PE=20). Use when user wants to: Get KWEB holdings breakdown, Calculate KWEB's weighted PE, Analyze KWEB's valuation metrics.
Redeploy a Vercel project using Vercel CLI. Use when user asks to redeploy the blog project or mentions blog deployment tasks like "redeploy my blog", "deploy the blog again", or "update and deploy blog".
Intelligent note-taking and query system with tags (#tag), feelings ($feel), mentions (@who), and todo (&) support. Use when user wants to save/record notes with automatic field extraction, query notes by time/feeling/tag or review notes with feelings/mentions, or visualize relationships between notes using ASCII art. Commands include save/record xxx, review notes from past X days, notes with {feel} from past X days, {tag} notes from past X months for relationship visualization.
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
SOC 職業分類に基づく
| name | nano-banana-pro |
| description | Generate images using AI. Use when the user asks to create, generate, or make images, pictures, graphics, illustrations, visuals, or artwork. Also use for image editing with reference images. |
| allowed-tools | Bash, Read, Write |
Generate images using Google's Gemini 3 Pro Image model.
Run the generation script:
python ~/.claude/skills/nano-banana-pro/generate_image.py "your prompt here" [options]
| Option | Description | Default |
|---|---|---|
--resolution | Output size: 1K, 2K, or 4K | 2K |
--aspect | Aspect ratio: 16:9, 1:1, 4:3, 9:16, 3:4 | 16:9 |
--output | Output directory path | ./generated_images |
--reference | Reference image(s) for style/editing (up to 14) | None |
--format | Output format: png, jpeg, webp | png |
python ~/.claude/skills/nano-banana-pro/generate_image.py "a serene mountain landscape at sunset, photorealistic"
python ~/.claude/skills/nano-banana-pro/generate_image.py "abstract geometric pattern in blue and gold" --aspect 1:1 --resolution 2K
python ~/.claude/skills/nano-banana-pro/generate_image.py "futuristic city skyline" --resolution 4K --output ~/Pictures/ai-generated
python ~/.claude/skills/nano-banana-pro/generate_image.py "transform this into a watercolor painting" --reference input.jpg
python ~/.claude/skills/nano-banana-pro/generate_image.py "add a rainbow in the sky" --reference landscape.png
Images are saved with timestamp filenames:
{timestamp}_{sanitized_prompt}.{format}20260106_143052_serene_mountain_landscape.pngThe script outputs the full path to the generated image.
google-genai libraryGEMINI_API_KEY environment variable