スキル一覧に戻る
AndyShaman

whisk

by AndyShaman

Generate images with Google Whisk AI (Imagen 3.5) directly from Claude Code

8🍴 2📅 2026年1月23日
GitHubで見るManusで実行

SKILL.md


name: whisk description: Use when user asks to generate, create, or draw an image, photo, picture, logo, illustration, or art. Triggers include 'сгенерируй', 'нарисуй', 'создай картинку', 'сделай фото', 'фотографию', 'изображение', 'иллюстрацию', 'логотип', 'generate image', 'create image', 'draw', 'make a picture', 'visualize'.

Whisk - Image Generation via Google Imagen 3.5

Generate images using Google Whisk AI directly from Claude Code.

When to Use

  • User asks to generate/create/draw an image, photo, picture
  • User wants a logo, illustration, art, or visualization
  • Keywords: "нарисуй", "сгенерируй", "создай картинку", "сделай фото", "generate", "draw", "create image"

Workflow (IMPORTANT)

Before generating an image, ALWAYS ask the user:

  1. Output folder — Where to save the image?
    • Default: ./whisk-images
    • User may specify a different folder

Use AskUserQuestion tool with options:

  • "По умолчанию (whisk-images)" / "Default (whisk-images)"
  • "Указать другую папку" / "Specify another folder"

If user chooses default or doesn't respond, use ./whisk-images.

Context Optimization (CRITICAL)

NEVER read generated images with the Read tool!

Why: Reading PNG files converts them to base64 and consumes thousands of tokens from context window.

After generation:

  1. Show only the file path to user
  2. Tell user: "Изображение сохранено: "
  3. DO NOT use Read tool on generated .png files
  4. DO NOT display the image inline

User can open the file manually in their file manager or image viewer.

Quick Reference

CommandDescription
whisk generate "prompt"Generate image
whisk generate "prompt" -c 3Generate 3 variants
whisk generate "prompt" -r 16:9Landscape format
whisk generate "prompt" -o ./folderSave to folder
whisk statusCheck auth status
RatioSizeUse Case
1:11024x1024Avatars, icons, logos
16:91365x768Banners, landscapes
9:16768x1365Stories, posters

CLI Usage

whisk generate "your prompt" [options]

Options

  • -c, --count <n> — Number of images (1-10), default: 1
  • -r, --ratio <ratio> — Aspect ratio (1:1, 16:9, 9:16), default: 1:1
  • -o, --output <dir> — Output directory, default: ./whisk-images

Examples

# Simple generation
whisk generate "cat in space, digital art"

# Multiple variants
whisk generate "minimalist coffee shop logo" -c 3

# Landscape banner
whisk generate "sunset over ocean" -r 16:9

# Custom output folder
whisk generate "abstract background" -o ./assets/bg

Authorization Flow

CLI handles authorization automatically:

  1. If no token exists, CLI starts auth-server on port 3847
  2. CLI shows instructions to user
  3. User opens labs.google/fx/tools/whisk in Chrome
  4. User clicks Connect in Whisk Proxy extension
  5. Extension sends token to localhost:3847
  6. CLI receives token and continues generation

No manual server startup required!

Prompt Tips

  1. Be specific: "orange cat on windowsill" > "cat"
  2. Add style: "digital art", "watercolor", "photorealistic", "minimalist"
  3. Composition: "centered", "close-up", "wide angle"
  4. Atmosphere: "cozy", "dramatic lighting", "vibrant colors"

Troubleshooting

"Not authorized" / "Не авторизован"

CLI will automatically show authorization instructions. Follow them:

  1. Open https://labs.google/fx/tools/whisk in Chrome
  2. Log into Google account
  3. Click Connect in Whisk Proxy extension

"Token expired"

CLI will automatically re-request authorization when token expires.

Check status

whisk status

スコア

総合スコア

65/100

リポジトリの品質指標に基づく評価

SKILL.md

SKILL.mdファイルが含まれている

+20
LICENSE

ライセンスが設定されている

+10
説明文

100文字以上の説明がある

0/10
人気

GitHub Stars 100以上

0/15
最近の活動

1ヶ月以内に更新

+10
フォーク

10回以上フォークされている

0/5
Issue管理

オープンIssueが50未満

+5
言語

プログラミング言語が設定されている

+5
タグ

1つ以上のタグが設定されている

+5

レビュー

💬

レビュー機能は近日公開予定です