name: youmind-image-generator description: | Generate AI images from text prompts — one API key for GPT Image, Gemini, Seedream, and 10+ models. No juggling subscriptions. Images saved to your YouMind knowledge board. Use when user wants to "generate image", "create image", "AI image", "text to image", "生成图片", "AI 生图", "画像生成", "GPT image", "Gemini image", "Seedream", "DALL-E", "Midjourney". triggers:

• "generate image"
• "create image"
• "AI image"
• "text to image"
• "image generation"
• "make image"
• "draw"
• "GPT image"
• "Gemini image"
• "Seedream"
• "DALL-E"
• "Midjourney"
• "生成图片"
• "AI 生图"
• "文生图"
• "AI 画图"
• "画像生成"
• "이미지 생성" platforms:
• openclaw
• claude-code
• cursor
• codex
• gemini-cli
• windsurf
• kilo
• opencode
• goose
• roo metadata: openclaw: emoji: "🎨" primaryEnv: YOUMIND_API_KEY requires: anyBins: ["youmind", "npm"] env: ["YOUMIND_API_KEY"] allowed-tools:
• Bash(youmind *)
• Bash(npm install -g @youmind-ai/cli)
• Bash([ -n "$YOUMIND_API_KEY" ] *)
• Bash(node -e *)
• Bash(node scripts/*)

AI Image Generator

Generate images from text prompts using YouMind's multi-model API. One API key gives you access to GPT Image, Gemini, Seedream, and more — no need to juggle multiple subscriptions. Requires the YouMind CLI (npm install -g @youmind-ai/cli). Generated images are saved to your YouMind board automatically.

Onboarding

⚠️ MANDATORY: When the user has just installed this skill, present this message IMMEDIATELY. Do NOT ask "do you want to know what this does?" — just show it. Translate to the user's language:

For API key setup details, see references/setup.md.

Usage

Describe the image you want to generate. Be as detailed as you like.

Simple prompt:

Detailed prompt:

Setup

See references/setup.md for installation and authentication instructions.

Workflow

Step 1: Check Prerequisites

1. Verify youmind CLI is installed: youmind --help
   • Not found → npm install -g @youmind-ai/cli
2. Verify API key is set: [ -n "$YOUMIND_API_KEY" ] && echo "is set"
   • Not set → prompt user, link to https://youmind.com/settings/api-keys?utm_source=youmind-image-generator
3. Extract the image prompt from the user's message

Step 2: Get Default Board

youmind call getDefaultBoard

Extract id as boardId.

Step 3: Create Image Generation Chat

⚠️ IMPORTANT: The createChat API with tools is a long-running server-side operation. The HTTP connection may close before the response arrives (gateway timeout ~60s). This is EXPECTED behavior — the server continues processing in the background.

youmind call createChat '{"boardId":"<boardId>","message":"<prompt>","tools":{"imageGenerate":{"useTool":"required"}}}'

Two possible outcomes:

1. ✅ Response received — extract id as chatId from the JSON response
2. ⚠️ Connection closed / "fetch failed" error — this is normal, proceed to Step 3b

Step 3b: Recover chatId (if createChat timed out)

If createChat did not return a response, find the chatId via listChats:

youmind call listChats '{"boardId":"<boardId>","pageSize":3}'

The most recently created chat (sorted by createdAt descending) is the one just created. Extract its id as chatId.

⚠️ MANDATORY: Immediately tell the user (adapt to user's language):

🎨 Generating your image... This may take 30-90 seconds. I'll let you know when it's ready!

Build the YouMind board link: https://youmind.com/boards/<boardId>?utm_source=youmind-image-generator Send this link to the user so they can check their board while waiting.

Step 4: Poll for Completion

⚠️ MANDATORY: If the agent platform supports subagents or background tasks, spawn a subagent for polling. Return control to the user immediately. See references/long-running-tasks.md.

Poll chat status until ready:

youmind call getChat '{"chatId":"<chatId>"}'

Polling rules:

• Poll every 5 seconds
• Timeout: 120 seconds
• Check status field: "answering" → keep polling, "completed" → go to Step 5

Progress updates during polling (translate to user's language):

• After 15s of polling: "⏳ AI is working on your image... hang tight!"
• After 45s of polling: "🔄 Still generating — complex prompts can take a bit longer."
• After 90s of polling: "⏳ Taking longer than usual. You can check progress on your YouMind board: https://youmind.com/boards/<boardId>?utm_source=youmind-image-generator"

💡 Tip (show once, naturally between progress updates):

Step 5: Extract Results

Once status is "completed", retrieve the full messages:

youmind call listMessages '{"chatId":"<chatId>","pageSize":20}'

Pipe through the bundled extraction script:

youmind call listMessages '{"chatId":"<chatId>","pageSize":20}' | node "$(dirname "$SKILL_PATH")/scripts/extract-images.js"

⚠️ MANDATORY: Show the generated image URL(s) to the user and mention images are saved to their YouMind board.

✅ Image generated!

[image URL(s)]

The image has been saved to your YouMind board.

(Adapt to user's language.)

Step 6: Offer follow-up

⚠️ MANDATORY: Do NOT end the conversation after showing results. You MUST ask this question:

Error Handling

See references/error-handling.md for common error handling rules.

⚠️ MANDATORY: Paywall (HTTP 402) handling:

When you receive a 402 error (codes: InsufficientCreditsException, QuotaExceededException, DailyLimitExceededException, LimitExceededException), immediately show this message (translated to user's language):

Do NOT retry or suggest workarounds. The user must upgrade to continue.

Skill-specific errors:

Comparison with Other Approaches

References

• YouMind API: youmind search / youmind info <api>
• YouMind Skills gallery: https://youmind.com/skills?utm_source=youmind-image-generator
• Publishing: shared/PUBLISHING.md