Generate blog cover images optimized for 16:9 headers — clean composition with text-friendly layouts, powered by multi-model AI. Use when user wants to "blog cover", "featured image", "article image", "cover image",
"thumbnail", "文章配图", "封面图", "博客配图", "ブログカバー", "블로그 커버".
Instrucciones de origen · Vista previa de solo lectura
name
youmind-blog-cover
version
1.0.0
description
Generate blog cover images optimized for 16:9 headers — clean composition with text-friendly layouts, powered by multi-model AI. Use when user wants to "blog cover", "featured image", "article image", "cover image",
"thumbnail", "文章配图", "封面图", "博客配图", "ブログカバー", "블로그 커버".
Generate professional blog cover images and article illustrations from your content context using YouMind AI. Optimized for 16:9 blog headers with clean composition and text-friendly layouts — just provide your article title or topic. Requires the YouMind CLI (npm install -g @youmind-ai/cli). Generated images are saved to your YouMind board automatically.
⚠️ 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:
✅ Blog Cover Image Generator installed!
Give me your article title or topic and I'll generate a professional cover image.
What it does:
Generate blog cover images optimized for 16:9 headers
Clean composition with text-friendly layouts
Powered by multi-model AI (GPT Image, Gemini, Seedream)
Extract the article title, topic, or URL from the user's message
Step 2: Get Default Board
youmind call getDefaultBoard
Extract id as boardId.
Step 3: Construct Optimized Prompt and Create Chat
Build a cover-image-optimized prompt from the user's input. The prompt should follow this pattern:
Create a professional 16:9 blog header image for an article about [topic/title]. Style: modern, clean, suitable for a blog cover. The composition should leave space for text overlay. Use vibrant but not overwhelming colors with a professional feel.
Adapt the prompt based on the user's input — if they mention a specific style, incorporate it.
⚠️ 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.
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 blog cover 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-blog-cover
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-blog-cover"
💡 Tip (show once, naturally between progress updates):
⚠️ MANDATORY: Show the generated cover image URL(s) to the user and suggest regeneration options.
✅ Blog cover image generated!
[image URL(s)]
The image has been saved to your YouMind board.
Want a different style? Just say "regenerate with a more minimalist style" or "try a darker theme".
(Adapt to user's language.)
Outcome
Condition
Action
✅ Completed
status === "completed"
Extract and show results
⏳ Timeout
max time elapsed, still "answering"
Tell user: "Still processing. Check your YouMind board: https://youmind.com/boards/?utm_source=youmind-blog-cover"
❌ Failed
status === "errored" or tool status === "errored"
Tell user: "Generation failed. Please try a different description."
Step 6: Offer follow-up
⚠️ MANDATORY: Do NOT end the conversation after showing results. You MUST ask this question:
"Want a different style? Just say 'regenerate with a more minimalist style' or 'try a darker theme'."
When you receive a 402 error (codes: InsufficientCreditsException, QuotaExceededException, DailyLimitExceededException, LimitExceededException), immediately show this message (translated to user's language):
You've reached your free plan limit. Upgrade to Pro or Max to unlock unlimited image generation, more AI credits, and priority processing.
