🦀 ClawHub
Creatok Generate Image
by @newt0n
This skill should be used when the user asks to generate an image, create an AI image, produce a product image, generate a visual from a prompt, or check and...
TERMINAL
clawhub install creatok-generate-image📖 About This Skill
name: creatok-generate-image version: "1.0.0" description: "This skill should be used when the user asks to generate an image, create an AI image, produce a product image, generate a visual from a prompt, or check and continue an existing image generation task. Generates images through CreatOK's image generation API and can also recover interrupted generation flows from an existing task id." license: Open Source compatibility: "Claude Code ≥1.0, OpenClaw skills, ClawHub-compatible installers. Requires network access to CreatOK Open Skills API. No local image rendering packages required." metadata: openclaw: requires: env: [] bins: - node primaryEnv: CREATOK_API_KEY author: creatok version: "1.0.0" geo-relevance: "low" tags: - image-generation - ai-image - text-to-image - product-image - gpt-image - seedream - nano-banana - prompt-to-image triggers: - "generate an image" - "create an image" - "generate a product image" - "make an image from this prompt" - "create an AI image" - "generate a visual" - "text to image" - "produce an image" - "start image generation" - "generate it as an image" - "check this image generation task" - "did my image finish" - "check this image task id" - "画像を生成して" - "画像を作って" - "商品画像を作って" - "このプロンプトで画像を作って" - "이미지 생성해줘" - "이미지 만들어줘" - "상품 이미지 만들어줘" - "이 프롬프트로 이미지를 만들어줘" - "genera una imagen" - "crea una imagen" - "genera una imagen de producto" - "convierte este prompt en una imagen" - "gere uma imagem" - "crie uma imagem" - "gere uma imagem de produto" - "transforme este prompt em uma imagem"
generate-image
Constraints
Model Selection Rules
The skill must read model list, defaults, and hard limits from the CreatOK capabilities endpoint at runtime instead of hardcoding them locally.
Keep the local client thin:
Inputs to clarify (ask if missing)
Workflow
1. Confirmation gate (mandatory)
n)
- aspect ratio if specified
- estimated cost/credits if available
2. Submit image generation
POST /api/open/skills/image-generation3. Poll status until completion
GET /api/open/skills/tasks/status?task_id=...&task_type=image_generation4. Persist artifacts + respond
outputs/result.json with task_id/status/images/raw
- outputs/result.md
task_id immediately after submission so the user can recover later.Existing Task Recovery
task_id, continue from that task instead of starting a new one.Artifacts
All artifacts under generate-image/.artifacts/.