菜单
Generate images via OpenAI (DALL-E / gpt-image-1) or Stable Diffusion (AUTOMATIC1111-compatible) endpoints.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | image-generation |
| description | Generate images via OpenAI (DALL-E / gpt-image-1) or Stable Diffusion (AUTOMATIC1111-compatible) endpoints. |
| version | 2026.2.21 |
| publisher | Local Publisher |
| handler_language | typescript |
| handler_file | handler.ts |
| inputs_schema | {"type":"object","properties":{"prompt":{"type":"string"},"provider":{"type":"string","enum":["openai","stable_diffusion"],"default":"openai"},"size":{"type":"string","enum":["256x256","512x512","1024x1024","1024x768","768x1024"],"default":"1024x1024"},"n":{"type":"integer","minimum":1,"maximum":4,"default":1},"style":{"type":"string","default":""}},"required":["prompt"],"additionalProperties":false} |
| outputs_schema | {"type":"object","properties":{"provider":{"type":"string"},"model":{"type":"string"},"images":{"type":"array","items":{"type":"object","properties":{"data_url":{"type":"string"},"seed":{"type":"number"},"width":{"type":"number"},"height":{"type":"number"}},"required":["data_url"]}}},"required":["images"]} |
Generate images from text prompts using either OpenAI's image generation APIs or a Stable Diffusion endpoint (AUTOMATIC1111-compatible).
OPENAI_API_KEY (required)OPENAI_IMAGE_MODEL (optional, default gpt-image-1)STABLE_DIFFUSION_URL (optional, default http://127.0.0.1:7860)STABLE_DIFFUSION_API_KEY (optional, for reverse proxies)Image generation produces new media artifacts and can incur external API costs. Treat this as write scope and require user approval when cost controls or restricted content policies apply.
api.openai.comSTABLE_DIFFUSION_URLimage.generate: write (creates media artifacts)image.generate.safe: write (same scope, but enforce safe prompt policies if configured)This skill returns data URLs by default for easy rendering in clients. Persist outputs to object storage if needed.
Sends messages between agents, broadcasts to channels, and retrieves message history for inter-agent communication.
Spawns, manages lifecycle, and terminates autonomous AI agents from the 40+ built-in agent catalog.
Optimize prompts and context windows to reduce token usage while preserving quality.
Animated desktop character state machine for Sven's Tauri companion app. Manages character form (ORB, ARIA, REX, ORION), state transitions (idle→thinking→speaking→celebrating), walk cycles, thought bubbles, sound effects, and real-time agent event sync.
Multi-model deliberation system. Sends queries to multiple LLMs simultaneously, has them peer-review each other's responses anonymously, then a chairman model synthesizes the best answer. Supports configurable council composition, voting strategies, and cost tracking.
Interactive educational autograd engine — port of Karpathy's micrograd. Build, train, and visualise tiny neural networks step-by-step to learn how backpropagation works.