Modellix 插件技能

通过 Modellix 准备提示并生成图片、视频或音频。

完整可移植插件包包含设计执行与图像提示工程技能，将创意规划连接到 Modellix CLI、API 和可选文档 MCP。

适用场景

  • 准备详细图像提示
  • 生成或编辑创意媒体
  • 执行 Modellix 生成流程

使用方法

准备提示无需凭据；生成时配置 API 密钥或 CLI 配置档，并按上游要求准备 Node.js CLI 与 Python 就绪检查工具。

Skills

  • modellix-design

    Integrate Modellix's unified API for AI image, video, and audio workflows. Use this skill whenever the user wants to generate or edit images, create or transform videos, synthesize speech, transcribe audio, clone a voice, do virtual try-on, or call any Modellix model API. Also trigger when the user mentions Modellix, model-as-a-service for media generation, or providers such as Qwen, Wan, Seedream, Seedance, Kling, Hailuo, MiniMax, Whisper, or CosyVoice through a unified API, or when they ask for a Modellix model's request schema, OpenAPI contract, or required input fields. Prefer modellix-cli (model get-schema, model run --wait, task download, doctor, model list) over hand-rolled REST polling whenever the CLI is available.

    modellix/modellix-plugin

  • modellix-image-prompt-engineering

    Engineer clear, high-density prompts for AI image generation and editing before execution. Use this skill whenever a user asks for a cover, poster, banner, infographic, product shot, packaging concept, editorial illustration, UI mockup, slide visual, icon set, character sheet, card set, sprite sheet, image edit, or a better image prompt—even when they do not say "prompt engineering." Turn vague visual requests into an execution-ready T2I or I2I brief, then hand generation to modellix-design. Skip video/audio tasks, CLI/auth troubleshooting, and requests that already contain a complete prompt and only need execution.

    modellix/modellix-plugin