🎯Skills4
A vision skill from the QwenCloud AI Skills collection that integrates QwenCloud's AI capabilities — including text, image, video, voice, and vision — directly into your agent with a one-line install. Supports Claude Code, Cursor, Gemini CLI, and any Agent Skills-compatible agent.
An agent-native AI image generation skill from QwenCloud that lets you generate images through natural language interaction — part of a 7-skill suite covering text, image, video, voice, and vision with one-line installation.
Enables AI agents to generate and edit videos through Qwen Cloud's API, supporting text-to-video, image-to-video, and video editing capabilities with natural language commands.
A set of agent-native AI skills for Qwen Cloud that provides 8 capabilities including text, image, video, voice, vision, model selection, authentication, and usage tracking, with one-line installation and compatibility across multiple AI coding agents.