Agent Skills · Design & Media
Curated skills for Claude, Cursor and other AI agents. Copy one prompt to install.
Conversational LLM role for natural portrait retouching, covering exposure, composition, and post-processing.
Integrate Microsoft Edge TTS into OpenClaw QQBot, supporting multiple Chinese voices, long-text synthesis, process isolation, and local service management.
Generate children's picture book images using Baidu ERNIE-Image-Turbo via an OpenAI-compatible API, with seven resolutions and Chinese text rendering.
Auto-generates editable SVG/PNG academic tech roadmaps from research topics or text using 10 template presets.
Guides users through AI image generation with clickable choices for use case, style, prompt, tool, ratio, and quality, while supporting versioned regeneration.
Turn listing photos into labeled room clips, with optional broker narration and approved talking-head openings or closings.
Supports AI-generated and Blender script 3D modeling workflows from requirements, references, preview, to export.
Invoke the Vidu Q2 cloud API via dLazy CLI to generate images from text or reference images and return hosted output URLs.
Convert optimization plans into executable video edits with multi-platform outputs, automatic backend fallback, and progress tracking.
A browser-based 3D model viewer with multi-format rendering and remote control via MCP, HTTP, or postMessage.
Download Douyin, Kuaishou, Xiaohongshu, and Bilibili videos with yt-dlp and browser cookie support.
A local tldraw-based infinite canvas for importing HTML, annotating, generating AI images, and applying changes via REST API.