发现优质的 AI Agent 技能

Generate talking avatar videos from images and audio using DreamAvatar 3.0 Fast API.

Download videos from Xiaohongshu (小红书) by extracting the real CDN URL from the page.

Fetches plain-text transcripts from YouTube videos using `extract_youtube_transcript.py` in this skill folder.

`video_type` is required by Boosta API.

来自 openclaw/skills 技能

Analyze images using **Google Cloud Vision API**.

Save and structure discharge summary information. Supports extraction from images or direct processing from text descriptions.

Capture the current RedNote App screen. Returns an image.

Download videos from Jable.tv with automatic organization by actress name.

Use the internal Google Antigravity sandbox to generate images with the `gemini-3-pro-image` model. This skill bypasses standard API restrictions by impersonating the VS Code plugin environment.

Images must look like a comic page. All conversation use Chinese.

Store and retrieve visual content — user images, charts, diagrams, website UIs — across conversations.