发现优质的 AI Agent 技能

yt-dlp is a CLI for downloading video/audio from TikTok and [many other sites](https://github.com/yt-dlp/yt-dlp/blob/master/supportedsites.md).

This skill turns the agent into a video DJ for Kosmi watch party rooms. It uses `agent-browser` (Chromium automation via accessibility-tree snapshots) to navigate to a Kosmi room, queue videos by URL, and auto-loop playback.

Record video demos of implemented features using Playwright's built-in screen recording. After a coding task completes, this skill starts your app, runs a scripted walkthrough, and captures video + screenshots + console logs as proof artifacts.

Record video demos of implemented features using Playwright's built-in screen recording. After a coding task completes, this skill starts your app, runs a scripted walkthrough, and captures video + screenshots + console logs as proof artifacts.

Generate terminal screenshots and animated GIFs/videos using [VHS](https://github.com/charmbracelet/vhs) from Charmbracelet.

Generate complete videos from text descriptions using AI.

来自 openclaw/skills 技能

Download m3u8/mp4 video and mp3/music, support 抖音、皮皮虾、微博 sharing links. Multi-thread download, WebUI, batch and Node API.

- **Text:** 280 characters (free), 25,000 (Premium+) - **Images:** Up to 4 per post, max 5MB each (JPEG, PNG, GIF, WEBP) - **Video:** Up to 140s, max 512MB - **Rate limit:** 300 posts/3h (app-level), 200 posts/15min (user-level) - **Threads:** Chain replies for longer content

> **Created:** 2026-02-18 > **Purpose:** Complete production plan for 3 demo formats targeting different audiences > **Product:** Self-Evolving Agent v4.0 — 5-stage multi-agent pipeline that reads AI logs, proposes AGENTS.md improvements, and measures whether those improvements actually worked.

来自 openclaw/skills 技能

Create animated circular avatar videos with lip-sync and blink animations. Takes 4 avatar frame images (neutral, slight open, wide open, eyes closed) and produces a round video with audio-driven mouth movement.