audio-transcribe
Speech-to-text transcription using Whisper with word-level timestamps. Use when users ask to transcribe audio or video to text, generate subtitles, or recognize speech.
browser
Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website", "log into", or any browser interaction request.
image-gen
AI image generation and editing. Use when users ask to generate, create, or draw images with AI, or edit and modify existing images.
maxmotion-edit
Activated when user message contains an <editor /> XML tag (injected by Max Client Video Editor). Guides how to edit Remotion project clips (maxmotion.json) and sequences (.tsx source code).
media-processing
Process audio and video files with ffmpeg — trim, merge, extract audio, convert formats, compress, and more.
memory
Read long-term memory files to get historical context, code references, and error fix records. Use when user wants to read memory, get context, check history, avoid repeating errors.
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
video-gen
AI video generation with text-to-video, image-to-video, and first/last frame control. Use when users ask to generate or create videos from text prompts or images.
youtube-download
Download videos, audio, or subtitles from YouTube, Bilibili, and other sites using yt-dlp. Use when users ask to download online videos or extract audio from video URLs.