web-audio
Production-tested patterns for fault-tolerant browser audio with zero-lag rapid-fire support. Use when implementing sound effects, background music, voice feedback, or any audio playback in web applications. Covers AudioContext singleton, preloading, cloneNode for rapid-fire, autoplay handling, and Web Audio API effects.
youtube-video-to-audio
Download YouTube videos as audio files using yt-dlp
extract-exif
Extract EXIF metadata from images to JSON. Works with any image folder. Outputs structured data including dimensions, orientation, and timestamps.
audio-debugging
Automatically helps debug Web Audio API issues, audio playback problems, pitch preservation, and caching issues in the VSSK-shadecn music practice app
audio-extract
从视频文件中提取音频。Use when user wants to 提取音频, 抽取音频, 视频转音频, 导出音频, extract audio, video to audio, get audio from video, 把视频的声音提取出来.
video-analysis
AI-powered video understanding and analysis toolkit. Use this skill when Claude needs to: (1) Analyze video files (.mp4, .mov, .avi, .mkv, .webm, screen recordings), (2) Extract video content or summarize videos, (3) Identify key moments with timestamps, (4) Analyze product demos or app tutorials, (5) Transcribe or understand video content, (6) Extract frames or screenshots from video, or any other video understanding task. Supports: general video summary, product feature extraction, key moment identification with timestamps, and custom prompt-based analysis.
convert-image
PNG/JPG/JPEG画像をWebP、ICO、SVG形式に変換。「画像を変換して」「webpに変換」などで使用。
bg-remover
Remove backgrounds from images using FAL.ai's BiRefNet model. Use when users ask to remove background, make transparent PNG, extract subject from image, or create cutouts. Trigger phrases include "remove background", "transparent background", "cut out", "extract subject", or any background removal request.
dashcam-frame-extraction
GPU-accelerated frame extraction for Movie_F dashcam videos. This skill should be used when the user needs to extract frames from Movie_F category dashcam videos placed in the Desktop CARDV folder. Extracts 3 frames per video (BEGIN, MIDDLE, END) using NVIDIA CUDA acceleration with automatic gap analysis, parallel processing, and strict error handling. This is specifically designed for Movie_F category only.
youtube-cache
YouTube video cache operations with Qdrant. Auto-checks cache when YouTube URLs detected. Provides semantic search, verification, ingestion, and archive access. Shows metadata by default, transcript on request.
ai-image-effects
Apply AI visual effects including Illusion Diffusion ($0.006), FLUX Fill Pro accessory replacement ($0.05), and SAM object detection (<$0.01). Use when adding AI effects, replacing image elements, detecting objects, or applying visual transformations.
upload-prepare
Prepare YouTube upload for bilingual audiobook video. Runs youtube-metadata skill, builds upload command, validates all files, checks languages by reading translations from middle of book, verifies wordcards play, shows thumbnail/background/output. Does NOT upload - only preparation and checklist. Use when user wants to prepare upload, check before upload, or validate video for YouTube.
youtube-download
使用 yt-dlp 下载 YouTube 视频、音频或字幕。Use when user wants to 下载视频, 下载YouTube, youtube下载, 下载油管, download youtube, download video, 下载B站, bilibili下载.
m4b-audiobook-builder
Build and merge M4B audiobooks on Linux from multiple audio files or multi-part M4B sets, with chapter generation, metadata normalization, UTF-8/Russian encoding handling, and validation. Use when combining MP3/M4A/AAC/FLAC/OGG/WAV into one M4B, merging split M4B parts, or fixing audiobook chapters and metadata.
check-images
Analyze and validate images on web pages. Use when users ask to check image alt tags, verify image accessibility, find missing alt attributes, audit image SEO, or check image optimization. Detects missing alt, empty alt, decorative images without proper markup, oversized images, and missing dimensions.
funimation
Stream dubbed anime on Funimation and access legacy content library
video-downloader
Downloads videos from YouTube and other platforms for offline viewing, editing, or archival. Handles various formats and quality options.
veo-image-to-video
Animate a single image into a video using fal.ai Veo 3.1. Use when the user wants to create a video from a still image, animate a photo, or bring an image to life. Supports up to 8 seconds of video with optional audio.
image-validator
Validate images against tacosdedatos illustration style guide. Use this skill when reviewing generated images, checking uploaded images for brand consistency, providing quality feedback on visual assets, or deciding if an image is ready for publication. Returns pass/fail with specific actionable feedback.
video-concat
合并多个视频文件为一个视频。Use when user wants to 合并视频, 拼接视频, 视频合并, 视频拼接, 把视频合在一起, 连接视频, join videos, merge videos, combine videos, concatenate videos.
gif-analyzer
Analyze animated GIF files by extracting and viewing frames as sequential video. Use when: - User mentions a GIF file path (e.g., "./demo.gif", "~/Downloads/animation.gif") - User wants to analyze or understand a GIF animation - User asks about motion, changes, or content in a GIF - User attaches or references a .gif file for analysis - User wants to examine a screen recording in GIF format - User invokes /gif slash command Keywords: "GIF", ".gif", "animation", "animated", "frames", "screen recording", "analyze gif", "gif analysis", "view gif", "gif content", "gif motion" Trigger patterns: - Natural language: "Analyze this GIF: ./demo.gif" - Slash command: `/gif <path>` or `/gif <path> <message>` When triggered, extract frames using the Python script, view frames in order, and interpret as continuous video sequence.
