CMS, document processing, and media generation.
Adjust photo brightness, contrast, and saturation based on natural language prompts using GPT-5 text analysis. Use when the user asks to adjust brightness, change contrast, modify saturation, apply a specific style, or fix photo issues like washed out colors.
Image and video registry management with automated slot injection
This skill should be used when the user asks to "analyze video", "summarize video", "extract video transcript", "understand video content", "video to text", "describe video", "ask questions about video", or "what happens in this video". Analyzes videos using Google Gemini API with local file upload or YouTube URL input.
Improves the quality of images, especially screenshots, by enhancing resolution, sharpness, and clarity. Perfect for preparing images for presentations, documentation, or social media posts.
Smart video processing for compress, convert, trim, and audio extraction with batch support. Use when users ask to compress videos, convert to MP4/WebM, extract video clips, trim videos, remove audio, extract audio tracks, or batch process video files. Supports modern codecs and social media presets.
Upload pipeline troubleshooting for Sketch Magic. Use when HEIC uploads fail, previews don’t render, files are too large, or upload validation errors appear.
Create standard SuperCollider audio effects for Bice-Box (delays, reverbs, filters, distortions). Provides templates, ControlSpecs, common patterns, and MCP workflow for safely creating/updating effects.
Video editing via FFmpeg with git-like staging workflow and platform presets. Use when the user asks to: (1) cut/trim/edit videos, (2) convert formats or codecs, (3) optimize for platforms (WhatsApp, Instagram, YouTube, Twitter, Telegram), (4) extract audio or create GIFs, (5) get video info/metadata, (6) rotate/resize/crop, (7) speed up/slow down videos, (8) compress videos, (9) concatenate multiple videos. All operations go to staging before final approval. Supports operation history, replay, batch processing, and undo/redo.
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.
Download YouTube videos as audio files using yt-dlp
Extract EXIF metadata from images to JSON. Works with any image folder. Outputs structured data including dimensions, orientation, and timestamps.
Automatically helps debug Web Audio API issues, audio playback problems, pitch preservation, and caching issues in the VSSK-shadecn music practice app
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.
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.
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。
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.
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 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.
