catsharp-sonification
Sonify GF(3) color streams via CatSharp scale. Maps Gay.jl colors to pitch classes and plays through sox. No voice synthesis.
Sonify GF(3) color streams via CatSharp scale. Maps Gay.jl colors to pitch classes and plays through sox. No voice synthesis.
Improves the quality of images, especially screenshots, by enhancing resolution, sharpness, and clarity. Perfect for preparing images for presentations, documentation, or social media posts.
Improves the quality of images, especially screenshots, by enhancing
Downloads videos from YouTube and other platforms for offline viewing,
Detect and extract hidden data embedded in images, audio, and other media files using steganalysis tools to uncover covert communication channels.
Automated video processing: metadata extraction, thumbnails, transcoding, audio extraction with DuckDB tracking
Extract transcripts from YouTube playlists into DuckDB ACSet schema. Uses pytubefix + mlx-whisper on Apple Silicon. Supports auto-captions and local transcription fallback.
Recover deleted files from disk images and storage media using PhotoRec's file signature-based carving engine regardless of file system damage.
Recover files from disk images and unallocated space using Foremost's header-footer signature carving to extract evidence regardless of file system state.
Create forensically sound bit-for-bit disk images using dd and dcfldd while preserving evidence integrity through hash verification.
Perform comprehensive forensic analysis of disk images using Autopsy to recover files, examine artifacts, and build investigation timelines.
FFmpeg media processing. Video/audio transcoding, stream manipulation, and filter graphs.
Always-on audio capture via whisper-cpp to org file with Emacs live display
Domain-specific guidance for Remotion video work in this repository. Use when creating, editing, or reviewing Remotion compositions, animations, captions, audio handling, transitions, or media-processing workflows.
Edits existing images via Gemini API and updates them in DexCode slide decks. Sends the original image with an edit prompt to apply targeted modifications such as removing objects, changing colors, or adding elements. Use when user says "edit image", "fix image", "modify image", "remove the background", or the Japanese equivalents "画像を編集", "画像を修正", "画像を直して". Key capabilities: in-place overwrite or save-as-new, visual verification before and after edit, aspect ratio and resolution control, English prompt optimization for best Gemini results.
Video processing toolkit. Use when user wants to: - Download videos from YouTube or other sites - Remove silence from videos - Trim, cut, or extract segments from videos - Extract audio from video files - Enhance or denoise audio - Replace audio track in a video - Change video playback speed - Concatenate multiple videos - Generate transcripts/captions (VTT) - Generate video descriptions, timestamps, or context cards - Upload videos to YouTube or Bunny.net CDN - Post social updates to X (Twitter) or LinkedIn - Get video metadata (duration, resolution, codec)
Download videos from URLs (YouTube, Bilibili, and any yt-dlp supported platform), transcribe speech to text using Whisper, generate a structured summary, and save both the summary and full transcript as linked Obsidian notes. Use this skill whenever the user wants to summarize a video, transcribe video content, extract key points from a video, or save video notes to Obsidian. Also trigger when the user shares a video URL and asks for analysis, notes, or a recap.
Edit talking-head videos by removing silences with neural VAD and adding 3D swivel teaser transitions. Use when user asks to edit video, remove silences, add jump cuts, or create video teasers.