AgriciDaniel

Edit and modify existing GIFs. Speed change, reverse, ping-pong, crop, resize, text overlay, frame extraction, loop control, trim. Uses gifsicle for frame-level operations and FFmpeg for filters. Use when user says "edit gif", "gif speed", "reverse gif", "crop gif", "resize gif", "add text to gif", "gif text overlay", "extract frames", "loop gif", "ping pong gif", or "trim gif".

AI video generation from text or image prompts using Google Veo 3.1 Fast ($0.15/sec, native audio, 8s clips, up to 4K), Runway Gen-4 Turbo ($0.05/sec, silent B-roll, 10s), or local Stable Video Diffusion (free, 2-4s). Generates transition clips, B-roll footage, animated intros/outros, establishing shots, and image-to-video animations. Use when user says "generate video", "AI video", "video from te

One-command platform-optimized video export using FFmpeg. Produces ready-to-upload files for YouTube, TikTok, Instagram Reels, Instagram Feed, LinkedIn, Web (WebM), Podcast (audio-only), and high-quality GIF. Handles resolution, codec, bitrate, aspect ratio, and container requirements per platform. Use when user says "export", "youtube", "tiktok", "reels", "shorts", "instagram", "linkedin", "web",

AI-powered audio enhancement for video using Demucs v4 (source separation, isolate vocals/drums/bass/other, 7GB VRAM), pyannote-audio 4.0 + WhisperX (speaker diarization), DeepFilterNet3 (AI noise reduction, superior to FFmpeg), ElevenLabs/OpenAI/Bark TTS (voiceover generation), and AudioSR (phone-to-studio quality upsampling). Use when user says "separate audio", "isolate vocals", "remove music",

Video analysis and inspection using FFprobe and FFmpeg. Reads metadata, codec info, resolution, bitrate, duration, HDR status, keyframe structure, audio loudness, scene boundaries, and quality metrics (VMAF, SSIM, PSNR). Use when user says "analyze", "inspect", "info", "metadata", "quality", "VMAF", "SSIM", "PSNR", "scene detect", "keyframes", "HDR", "bitrate", "ffprobe", or "what codec".

Longform-to-shortform video pipeline that automatically extracts viral-ready short clips from long videos. V3 pipeline with VLM-powered visual analysis (Gemini 2.5 Flash), auto-detects screen recordings vs talking-head, uses "Framed" layout for screen content (padded top/bottom with centered captions), face-tracked crop for talking-head. Transcribes with WhisperX, scores by visual interest + trans

Programmatic video creation using Remotion (React-based). Generates title cards, data visualizations, motion graphics, branded intros/outros, animated text, and template-based videos from data. Claude writes React components, Remotion renders them headlessly to video. Use when user says "create video", "title card", "intro", "outro", "motion graphics", "animated text", "data visualization video",

Convert video files, image sequences, and animated SVGs to optimized GIFs. Mode A: Video to GIF (FFmpeg two-pass palette). Mode B: Image sequence to GIF. Mode C: AI image sequence to GIF (Gemini/FLUX.2 progressive prompts). Mode D: Animated SVG to transparent GIF (Playwright + FFmpeg). Use when user says "video to gif", "convert to gif", "screen recording gif", "images to gif", "photo sequence gif

Video downloading via yt-dlp with format selection, quality control, subtitle download, audio-only extraction, and playlist support. Downloads from YouTube, Vimeo, Twitter, TikTok, and 1000+ other sites. Use when user says "download video", "download from youtube", "yt-dlp", "grab video", "save video", "download audio", "download playlist", or provides a video URL to download.

Web screenshot capture for video production using Playwright. Takes full-page, viewport, or element-specific screenshots at video-native dimensions (1920x1080, 1080x1920). Device emulation (100+ presets), CSS injection to hide ads/banners, authentication persistence, Ken Burns zoom/pan animation from screenshots, browser session recording, and batch URL capture. Use when user says "screenshot", "w

Optimize GIF file size and quality. Multi-strategy optimization: gifsicle lossy compression, color reduction, dimension reduction, frame rate reduction, dithering changes. Platform auto-fit for Discord (256KB), Slack (500KB), Twitter (15MB), web (2MB). Use when user says "optimize gif", "reduce gif size", "compress gif", "gif too large", "fit discord", "fit slack", "gif file size", or "shrink gif"

Audio processing for video files using FFmpeg. Loudness normalization to streaming standards (LUFS), noise reduction, audio mixing, extraction, replacement, silence detection and removal, equalization, compression, fade effects, format conversion, and audio ducking. Use when user says "audio", "normalize", "volume", "loudness", "LUFS", "noise", "silence", "extract audio", "replace audio", "mix aud