Media Processing

Media Processing harnesses FFmpeg and ImageMagick to handle video, audio, and image workflows—from format conversion and codec selection to streaming manifest generation and batch optimization. Extract audio, generate thumbnails, apply filters, add watermarks, and leverage hardware acceleration for faster encoding.

FFmpeg Patterns provides ready-to-use command examples for video and audio tasks like transcoding to MP4 or WebM, extracting audio tracks, trimming clips, applying filters, merging media, generating thumbnails, and streaming formats. It covers hardware acceleration, batch operations, and practical probing commands.

This skill covers FFmpeg's position-sensitive command structure, explaining where global, input, and output options must appear and how their meaning shifts based on placement. It addresses stream specifiers, multi-input/output handling, and the critical behaviors of options like -ss, -t, -r, and -c that work differently before versus after -i.

Faceswap uses HeyGen's API to replace faces in videos by applying a source image onto target video content. Submit a source face photo and target video, then poll for completion as the AI processes the swap. Works with any video format and chains with other workflows for personalized video creation.

Mix Output Compression installs rtk filters that intercept mix test, credo, dialyzer, and compile output before it enters your transcript. The filters collapse successful runs to single lines while keeping all failures, errors, and stack traces intact, typically saving 5-15% of tokens per session.

Install rtk filters to compress verbose mix command output before it consumes context. The skill preserves critical signals like compile errors and test failures while short-circuiting successful runs to single lines, delivering 5-15% token savings on mix-heavy workflows.