media-processing

Process multimedia files with FFmpeg, ImageMagick, and RMBG for encoding, conversion, and background removal.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/tkhieu/peraichi-coding-agent-starter-kit --skill media-processing-tkhieu
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: media-processing
Source: https://github.com/tkhieu/peraichi-coding-agent-starter-kit/tree/main/.claude/skills/media-processing
Command: npx skills add https://github.com/tkhieu/peraichi-coding-agent-starter-kit --skill media-processing-tkhieu

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates heavy media workflows (video, audio, images) using FFmpeg, ImageMagick, RMBG, and batch processing techniques to save time and reduce manual toil.

Core Features & Use Cases

  • Video encoding/conversion with FFmpeg
  • Audio extraction/conversion and format management
  • Image resizing, batch processing via ImageMagick
  • Background removal using RMBG CLI with model selection
  • Thumbnails, sprites, and streaming prep for web delivery
  • Broad format support and hardware-accelerated workflows

Quick Start

Example: convert a batch of JPEGs to optimized WEBP images and remove backgrounds:

  • Use batch_resize.py for batch processing
  • Use batch-remove-background.sh to strip backgrounds
  • Reference workflows in references/common-workflows.md

Frequently Asked Questions about media-processing

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I batch convert video files to different codecs like H.264 or H.265?

Video encoding with FFmpeg supports H.264, H.265, VP9, and AV1 codecs across batch workflows. This Skill automates format conversion and hardware-accelerated encoding (NVENC, QSV, VCE) to process multiple files efficiently without manual codec configuration.

Can I remove backgrounds from images automatically in bulk?

Background removal using RMBG CLI strips backgrounds from batches of images with model selection. This Skill orchestrates RMBG-based processing across multiple files, eliminating manual per-image background extraction for web or design workflows.

What's the best way to prepare video and audio for streaming delivery?

Streaming preparation includes thumbnail generation, sprite creation, and HLS/DASH manifest generation alongside video encoding. This Skill automates the complete pipeline—format conversion, audio extraction, and streaming-ready output—end-to-end.

How do I resize and process large batches of images with ImageMagick?

Batch image resizing with ImageMagick handles multiple files simultaneously for composition and optimization tasks. This Skill provides documented workflows and scripts for processing image collections at scale without individual file handling.

Does FFmpeg support hardware acceleration for faster encoding?

Hardware acceleration via NVENC, QSV, and VCE/VCN codecs speeds video encoding significantly. This Skill includes documented hardware-accelerated workflows for supported GPUs and platforms, reducing encoding time for batch and pipeline scenarios.

Can I orchestrate video, audio, and image processing together in one workflow?

Cross-tool orchestration with FFmpeg, ImageMagick, and RMBG CLI processes multimedia end-to-end in unified pipelines. This Skill handles format conversions, audio extraction, image transforms, and background removal in coordinated batch or sequential workflows.