EasyPlatform media-processing

[AI & Tools] Use when processing multimedia files with FFmpeg (video/audio encoding, conversion, streaming), ImageMagick (image manipulation, batch processing), or RMBG (AI background removal). Covers format conversion, resizing, filtering, thumbnails, and media pipelines.

install
source · Clone the upstream repo
git clone https://github.com/duc01226/EasyPlatform
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/duc01226/EasyPlatform "$T" && mkdir -p ~/.claude/skills && cp -r "$T/.claude/skills/media-processing" ~/.claude/skills/duc01226-easyplatform-media-processing && rm -rf "$T"
manifest: .claude/skills/media-processing/SKILL.md
source content

[IMPORTANT] Use

TaskCreate
to break ALL work into small tasks BEFORE starting — including tasks for each file read. This prevents context loss from long files. For simple tasks, AI MUST ATTENTION ask user whether to skip.

<!-- SYNC:critical-thinking-mindset -->

Critical Thinking Mindset — Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence >80% to act. Anti-hallucination: Never present guess as fact — cite sources for every claim, admit uncertainty freely, self-check output for errors, cross-reference independently, stay skeptical of own confidence — certainty without evidence root of all hallucination.

<!-- /SYNC:critical-thinking-mindset --> <!-- SYNC:ai-mistake-prevention -->

AI Mistake Prevention — Failure modes to avoid on every task:

  • Check downstream references before deleting. Deleting components causes documentation and code staleness cascades. Map all referencing files before removal.
  • Verify AI-generated content against actual code. AI hallucinates APIs, class names, and method signatures. Always grep to confirm existence before documenting or referencing.
  • Trace full dependency chain after edits. Changing a definition misses downstream variables and consumers derived from it. Always trace the full chain.
  • Trace ALL code paths when verifying correctness. Confirming code exists is not confirming it executes. Always trace early exits, error branches, and conditional skips — not just happy path.
  • When debugging, ask "whose responsibility?" before fixing. Trace whether bug is in caller (wrong data) or callee (wrong handling). Fix at responsible layer — never patch symptom site.
  • Assume existing values are intentional — ask WHY before changing. Before changing any constant, limit, flag, or pattern: read comments, check git blame, examine surrounding code.
  • Verify ALL affected outputs, not just the first. Changes touching multiple stacks require verifying EVERY output. One green check is not all green checks.
  • Holistic-first debugging — resist nearest-attention trap. When investigating any failure, list EVERY precondition first (config, env vars, DB names, endpoints, DI registrations, data preconditions), then verify each against evidence before forming any code-layer hypothesis.
  • Surgical changes — apply the diff test. Bug fix: every changed line must trace directly to the bug. Don't restyle or improve adjacent code. Enhancement task: implement improvements AND announce them explicitly.
  • Surface ambiguity before coding — don't pick silently. If request has multiple interpretations, present each with effort estimate and ask. Never assume all-records, file-based, or more complex path.
<!-- /SYNC:ai-mistake-prevention -->

Quick Summary

Goal: Process multimedia files using FFmpeg for video/audio encoding, conversion, streaming, and filtering.

Workflow:

  1. Identify -- Match input to correct FFmpeg operation (convert, trim, merge, compress)
  2. Execute -- Run FFmpeg command with appropriate codec and quality settings
  3. Verify -- Check output file integrity and quality

Key Rules:

  • Use tool selection table to pick correct FFmpeg operation
  • Prefer hardware-accelerated encoding when available
  • Always verify output file exists and is playable

Be skeptical. Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence percentages (Idea should be more than 80%).

Media Processing Skill

Process video, audio, and images using FFmpeg, ImageMagick, and RMBG CLI tools.

Tool Selection

TaskToolReason
Video encoding/conversionFFmpegNative codec support, streaming
Audio extraction/conversionFFmpegDirect stream manipulation
Image resize/effectsImageMagickOptimized for still images
Background removalRMBGAI-powered, local processing
Batch imagesImageMagickmogrify for in-place edits
Video thumbnailsFFmpegFrame extraction built-in
GIF creationFFmpeg/ImageMagickFFmpeg for video, ImageMagick for images

Installation

# macOS
brew install ffmpeg imagemagick
npm install -g rmbg-cli

# Ubuntu/Debian
sudo apt-get install ffmpeg imagemagick
npm install -g rmbg-cli

# Verify
ffmpeg -version && magick -version && rmbg --version

Essential Commands

# Video: Convert/re-encode
ffmpeg -i input.mkv -c copy output.mp4
ffmpeg -i input.avi -c:v libx264 -crf 22 -c:a aac output.mp4

# Video: Extract audio
ffmpeg -i video.mp4 -vn -c:a copy audio.m4a

# Image: Convert/resize
magick input.png output.jpg
magick input.jpg -resize 800x600 output.jpg

# Image: Batch resize
mogrify -resize 800x -quality 85 *.jpg

# Background removal
rmbg input.jpg                          # Basic (modnet)
rmbg input.jpg -m briaai -o output.png  # High quality
rmbg input.jpg -m u2netp -o output.png  # Fast

Key Parameters

FFmpeg:

  • -c:v libx264
    - H.264 codec
  • -crf 22
    - Quality (0-51, lower=better)
  • -preset slow
    - Speed/compression balance
  • -c:a aac
    - Audio codec

ImageMagick:

  • 800x600
    - Fit within (maintains aspect)
  • 800x600^
    - Fill (may crop)
  • -quality 85
    - JPEG quality
  • -strip
    - Remove metadata

RMBG:

  • -m briaai
    - High quality model
  • -m u2netp
    - Fast model
  • -r 4096
    - Max resolution

References

Detailed guides in

references/
:

  • ffmpeg-encoding.md
    - Codecs, quality, hardware acceleration
  • ffmpeg-streaming.md
    - HLS/DASH, live streaming
  • ffmpeg-filters.md
    - Filters, complex filtergraphs
  • imagemagick-editing.md
    - Effects, transformations
  • imagemagick-batch.md
    - Batch processing, parallel ops
  • rmbg-background-removal.md
    - AI models, CLI usage
  • common-workflows.md
    - Video optimization, responsive images, GIF creation
  • troubleshooting.md
    - Error fixes, performance tips
  • format-compatibility.md
    - Format support, codec recommendations

Closing Reminders

  • MANDATORY IMPORTANT MUST ATTENTION break work into small todo tasks using
    TaskCreate
    BEFORE starting
  • MANDATORY IMPORTANT MUST ATTENTION search codebase for 3+ similar patterns before creating new code
  • MANDATORY IMPORTANT MUST ATTENTION cite
    file:line
    evidence for every claim (confidence >80% to act)
  • MANDATORY IMPORTANT MUST ATTENTION add a final review todo task to verify work quality <!-- SYNC:critical-thinking-mindset:reminder -->
  • MUST ATTENTION apply critical thinking — every claim needs traced proof, confidence >80% to act. Anti-hallucination: never present guess as fact. <!-- /SYNC:critical-thinking-mindset:reminder --> <!-- SYNC:ai-mistake-prevention:reminder -->
  • MUST ATTENTION apply AI mistake prevention — holistic-first debugging, fix at responsible layer, surface ambiguity before coding, re-read files after compaction. <!-- /SYNC:ai-mistake-prevention:reminder -->