Media Processing

What it does

When your agent uses it

• : converting video/audio formats
• Encoding with specific codecs
• Generating thumbnails
• Creating streaming manifests

Example prompts

• “/media-processing”

Requirements

• Python 3

Workflow steps

10 steps, taken from the first numbered list in SKILL.md.

1. 1Use CRF for quality control - Better than bitrate for video
2. 2Copy streams when possible - Avoid re-encoding with -c copy
3. 3Hardware acceleration - GPU encoding 5-10x faster
4. 4Appropriate presets - Balance speed vs compression
5. 5Batch with mogrify - In-place image processing
6. 6Strip metadata - Reduce file size with -strip
7. 7Progressive JPEG - Better web loading with -interlace Plane
8. 8Limit memory - Prevent crashes on large batches
9. 9Test on samples - Verify settings before batch
10. 10Parallel processing - Use GNU Parallel for multiple files

What it can do on your machine

Read from SKILL.md and the folder at commit d167b41. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 8 files in scripts/ (Python), which the agent can run.

  Shell commands in SKILL.md call:

  • ffmpeg
  • magick
  • ffprobe
  • apt-get
  • winget
  • brew

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • imagemagick.org
  • ffmpeg.org

  Also links to:

  • trac.ffmpeg.org

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Media Processing loads about 2.4k tokens when it runs, and up to ~19k if it reads all its reference files. Until then it costs about 216 tokens; SKILL.md has 505 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~216

When it runs · the whole SKILL.md, loaded when a task matches

~2.4k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~19k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NoteRuns commands with sudoSKILL.md:71

  sudo apt-get install ffmpeg imagemagick

• NoteRuns commands with sudoSKILL.md:335

  sudo apt-get install libx264-dev libx265-dev

• NoteRuns commands with sudoSKILL.md:341

  sudo nano /etc/ImageMagick-7/policy.xml

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from nicepkg/ai-workflow at commit d167b41, republished under its MIT licence (© nicepkg). 505 words, ~2,443 tokens.

name

media-processing

description

Video/audio/image processing with FFmpeg and ImageMagick. Tools: FFmpeg (video/audio), ImageMagick (images). Capabilities: format conversion, encoding (H.264/H.265/VP9/AV1), streaming (HLS/DASH), filters, effects, thumbnails, watermarks, batch processing, hardware acceleration (NVENC/QSV). Actions: convert, encode, resize, crop, compress, extract, merge, stream, transcode media. Keywords: FFmpeg, ImageMagick, video encoding, audio extraction, image resize, thumbnail, watermark, HLS, DASH, H.264, H.265, VP9, AV1, codec, bitrate, framerate, resolution, aspect ratio, filter, overlay, concat, trim, fade, batch processing. Use when: converting video/audio formats, encoding with specific codecs, generating thumbnails, creating streaming manifests, extracting audio from video, batch processing images, adding watermarks, optimizing file sizes.

license

MIT

brew install ffmpeg imagemagick

sudo apt-get install ffmpeg imagemagick

# Using winget
winget install ffmpeg
winget install ImageMagick.ImageMagick

# Or download binaries
# FFmpeg: https://ffmpeg.org/download.html
# ImageMagick: https://imagemagick.org/script/download.php

ffmpeg -version
ffprobe -version
magick -version
# or
convert -version

# Convert format (copy streams, fast)
ffmpeg -i input.mkv -c copy output.mp4

# Re-encode with H.264
ffmpeg -i input.avi -c:v libx264 -crf 22 -c:a aac output.mp4

# Resize video to 720p
ffmpeg -i input.mp4 -vf scale=-1:720 -c:a copy output.mp4

# Extract audio (no re-encoding)
ffmpeg -i video.mp4 -vn -c:a copy audio.m4a

# Convert to MP3
ffmpeg -i video.mp4 -vn -q:a 0 audio.mp3

# Convert format
magick input.png output.jpg

# Resize maintaining aspect ratio
magick input.jpg -resize 800x600 output.jpg

# Create square thumbnail
magick input.jpg -resize 200x200^ -gravity center -extent 200x200 thumb.jpg

# Resize all JPEGs to 800px width
mogrify -resize 800x -quality 85 *.jpg

# Output to separate directory
mogrify -path ./output -resize 800x600 *.jpg

# Extract frame at 5 seconds
ffmpeg -ss 00:00:05 -i video.mp4 -vframes 1 -vf scale=320:-1 thumb.jpg

# Generate HLS playlist
ffmpeg -i input.mp4 \
  -c:v libx264 -preset fast -crf 22 -g 48 \
  -c:a aac -b:a 128k \
  -f hls -hls_time 6 -hls_playlist_type vod \
  playlist.m3u8

# Add watermark to corner
magick input.jpg watermark.png -gravity southeast \
  -geometry +10+10 -composite output.jpg

# H.264 with good compression
ffmpeg -i input.mp4 \
  -c:v libx264 -preset slow -crf 23 \
  -c:a aac -b:a 128k \
  -movflags +faststart \
  output.mp4

# Generate multiple sizes
for size in 320 640 1024 1920; do
  magick input.jpg -resize ${size}x -quality 85 "output-${size}w.jpg"
done

# From 1:30 to 3:00 (re-encode for precision)
ffmpeg -i input.mp4 -ss 00:01:30 -to 00:03:00 \
  -c:v libx264 -c:a aac output.mp4

# Convert PNG to optimized JPEG
mogrify -path ./optimized -format jpg -quality 85 -strip *.png

# High quality GIF with palette
ffmpeg -i input.mp4 -vf "fps=15,scale=640:-1:flags=lanczos,split[s0][s1];[s0]palettegen[p];[s1][p]paletteuse" output.gif

# Gaussian blur
magick input.jpg -gaussian-blur 0x8 output.jpg

# Pass 1 (analysis)
ffmpeg -y -i input.mkv -c:v libx264 -b:v 2600k -pass 1 -an -f null /dev/null

# Pass 2 (encoding)
ffmpeg -i input.mkv -c:v libx264 -b:v 2600k -pass 2 -c:a aac output.mp4

# NVIDIA NVENC
ffmpeg -hwaccel cuda -i input.mp4 -c:v h264_nvenc -preset fast -crf 22 output.mp4

# Intel QuickSync
ffmpeg -hwaccel qsv -c:v h264_qsv -i input.mp4 -c:v h264_qsv output.mp4

# Resize, crop, border, adjust
magick input.jpg \
  -resize 1000x1000^ \
  -gravity center \
  -crop 1000x1000+0+0 +repage \
  -bordercolor black -border 5x5 \
  -brightness-contrast 5x10 \
  -quality 90 \
  output.jpg

# Scale, denoise, watermark
ffmpeg -i video.mp4 -i logo.png \
  -filter_complex "[0:v]scale=1280:720,hqdn3d[v];[v][1:v]overlay=10:10" \
  -c:a copy output.mp4

# Create with delay
magick -delay 100 -loop 0 frame*.png animated.gif

# Optimize size
magick animated.gif -fuzz 5% -layers Optimize optimized.gif

# Detailed JSON output
ffprobe -v quiet -print_format json -show_format -show_streams input.mp4

# Get resolution
ffprobe -v error -select_streams v:0 \
  -show_entries stream=width,height \
  -of csv=s=x:p=0 input.mp4

# Basic info
identify image.jpg

# Detailed format
identify -verbose image.jpg

# Custom format
identify -format "%f: %wx%h %b\n" image.jpg

# Check available encoders
ffmpeg -encoders | grep h264

# Install codec libraries
sudo apt-get install libx264-dev libx265-dev

# Edit policy file
sudo nano /etc/ImageMagick-7/policy.xml
# Change <policy domain="coder" rights="none" pattern="PDF" />
# to <policy domain="coder" rights="read|write" pattern="PDF" />

# Limit memory usage
ffmpeg -threads 4 input.mp4 output.mp4
magick -limit memory 2GB -limit map 4GB input.jpg output.jpg

© nicepkg, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 14 other files (scripts, references) in workflows/video-creator-workflow/.claude/skills/media-processing of nicepkg/ai-workflow.

• SKILL.md
• references/ffmpeg-encoding.md
• references/ffmpeg-filters.md
• references/ffmpeg-streaming.md
• references/format-compatibility.md
• references/imagemagick-batch.md
• references/imagemagick-editing.md
• scripts/batch_resize.py
• scripts/media_convert.py
• scripts/requirements.txt
• scripts/tests/requirements.txt
• scripts/tests/test_batch_resize.py
• scripts/tests/test_media_convert.py
• scripts/tests/test_video_optimize.py
• scripts/video_optimize.py

Open the folder on GitHubat commit d167b41