Video Processing

What it does

When your agent uses it

• : compressing videos for upload
• Extracting audio from video
• Resizing for social formats
• Clipping segments

Example prompts

• “/video-processing”

Requirements

• Python 3

Workflow steps

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

1. 1GPU acceleration - FFmpeg uses hardware encoding when available (NVENC, VideoToolbox)
2. 2CRF values - Lower = better quality, larger file. 18-28 typical range
3. 3Preset selection - ultrafast for drafts, slow for final exports
4. 4Two-pass encoding - Better quality for target bitrate

What it can do on your machine

Read from SKILL.md and the folder at commit 4108f5c. 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 2 files in scripts/ (Python), which the agent can run.

  Shell commands in SKILL.md call:

  • python
  • pip

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

• Network

  No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.

  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

Video Processing loads about 1.3k tokens when it runs. Until then it costs about 56 tokens; SKILL.md has 293 words of instructions outside code blocks.

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

~56

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

~1.3k

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:40

  # Ubuntu: sudo apt install ffmpeg

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 guia-matthieu/clawfu-skills at commit 4108f5c, republished under its MIT licence (© guia-matthieu). 293 words, ~1,311 tokens.

name

video-processing

description

Process video files with ffmpeg automation. Use when: compressing videos for upload; extracting audio from video; resizing for social formats; clipping segments; merging multiple videos; generating thumbnails

license

MIT

metadata.author

ClawFu

metadata.version

1.0.0

metadata.mcp-server

@clawfu/mcp-skills

pip install ffmpeg-python moviepy click
# Also requires ffmpeg installed on system
# macOS: brew install ffmpeg
# Ubuntu: sudo apt install ffmpeg

python scripts/main.py compress video.mp4 --target-mb 10
python scripts/main.py compress video.mp4 --crf 28 --output compressed.mp4

python scripts/main.py extract-audio video.mp4 --format mp3
python scripts/main.py extract-audio video.mp4 --format wav --output audio.wav

python scripts/main.py resize video.mp4 --format instagram  # 1080x1920 (9:16)
python scripts/main.py resize video.mp4 --format youtube    # 1920x1080 (16:9)
python scripts/main.py resize video.mp4 --format square     # 1080x1080 (1:1)
python scripts/main.py resize video.mp4 --width 1280 --height 720

python scripts/main.py clip video.mp4 --start 00:30 --end 01:45
python scripts/main.py clip video.mp4 --start 00:30 --duration 60

python scripts/main.py concat video1.mp4 video2.mp4 --output merged.mp4
python scripts/main.py concat ./clips/ --output compilation.mp4

python scripts/main.py thumbnail video.mp4 --time 00:30
python scripts/main.py thumbnail video.mp4 --best  # Auto-select best frame

# Original: 4K horizontal video, 500MB
python scripts/main.py resize long-video.mp4 --format instagram
python scripts/main.py compress long-video_instagram.mp4 --target-mb 50

# Output: long-video_instagram_compressed.mp4 (1080x1920, <50MB)

# Extract audio track
python scripts/main.py extract-audio webinar-recording.mp4 --format mp3 --bitrate 192k

# Output: webinar-recording.mp3 (ready for podcast hosting)

# Extract multiple clips
python scripts/main.py clip interview.mp4 --start 05:30 --end 06:15 --output clip1.mp4
python scripts/main.py clip interview.mp4 --start 12:00 --end 12:45 --output clip2.mp4
python scripts/main.py clip interview.mp4 --start 28:30 --end 29:00 --output clip3.mp4

# Merge into highlight reel
python scripts/main.py concat clip1.mp4 clip2.mp4 clip3.mp4 --output highlights.mp4

category: automation
subcategory: video-processing
dependencies: [ffmpeg-python, moviepy]
difficulty: beginner
time_saved: 5+ hours/week

© guia-matthieu, 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 2 other files (scripts) in skills/automation/video-processing of guia-matthieu/clawfu-skills.

• SKILL.md
• scripts/main.py
• scripts/requirements.txt

Open the folder on GitHubat commit 4108f5c