Agent skill

Ffmpeg Core

by MadAppGang in MadAppGang/claude-code

FFmpeg fundamentals for video/audio manipulation. An agent skill from MadAppGang/claude-code.

MITAuto-check: notesMedia & Creative

Install Ffmpeg Core

skills CLI
$ npx skills add MadAppGang/claude-code --skill ffmpeg-core -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install MadAppGang/claude-code ffmpeg-core --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/MadAppGang/claude-code.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/video-editing/skills/ffmpeg-core .claude/skills/ffmpeg-core && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
ffmpeg-core
GitHub stars
285
Token cost
~1.4k tokens
SKILL.md length
171 words
Files
1
Skills in repo
69
Repo updated
First seen
Licence
MIT

At a glance

FFmpeg fundamentals for video/audio manipulation. An agent skill from MadAppGang/claude-code.

  • Works in 7 steps: Video Information → Trimming and Cutting → Concatenation → …
  • Executing video processing tasks
  • SKILL.md covers System Requirements, Common Operations Reference, Codec Selection Guide and ProRes Profiles (for FCP), plus 3 more sections
  • Calls ffmpeg, ffprobe and apt; reaches ffmpeg.org

What it does

Ffmpeg Core is an agent skill from MadAppGang/claude-code. FFmpeg fundamentals for video/audio manipulation. Covers common operations (trim, concat, convert, extract), codec selection, filter chains, and performance optimization. Use when planning or executing video processing tasks.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Media & Creative, covering Video production and Performance optimization. It works with FFmpeg. The repository describes itself as: claude code plugins marketplace. The licence is MIT.

When your agent uses it

  • Executing video processing tasks
  • Tasks that involve Video production
  • Tasks that involve Performance optimization

Example prompts

  • “/ffmpeg-core”

Workflow steps

7 steps, taken from the step headings in SKILL.md.

  1. Video Information
  2. Trimming and Cutting
  3. Concatenation
  4. Format Conversion
  5. Resolution and Scaling
  6. Audio Operations
  7. Video Effects and Filters

What it can do on your machine

Read from SKILL.md and the folder at commit 6097ad4. 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

    Shell commands in SKILL.md call:

    • ffmpeg
    • ffprobe
    • apt
    • brew
    • dnf
    • choco

    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:

    • 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

Ffmpeg Core loads about 1.4k tokens when it runs. Until then it costs about 59 tokens; SKILL.md has 171 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~59
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

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

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteRuns commands with sudoSKILL.md:27
    sudo apt update && sudo apt install ffmpeg
  • NoteRuns commands with sudoSKILL.md:32
    sudo dnf 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); files beside SKILL.md are not scanned.

SKILL.md

The full file from MadAppGang/claude-code at commit 6097ad4, republished under its MIT licence (© MadAppGang). 171 words, ~1,395 tokens.

Download SKILL.mdSave it as .claude/skills/ffmpeg-core/SKILL.md (or your agent's skills folder).
name
ffmpeg-core
description
FFmpeg fundamentals for video/audio manipulation. Covers common operations (trim, concat, convert, extract), codec selection, filter chains, and performance optimization. Use when planning or executing video processing tasks.

plugin: video-editing updated: 2026-01-20

FFmpeg Core Operations

Production-ready patterns for video and audio manipulation using FFmpeg.

System Requirements

  • FFmpeg (5.0+ recommended)
  • Verify installation: ffmpeg -version
  • For hardware acceleration: check ffmpeg -hwaccels
Cross-Platform Installation

macOS:

bash
brew install ffmpeg

Linux (Ubuntu/Debian):

bash
sudo apt update && sudo apt install ffmpeg

Linux (Fedora/RHEL):

bash
sudo dnf install ffmpeg

Windows:

bash
# Using Chocolatey
choco install ffmpeg

# Or download from https://ffmpeg.org/download.html

Common Operations Reference

1. Video Information

Extract metadata and stream information:

bash
# Get full metadata
ffprobe -v quiet -print_format json -show_format -show_streams "input.mp4"

# Get duration only
ffprobe -v error -show_entries format=duration -of default=noprint_wrappers=1:nokey=1 "input.mp4"

# Get resolution
ffprobe -v error -select_streams v:0 -show_entries stream=width,height -of csv=s=x:p=0 "input.mp4"
2. Trimming and Cutting
bash
# Trim by time (fast, no re-encoding)
ffmpeg -ss 00:01:30 -i input.mp4 -to 00:02:45 -c copy output.mp4

# Trim with re-encoding (frame-accurate)
ffmpeg -ss 00:01:30 -i input.mp4 -to 00:02:45 -c:v libx264 -c:a aac output.mp4

# Extract specific segment by frames
ffmpeg -i input.mp4 -vf "select=between(n\,100\,500)" -vsync vfr output.mp4
3. Concatenation
bash
# Using concat demuxer (same codecs required)
# First create file list:
# file 'clip1.mp4'
# file 'clip2.mp4'
# file 'clip3.mp4'

ffmpeg -f concat -safe 0 -i filelist.txt -c copy output.mp4

# Using concat filter (different codecs, re-encodes)
ffmpeg -i clip1.mp4 -i clip2.mp4 -filter_complex "[0:v][0:a][1:v][1:a]concat=n=2:v=1:a=1" output.mp4
4. Format Conversion
bash
# MP4 to MOV (ProRes for FCP)
ffmpeg -i input.mp4 -c:v prores_ks -profile:v 3 -c:a pcm_s16le output.mov

# Any to H.264 MP4 (web-friendly)
ffmpeg -i input.avi -c:v libx264 -preset medium -crf 23 -c:a aac -b:a 128k output.mp4

# Extract audio only
ffmpeg -i video.mp4 -vn -c:a libmp3lame -q:a 2 audio.mp3
ffmpeg -i video.mp4 -vn -c:a pcm_s16le audio.wav
5. Resolution and Scaling
bash
# Scale to specific resolution
ffmpeg -i input.mp4 -vf "scale=1920:1080" output.mp4

# Scale maintaining aspect ratio
ffmpeg -i input.mp4 -vf "scale=1920:-1" output.mp4

# Scale to fit within bounds
ffmpeg -i input.mp4 -vf "scale='min(1920,iw)':min'(1080,ih)':force_original_aspect_ratio=decrease" output.mp4
6. Audio Operations
bash
# Adjust volume
ffmpeg -i input.mp4 -af "volume=1.5" output.mp4

# Normalize audio (loudnorm)
ffmpeg -i input.mp4 -af loudnorm=I=-16:TP=-1.5:LRA=11 output.mp4

# Mix audio tracks
ffmpeg -i video.mp4 -i audio.mp3 -filter_complex "[0:a][1:a]amerge=inputs=2" -c:v copy output.mp4

# Replace audio
ffmpeg -i video.mp4 -i new_audio.mp3 -c:v copy -map 0:v:0 -map 1:a:0 output.mp4
7. Video Effects and Filters
bash
# Fade in/out
ffmpeg -i input.mp4 -vf "fade=t=in:st=0:d=1,fade=t=out:st=9:d=1" output.mp4

# Speed adjustment (2x faster)
ffmpeg -i input.mp4 -filter_complex "[0:v]setpts=0.5*PTS[v];[0:a]atempo=2.0[a]" -map "[v]" -map "[a]" output.mp4

# Add text overlay
ffmpeg -i input.mp4 -vf "drawtext=text='Title':fontsize=48:fontcolor=white:x=(w-text_w)/2:y=50" output.mp4

# Color correction
ffmpeg -i input.mp4 -vf "eq=brightness=0.1:saturation=1.2:contrast=1.1" output.mp4

Codec Selection Guide

Use CaseVideo CodecAudio CodecContainer
Web deliverylibx264/libx265aacmp4
Final Cut Proprores_kspcm_s16lemov
Archive/losslessffv1flacmkv
Quick previewlibx264 -preset ultrafastaacmp4
Social medialibx264 -crf 20aac -b:a 192kmp4

ProRes Profiles (for FCP)

ProfileFlagQualityUse Case
Proxy-profile:v 0LowOffline editing
LT-profile:v 1MediumLight grading
Standard-profile:v 2HighGeneral editing
HQ-profile:v 3Very HighFinal delivery
4444-profile:v 4HighestVFX/compositing

Performance Optimization

bash
# Use hardware acceleration (macOS)
ffmpeg -hwaccel videotoolbox -i input.mp4 -c:v h264_videotoolbox output.mp4

# Use hardware acceleration (Linux with NVIDIA)
ffmpeg -hwaccel cuda -i input.mp4 -c:v h264_nvenc output.mp4

# Parallel processing
ffmpeg -i input.mp4 -threads 0 output.mp4

# Limit memory usage
ffmpeg -i input.mp4 -max_muxing_queue_size 1024 output.mp4

Error Handling Patterns

bash
# Check if file is valid video
ffprobe -v error -select_streams v:0 -show_entries stream=codec_type -of csv=p=0 "file.mp4" 2>/dev/null
# Returns "video" if valid

# Validate output after processing
validate_video() {
  local file="$1"
  if ffprobe -v error -select_streams v:0 -show_entries stream=codec_type -of csv=p=0 "$file" 2>/dev/null | grep -q "video"; then
    echo "Valid"
    return 0
  else
    echo "Invalid or missing video stream"
    return 1
  fi
}
  • transcription - Extract audio for Whisper processing
  • final-cut-pro - Convert processed clips for FCP timelines

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

Files

Just SKILL.md in plugins/video-editing/skills/ffmpeg-core of MadAppGang/claude-code.

Open the folder on GitHubat commit 6097ad4

Compare with similar skills

Ffmpeg Core next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Ffmpeg Core compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ffmpeg Core this skillMadAppGang/claude-code285—~1.4kAutomated safety check: NotesMIT
Video Understandcalesthio/OpenMontage66k—~841Automated safety check: PassAGPL-3.0
HyperFrames Video Entry Pointheygen-com/hyperframes59k3 repos~5.2kAutomated safety check: PassApache-2.0
Video Shotseternityspring/reelbench-skills8721 repos~1.8kAutomated safety check: NotesApache-2.0
Mobile Demo Film Editorsuperset-sh/superset15k—~1.8kAutomated safety check: PassCustom licence
Video Editcalesthio/OpenMontage66k—~855Automated safety check: NotesAGPL-3.0

Similar skills

  • Video Understand

    calesthio/OpenMontage

    Understand video content locally using ffmpeg frame extraction and Whisper transcription.

    66k GitHub stars~841 tokensUpdated 6 days ago
    Media & CreativeAuto-check passed
  • HyperFrames Video Entry Point

    heygen-com/hyperframes

    Entry point for making, editing and rendering videos from HTML compositions with HyperFrames, routing each request to the right workflow.

    59k GitHub starsUsed in 3 repos~5.2k tokens
    Media & CreativeAuto-check passed
  • Video Shots

    eternityspring/reelbench-skills

    拉片:把一条成片拆成逐镜头的分析表——每个镜头的时长、景别、类别、运镜、画面. An agent skill from eternityspring/reelbench-skills.

    872 GitHub starsUsed in 1 repo~1.8k tokens
    Media & CreativeAuto-check: notes
  • Mobile Demo Film Editor

    superset-sh/superset

    Edits real mobile screen recordings into a configurable demo video with phone framing, title cards, cutaways and an end card, using a bundled renderer.

    15k GitHub stars~1.8k tokensUpdated today
    Media & CreativeAuto-check passed
  • Video Edit

    calesthio/OpenMontage

    Edit videos locally using ffmpeg. An agent skill from calesthio/OpenMontage.

    66k GitHub stars~855 tokensUpdated 6 days ago
    Media & CreativeAuto-check: notes
  • Lemo-Opuscar Short Film Director

    lemomo-ai/lemo-opuscar

    Directs a short film made entirely in code in one of the Lemo-Opuscar library's named visual styles, from fetching the library through production and delivery.

    1.4k GitHub stars~596 tokensUpdated yesterday
    Media & CreativeAuto-check passed

More from MadAppGang/claude-code

All 69 skills in this repo
  • Content Brief

    MadAppGang/claude-code

    Content brief template and creation methodology for SEO-optimized content.

    285 GitHub starsUsed in 1 repo~959 tokens
    Auto-check passed
  • Context Detection

    MadAppGang/claude-code

    A skill your agent uses when detecting project technology stack from files/configs/directory structure, auto-loading framework-specific skills, or analyzing multi-stack fullstack projects (e.g…

    285 GitHub stars~5.4k tokensUpdated 6 mo ago
    Auto-check passed
  • Content Optimizer

    MadAppGang/claude-code

    On-page SEO optimization techniques including keyword density, meta tags, heading structure, and readability.

    285 GitHub starsUsed in 1 repo~694 tokens
    Auto-check passed
  • Keyword Cluster Builder

    MadAppGang/claude-code

    Techniques for expanding seed keywords and clustering by topic and intent.

    285 GitHub starsUsed in 1 repo~674 tokens
    Auto-check passed
  • Serp Analysis

    MadAppGang/claude-code

    SERP analysis techniques for intent classification, feature identification, and competitive intelligence.

    285 GitHub starsUsed in 1 repo~1k tokens
    Auto-check passed
  • Agent Coordination Discipline

    MadAppGang/claude-code

    A skill your agent uses when deciding whether to launch an agent, selecting which agent to use, or coordinating multiple agents.

    285 GitHub stars~3.8k tokensUpdated 6 mo ago
    Auto-check passed

Works with

Questions about Ffmpeg Core

What does Ffmpeg Core do?

FFmpeg fundamentals for video/audio manipulation. An agent skill from MadAppGang/claude-code. Ffmpeg Core is an agent skill from MadAppGang/claude-code. FFmpeg fundamentals for video/audio manipulation.

When should I use Ffmpeg Core?

Ffmpeg Core fits situations like: executing video processing tasks; tasks that involve Video production; tasks that involve Performance optimization.

How do I install Ffmpeg Core in Claude Code?

Run `npx skills add MadAppGang/claude-code --skill ffmpeg-core -a claude-code`. Or copy the skill folder (plugins/video-editing/skills/ffmpeg-core in MadAppGang/claude-code) into .claude/skills/ffmpeg-core in your project. Claude Code loads it when a task matches its description.

How do I install Ffmpeg Core in Codex?

Run `npx skills add MadAppGang/claude-code --skill ffmpeg-core -a codex`. Or copy the skill folder (plugins/video-editing/skills/ffmpeg-core in MadAppGang/claude-code) into .agents/skills/ffmpeg-core in your project. Codex loads it when a task matches its description.

Can I use Ffmpeg Core in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add MadAppGang/claude-code --skill ffmpeg-core -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ffmpeg-core, .gemini/skills/ffmpeg-core, .github/skills/ffmpeg-core and .opencode/skills/ffmpeg-core in your project.

What does Ffmpeg Core need to run?

Going by SKILL.md and its folder, Ffmpeg Core needs the command-line tools its instructions call (ffmpeg, ffprobe, apt, brew, dnf and choco).

Does Ffmpeg Core access the network?

SKILL.md names 1 domain. In commands or code: ffmpeg.org; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Ffmpeg Core safe to install?

Our automated static check of SKILL.md found notes only (runs commands with sudo), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Ffmpeg Core use?

Ffmpeg Core is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Ffmpeg Core use?

About 1.4k tokens (SKILL.md is roughly 5.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Ffmpeg Core?

Skills that share tags, products or a category with Ffmpeg Core: Video Understand (calesthio/OpenMontage, 66k stars), HyperFrames Video Entry Point (heygen-com/hyperframes, 59k stars), Video Shots (eternityspring/reelbench-skills, 872 stars) and Mobile Demo Film Editor (superset-sh/superset, 15k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ffmpeg Core?

MadAppGang (a GitHub organization) maintains it in MadAppGang/claude-code, which has 285 GitHub stars. The repository holds 69 skills in this directory. The repository was last updated on March 15, 2026.

Source: MadAppGang/claude-code on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.