A guide for using FFmpeg, an open-source command-line tool for converting, processing, streaming, and packaging audio and video. It covers encoding settings, hardware acceleration, filters, and batch automation.

Use it to transcode media, create HLS or DASH streams, apply filter chains, use NVIDIA, Intel, Apple, or VAAPI hardware acceleration, and automate batches with Python.

It helps turn complex media-processing tasks into repeatable commands and scripts, while diagnosing problems such as poor quality, slow encoding, or incompatible formats.

ffmpeg — Skill for Claude Code by alivirgo/Major-AI-Skills

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add alivirgo/Major-AI-Skills --skill ffmpeg

Clone the repo

git clone --depth 1 https://github.com/alivirgo/Major-AI-Skills

Made for: Claude Code.

Or install mas-video-lab, the plugin that ships this one along with the rest of its 7 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/ffmpeg/github.svg)](https://agentmods.dev/skills/alivirgo/major-ai-skills/ffmpeg)

Your own site

<a href="https://agentmods.dev/skills/alivirgo/major-ai-skills/ffmpeg"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/ffmpeg/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/alivirgo/major-ai-skills/ffmpeg"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/ffmpeg.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,350 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00035	$0.01350
Opus 5.5	$0.00014	$0.00540
Sonnet 5.5	$0.00007	$0.00270
Haiku 4.5	$0.00003	$0.00135

Measured 24d ago against content hash 42472e2401ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ffmpeg scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 24d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/mas-video-lab/skills/ffmpeg/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FFmpeg Media Engineering AI Skill Guide (Claude)

Overview & Engine Architecture

FFmpeg (pin 6.x / 7.x / 8.x — run ffmpeg -version in CI) is the standard CLI transcode graph: demux → decode → filter_complex → encode → mux. Claude acts as Principal Video Engineer: ffprobe-first, BT.709 tagging, HDR tone-map chains, ABR HLS, hardware encode with software fallback, deterministic frame counts for QA.

┌─────────────────────────────────────────────────────────────┐
│  ffprobe JSON  →  filtergraph  →  encode  →  verify tags    │
│  SDR web: yuv420p + bt709 metadata + faststart              │
│  HDR→SDR: zscale linear → tonemap → zscale bt709 (NOT colorspace alone) │
└─────────────────────────────────────────────────────────────┘

When to use / when not to

Use when: mezzanine → delivery transcodes, loudness normalize, HLS/DASH packaging, concat/remux, thumbnail/still extraction, batch folder processing.

Do not use when: NLE project semantics (use Resolve/Premiere skills); DRM packaging; proprietary camera RAW without documented decoder.

Operational Capabilities & Agent Directives

Probe before encode: ffprobe -show_streams -show_format -print_format json — record color_transfer, color_primaries, pix_fmt, VFR (avg_frame_rate vs r_frame_rate).
SDR deliverables: -pix_fmt yuv420p + -color_primaries bt709 -color_trc bt709 -colorspace bt709 -color_range tv on output; -movflags +faststart for MP4 web.
HDR PQ/HLG → SDR: colorspace filter cannot tone-map PQ; use zscale=t=linear:npl=100,format=gbrpf32le,zscale=p=bt709,tonemap=...,zscale=t=bt709:m=bt709:r=tv,format=yuv420p. If tags unknown, prefix setparams=color_primaries=bt2020:color_trc=smpte2084:colorspace=bt2020nc.
NVENC tags: Without explicit format=yuv420p or -pix_fmt yuv420p, NVENC may write wrong color_space (e.g. bt470bg) — always end filter chain with format=yuv420p (FFmpeg trac #11541).
Deterministic QA: For regression, use -frames:v N, fixed GOP (-g), -vsync cfr, -fflags +bitexact where applicable; avoid time-based -ss before -i vs after for frame-accurate tests.
VFR fix: -vf fps=30 or -vsync cfr; audio aresample=async=1:first_pts=0.
Batch: -progress pipe:1 for machine-parseable status; exit code = last ffmpeg in shell chain.

Read the full file on GitHub · 95 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

24d ago Changed · -67 lines 42472e2401ce
1mo ago Changed · -9 tokens per session 981721674026
1mo ago First seen · 162 lines · 44 tokens per session scan A 2b5b0bcd26e7

Subscribe to this mod's changes

ffmpeg is a skill published in the GitHub repository alivirgo/Major-AI-Skills (2 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 1,350 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Creative and media Deterministic agent-skills agentic-skills ai-agent-skills batch colorspace cross-platform ffmpeg ffprobe hdr hls nvenc

openscreen-demo

Make a polished video of an app or a feature with OpenScreen's MCP tools, from storyboard to recording, editing and export, then either attach it to a pull request or draft a post on X. Use when the user asks for a demo, a demo video, a screen recording, a product video, a launch clip, a video for X/Twitter, LinkedIn…

getopenscreen/openscreen · 130 tokens

openscreen-design

Use this skill to generate well-branded interfaces and assets for OpenScreen (an AI-native screen-recording studio & video editor), either for production or throwaway prototypes/mocks/etc. Contains essential design guidelines, colors, type, fonts, assets, and UI kit components for prototyping.

getopenscreen/openscreen · 62 tokens

ffmpeg

Use when converting, cutting, stitching or streaming video/audio from the command line — ffmpeg -i / -ss / -t, fps and scale filters, CRF and preset for H.264/H.265, -hwaccel decoding, hls muxer with hlstime and hlssegmentfilename, RTSP/UDP ingestion, frame extraction for textures. FFmpeg 9.0.2. Also for "moov atom…

znlgis/opengis-skills · 122 tokens

video-streaming-expert

Expert in video streaming technologies, HLS, DASH, adaptive bitrate streaming, CDN delivery, DRM protection, and video encoding/transcoding. Use when the user mentions video, streaming, media, WebRTC, multimedia, or HLS, or when the task involves Streaming Protocols, Adaptive Bitrate Streaming, FFmpeg Video…

personamanagmentlayer/pcl · 79 tokens

brand-assets-setup

Generate and deploy a complete brand asset pack for a Next.js App Router project. Scans the project, prints what to generate with exact specs, then imports and wires everything correctly.

JohnWayneeee/ai-agent-skills · 41 tokens

browser-audit

Run a pre-deploy browser audit of a live, preview, or local web page for accessibility, SEO, Lighthouse quality, and critical UX issues. Use when asked to audit a page/site before deployment, check WCAG 2.2 AA, WAI-ARIA, Lighthouse, accessibility, SEO, contrast, keyboard navigation, focus states, semantic HTML, forms…

JohnWayneeee/ai-agent-skills · 96 tokens

ffmpeg

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

FFmpeg Media Engineering AI Skill Guide (Claude)

Overview & Engine Architecture

When to use / when not to

Operational Capabilities & Agent Directives

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

openscreen-demo

openscreen-design

ffmpeg

video-streaming-expert

brand-assets-setup

browser-audit