explainx.ai350K+ learn from us
TrendingAI News TodayPathwaysSkills
Pricing
explainx.ai

Upskill in AI — 16 free pathways, live workshops & bootcamps, and 50+ courses from practitioners. Plus the skills, tools, and MCP servers to practice on.

follow us

follow on google

Add explainx.ai as a preferred source

corporate training

support@explainx.ai

get started

Find your pathTake Free Evaluation

community

Join the community

learn

mind: share how you thinkpathways — start freeworkshopsbootcampscoursescompare Explainxcertificationsmock testsexplainx universitycorporate traininglearn skills & mcp

discover

skillsmcp serversexplainx mcpestacktoolsmdx readeragentsllmsdesignsdictionarypeopleagi trackerfelony benchranks

company

aboutvisionmissionteaminstructorsteach on explainxpartnershipscommunityhackathonscareers

content

daily AI newsstate of AI — live resultsblogreleasespromptsgeneratorsresource libraryfor LLMsexplainx.ai kids

solutions

all solutionsdeveloper upskillingmarketing upskillingproduct manager upskillingleadership upskilling

newsletter · weekly

Get AI news, tools, and insights in your inbox.

supportcontactprivacytermsdata rightshow we create contentsubmission guidelines

© 2026 AISOLO Technologies Pvt Ltd

explainx.ai

On this page

  • TL;DR
  • Why agents need a video skill — not raw FFmpeg
  • Quick start
  • Workflow the skill enforces
  • Tool surface (selected)
  • MCP integration
  • Ecosystem note (optional brain layer)
  • Security and privacy
  • Compared to cinecode and Cursor FFmpeg credits
  • Caption, karaoke, and accessibility workflows
  • Cost comparison versus cloud video APIs
  • When to adopt
  • Platform export templates explained
  • Silent removal, fillers, and podcast cleanup
  • Multicam, sync drift, and HDR
  • Batch folders and CI
  • SPEC contract discipline
  • Installing across Claude Code, Cursor, and Codex
  • Related reading
← Back to blog

explainx / blog

ffmpeg-skill: Local Video Editing MCP for Claude Code, Cursor and Codex

FFmpeg, Coding Agents, MCP, Open Source, Guides

Part of AI Coding Tools

kajisho5/ffmpeg-skill adds 42 probe-verify FFmpeg scripts plus MCP for agents. Install with npx, no cloud keys, and how it differs from cinecode.

Nov 16, 2026·8 min read·Yash Thakker
add explainx.ai
go deep
ffmpeg-skill: Local Video Editing MCP for Claude Code, Cursor and Codex

ffmpeg-skill gives coding agents a local video department: 42 FFmpeg-backed Python tools, an MCP server, and a probe-edit-verify discipline — with no cloud upload and no API keys. The kajisho5/ffmpeg-skill repository listed 6,158 GitHub stars when we fetched it on November 16, 2026.

If you already use cinecode for generative films, think of ffmpeg-skill as the operator bench for real footage: cuts, captions, loudness, reframes, and TikTok or YouTube export presets agents can verify before they say "done."

Daily briefFrom Yash · 350K+ students taught

Catch up on AI

One AI story explained in plain English, plus one thing to try. Every day, free. Unsubscribe anytime.

TL;DR

table · 2 cols
PieceWhat it does
SKILL.mdMaps user requests → scripts; enforces probe → edit → verify reporting
42 toolscut, join, captions, loudness, scenes, render templates, batch, etc.
contract --jsonSchemas generated from argparse — CI blocks drift
MCPmcp/server.py exposes tools/list derived from contract
Installnpx ffmpeg-skill (+ --cursor, --codex, or --all)

Why agents need a video skill — not raw FFmpeg

Agents that "know FFmpeg" still hallucinate frame rates, pick codecs containers reject, and re-encode when stream copy would work. ffmpeg-skill's README states the fix plainly: probe first, structured tools, contract, verification.

That mirrors Plannotator's human-in-the-loop review for plans, but for pixels and loudness.

The author documents the design in a Zenodo position paper (DOI 10.5281/zenodo.23720216) and notes the skill does not yet fully meet its own verification ideal — honest scope for adopters.

Quick start

Prerequisites: ffmpeg on PATH (README shows sudo apt install ffmpeg on Debian).

bash
npx ffmpeg-skill
npx ffmpeg-skill doctor
npx ffmpeg-skill contract --json | head -40

Re-run npx ffmpeg-skill to refresh ~/.claude/skills/ffmpeg-skill; copies do not auto-update.

Optional captions from speech need a local ASR (pip install faster-whisper is the simplest path per README). Audio never uploads; models download on first run.

Workflow the skill enforces

Cream scissors trim a short green section from a filmstrip — the probe-then-cut loop ffmpeg-skill asks agents to followCream scissors trim a short green section from a filmstrip — the probe-then-cut loop ffmpeg-skill asks agents to follow

  1. probe.py — duration, fps, HDR, rotation, audio layout.
  2. Edit tools — prefer lossless stream copy when filters are not required (cut.py, parts of loudness.py).
  3. --dry-run / --plan — print ffmpeg lines or save a fingerprinted plan for render.py.
  4. Verify — probe output, check.py against platform specs, look.py contact sheets when pixels change.

Agents must end reports with Done: or Failed: per SKILL rules — no invented partial states.

Tool surface (selected)

The README groups 42 public tools. Highlights for builders:

table · 2 cols
CategoryExamples
Analysisprobe.py, scenes.py (cuts, peaks, beats — ranking is proxy-based, not semantic)
Editingcut.py, join.py, silence.py, fit.py, reframe.py
Captionscaption.py with karaoke and animation modes
Deliveryexport.py presets, `render.py --template tiktok
Audioloudness.py (-14 LUFS targets), noise reduction, dynamics
QCcheck.py --platform, metadata.py, verify.py orchestration

render.py can emit a multi-platform pack (--template all) — useful for shorts workflows next to Seedance video APIs where you still need mechanical compliance (loudness, aspect, safe zones).

MCP integration

A tower with a green beacon linked to small boxes — how MCP exposes ffmpeg-skill tools to Claude Code, Cursor and CodexA tower with a green beacon linked to small boxes — how MCP exposes ffmpeg-skill tools to Claude Code, Cursor and Codex

mcp/server.py implements JSON-RPC stdio. tools/list schemas are generated at startup from argparse, so new flags cannot desync MCP silently — a regression test copies the repo and mutates scripts to prove it.

Default tools/list exposes 12 core tools to protect context windows. Set FFMPEG_SKILL_MCP_FULL=1 to advertise all 42.

Same pattern as Google Stitch Skills MCP: contract-first, host-agnostic.

Ecosystem note (optional brain layer)

The README positions ffmpeg-skill as "hands" in kajisho5's wider video stack — video-production-agent and remotion-ffmpeg-skill sit above as planners. This repo does not call upstream; dependency is one-way. Standalone adopters can ignore the ecosystem block.

Security and privacy

  • Local-only video — good for NDA footage and pre-release game capture unlike cloud editors.
  • ASR models download from Hugging Face or whisper.cpp hosts on first transcribe — air-gap if needed.
  • No shell injection — tools use typed argparse, not arbitrary filter strings from the model.

For agent misuse (destructive batch deletes), combine with human approval workflows — the skill verifies technical output, not editorial intent.

Compared to cinecode and Cursor FFmpeg credits

table · 2 cols
ToolBest for
ffmpeg-skillOperator edits on existing video inside agent sessions
cinecodeProcedural films from code
Cursor FFmpeg creditsSponsorship for upstream FFmpeg devs, not agent tooling

Caption, karaoke, and accessibility workflows

caption.py burns user-supplied cue text — the README promises it never rewrites lines to fit timing. That is important for legal and marketing review: agents cannot silently soften claims in supers.

Animation modes (--animate pop, karaoke styles in README demos) pair with fit.py --aspect 9:16 for vertical social delivery. When captions must meet WCAG contrast, run look.py and inspect PNGs yourself; the skill does not auto-score contrast ratios.

For multilingual pipelines, feed SRT or VTT you already audited; optional --transcribe stays on-device with faster-whisper or parakeet-mlx per README install lines.

Cost comparison versus cloud video APIs

Cloud editors charge per minute rendered and often retain content on their servers. ffmpeg-skill's economic model is cap-ex on CPU you already own:

  • Pros — predictable cost at scale, NDA-safe footage, scriptable QC.
  • Cons — you maintain ffmpeg builds, ASR models, and agent guardrails.

If your product mixes generative inserts and human A-roll, use generative APIs for B-roll only, then pass through ffmpeg-skill for loudness, captions, and platform compliance — the division of labor cinecode and ffmpeg-skill were designed for.

When to adopt

Adopt ffmpeg-skill if your agent routinely:

  • Produces Shorts/Reels variants from one master clip.
  • Needs LUFS normalization before upload.
  • Must prove 9:16 reframes with contact sheets.
  • Runs offline on laptops without GPU video APIs.

Skip it if you only need generative video — use fal or BytePlus video models instead.

Platform export templates explained

render.py --list-templates advertises presets such as tiktok, reels, shorts, youtube-shorts, youtube, x, linkedin, facebook, podcast, and audiogram. Each JSON template encodes:

  • Target aspect ratio (for example 9:16 crop with safe zones)
  • Caption placement above platform chrome (TikTok description bar called out in README demos)
  • Loudness targets (for example −14 LUFS integrated)
  • check.py --platform validation after render

The README's demo gallery (npm run demo) rebuilds before/after frames via python3 demos/build.py, using synthetic FFmpeg sources — proof the scripts are reproducible, not cherry-picked stills.

table · 2 cols
Platform presetTypical agent task
tiktok / reels / shortsCrop talking-head to vertical, pop captions
youtube16:9 deliverable with broadcast safe guides in look.py
podcast / audiogramAudio-first exports when video is static waveform
linkedin / x / facebookCorporate talking clips with conservative loudness

Pair exports with Seedance-generated B-roll only after you probe generative files — AI video often ships variable frame rate or odd color tags probe.py must measure.

Silent removal, fillers, and podcast cleanup

silence.py removes dead air; with --transcribe it can align cuts to speech (optional local ASR). --filler modes target verbal fillers when transcript timing exists. For interview podcasts, the README recommends measuring sentence-level silences with --sentence-min-silence — tunable margins matter because aggressive silence stripping sounds robotic on Zoom recordings.

Agents should run --dry-run first and attach look.py sheets when the video track changes — audio-only jobs explicitly end with Look: not needed per SKILL reporting rules.

Multicam, sync drift, and HDR

Advanced tools include multicam switching, audio drift correction, and HDR → SDR with LUT support. doctor lists whether your ffmpeg build exposes zscale, libass, and loudnorm — Homebrew defaults sometimes lack subtitles filters, producing missing not unknown in capability tables.

If doctor reports unknown for a filter listing, treat the host as untrusted for production until you install a full ffmpeg build (static builds from upstream are the usual fix on macOS).

Batch folders and CI

batch.py walks directories with consistent operations — useful when an agent generates hundreds of UGC variants. Combine with --plan files so CI replays the exact ffmpeg graph later; plans fingerprint inputs and refuse stale reruns if source media changed.

For GitHub Actions, mount ffmpeg once in the runner image, run npx ffmpeg-skill doctor in a setup step, and cap parallelism — ffmpeg is CPU-heavy and agents may spawn concurrent tools unless you throttle MCP calls.

SPEC contract discipline

The README's SPEC (Self-Producing Execution Contract) promise matters for MCP users: input_schema is generated from argparse at runtime, and CI fails if schemas drift. That is stricter than ad-hoc "tool JSON" many agent demos ship. When you add a wrapper skill on top, do not duplicate schemas — call npx ffmpeg-skill contract --json and ingest it.

Installing across Claude Code, Cursor, and Codex

bash
npx ffmpeg-skill --all

lays skill copies for each host. Re-run after upgrades so MCP tools/list schemas refresh. IT should ship libass-enabled ffmpeg on agent laptops used for caption workflows.

SKILL.md requires agent reports to end with Done: or Failed:, JSON probes, and Look: paths when pixels change — add that rule to your AGENTS.md or agents skip verification.

For workshop teams comparing agent stacks, ffmpeg-skill is a useful shared homework assignment: give every attendee the same master clip, let Claude Code and Cursor each run npx ffmpeg-skill, and compare LUFS and contact sheets. The exercise surfaces host differences faster than abstract benchmark slides, and it mirrors how we teach verification in live AI workshops without uploading client media to the cloud. Bring your own ffmpeg build so everyone measures the same loudnorm filter chain locally.

Tool count, MCP defaults, and Zenodo paper reference match kajisho5/ffmpeg-skill README November 16, 2026.

Related reading

  • cinecode: films from Claude Code
  • Scenario game-art agent skills
  • Google Stitch Skills MCP install
  • Plannotator agent plan review
  • Seedance 2.5 generative video context
  • Connect health data to agents via MCP
Spotted something out of date? Let us know.
Daily briefFrom Yash · 350K+ students taught

Catch up on AI

One AI story explained in plain English, plus one thing to try. Every day, free. Unsubscribe anytime.

  • ✓ Free
  • ✓ One email a day, no spam
  • ✓ Unsubscribe anytime
Yash Thakker

Written by

Yash Thakker

Yash is an AI expert with over 300K learners. Join his workshops →

View Yash Thakker in People in AI →

Related posts

Nov 16, 2026

Qwen Code: Open-Source Terminal Coding Agent From Alibaba's QwenLM

Qwen Code is an open-source agent harness from QwenLM with terminal, desktop, web, and chat integrations. The repo crossed 30,000 GitHub stars this week with Agent Teams, Auto-Memory, and multi-provider routing.

Nov 14, 2026

Univer Office SDK: Open-Source Spreadsheets and Docs Your AI Agents Can Edit

The Univer repository pairs an Apache-2.0 Web SDK core with optional commercial Server and AI SDK tiers. Developers embed Sheets and Docs, then drive cells through Facade APIs that agents and apps share.

Nov 11, 2026

ScoutCode Scout Harness: Free Model Pools, Permission Modes, and Fallback Routing

ScoutCode launched Scout, a Windows and Linux coding agent that rotates through pooled free models when one rate-limits, keeps memory in Markdown files the harness edits, and exposes five permission modes from ask-first to yolo.