Cut, Caption, Ship: FFmpeg Video Editing

    0

    Cuts dead air, burns captions, reframes to 9:16, normalizes loudness and exports platform-ready video with one tested FFmpeg CLI.

    Free

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Cut, Caption, Ship: FFmpeg Video Editing

    Example session with this skill installed

    Edit interview.mp4: cut the pauses, make a 9:16 cut with captions, and export it for Reels.

    • Read your context and instructions
    • Compiled the cut caption ship

    edit/final.mp4 - 0:48, 1080x1920, H.264 CRF 18, AAC 192 kbps, -14 LUFS, captions burned with a 240px bottom margin. QA reports no issues.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Cut, Caption, Ship turns raw footage into a finished, platform-ready video with a tested FFmpeg CLI instead of hand-written commands.

    What it does:

    • Removes dead air and filler pauses and writes an editable keep list
    • Reframes 16:9 to 9:16, 1:1 or 4:5 with crop or blurred-bar padding
    • Burns SRT, VTT or ASS captions at pixel-accurate sizes and platform-safe margins
    • Normalizes loudness to -14 LUFS and exports YouTube, Shorts, Reels and TikTok presets
    • Runs a QA pass for black frames, freezes, odd dimensions and missing audio

    Bundled:

    • scripts/ffedit.py: probe, silence, cut, caption, reframe, export, qa, doctor
    • references/export-presets.md: platform specs, caption safe areas, troubleshooting

    Requirements: FFmpeg 6+ with libx264, aac and libass, plus Python 3.9+. No API keys and no network calls; everything runs locally on the user's footage.

    Tested end to end on a 12-second clip with two silent gaps: cut 12.0s to 9.99s, burned captions, reframed to 1080x1920 in both modes, exported at -14 LUFS with audio intact.

    No built-in transcription; supply an SRT, VTT or ASS file or generate one first. Autocut assumes speech, not music. Burned captions are not editable after export. Each stage re-encodes the video.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 2 days ago

    • Free with an Agensi account

    Requires

    FFmpeg 6+ with libx264, aac, libass
    Python 3.9+
    Python

    Permissions

    File Scopes

    the
    folder
    holding
    source
    video
    and
    edit
    outputs

    Local FFmpeg only; no network calls or credentials.

    Listed2 days ago

    What's inside

    Frequently Asked Questions

    No. Supply an SRT, VTT or ASS file, or generate captions with a speech-to-text tool first and have the agent verify names and numbers.

    No. It renders the final file and reports the settings; uploading is up to you.

    No. The workflow writes every output under an edit folder and leaves the original untouched.

    Yes. The bundled CLI escapes filter paths itself, so you do not need to hand-edit ffmpeg filter strings. FFmpeg and Python must be on PATH.

    No. Burn-in is permanent, so keep the subtitle file. Re-run the caption step if you need changes.

    New in Image & Video