Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    ffmpeg Preset Finder

    1

    Generate precise ffmpeg commands for YouTube, TikTok, and web video optimization with proper scaling and audio.

    Free

    1 useSecurity scanned
    ffmpeg Preset Finder

    ffmpeg Preset Finder

    Example session with this skill installed

    I need to turn a landscape video into a TikTok. I want to pad the edges so nothing gets cut off, and make sure the audio is normalized.

    • Read your context and instructions
    • Compiled the ffmpeg preset finder

    I have generated the ffmpeg command to convert your landscape video to a 9:16 TikTok format using padding. This ensures the full frame is visible with black bars on the top and bottom.

    TikTok Vertical (Padded) Command

    ffmpeg -i input.mp4 \
      -vf "scale=1080:1920:force_original_aspect_ratio=decrease,pad=1080:1920:(ow-iw)/2:(oh-ih)/2,fps=30" \
      -c:v libx264 -profile:v high -pix_fmt yuv420p -crf 18 \
      -af "loudnorm=I=-16:TP=-1.5:LRA=11" \
      -c:a aac -ar 48000 -ac 2 -b:a 192k \
      -movflags +faststart tiktok_output.mp4
    

    Target Specification

    PropertyTarget ValueFlag Logic
    Resolution1080x1920scale and pad filters maintain 9:16 aspect ratio.
    Video CodecH.264 (High)libx264 with yuv420p for maximum compatibility.
    Frame Rate30 fpsStandardized via fps=30 filter.
    AudioAAC 48kHzNormalized to -16 LUFS via loudnorm.
    OptimizationFaststart+faststart allows video to play before fully downloaded.

    Next steps

    1. Run the command in your terminal; ensure you have ffmpeg installed.
    2. Verify the output file with ffprobe -v error -show_entries stream=width,height,r_frame_rate -of default=nw=1 tiktok_output.mp4.
    3. Check the audio levels in your media player before uploading.

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

    About this skill

    Handling ffmpeg flags by memory leads to broken uploads and corrupted aspect ratios. This skill generates precise, copy-pasteable commands for major social platforms and web targets. It eliminates the guesswork of converting landscape footage to vertical formats or meeting specific bitrate requirements for YouTube and TikTok.

    What it does

    • Platform targeting generates commands optimized for YouTube, Shorts, TikTok, Reels, or generic web MP4s.
    • Orientation management handles landscape-to-portrait conversions using padding or cropping logic.
    • Audio normalization includes optional loudness passes to ensure consistent volume levels.
    • Spec verification provides ffprobe commands to validate the output against target requirements.
    • Flag explanation breaks down every complex filter and codec setting for transparency.

    How it works

    1. Context gathering identifies the target platform, source orientation, and desired fit (pad or crop).
    2. Preset selection executes a script to retrieve the optimal resolution, bitrate, and codec flags.
    3. Command generation outputs a full ffmpeg command with libx264 and aac defaults.
    4. Validation check provides an ffprobe snippet to verify the codec, frame rate, and pixel format.

    Frameworks & tools

    Uses the ffmpeg CLI, ffprobe, and a Python-based preset selector.

    Why this beats prompting it yourself

    Generic LLMs often hallucinate deprecated flags or incompatible filter chains that cause encoding errors. This skill uses a verified library of platform specs to ensure the command actually runs and produces a valid file on the first try.

    Use cases

    • Convert landscape b-roll into a padded 9:16 video for Instagram Reels.
    • Prepare high-quality MP4s with +faststart for web playback.
    • Fix audio levels and sample rates for TikTok upload compliance.
    • Scale and re-encode 4K footage to 1080p for standard YouTube uploads.

    Known limitations

    Does not support AI-based upscaling or caption generation. It will not automatically run the command to prevent accidental CPU spikes or file overwrites.

    Requires ffmpeg/ffprobe installed. Does not automate execution. Platform specs are based on internal references and may lag behind official API changes.

    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

    1 use

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 27 days ago

    • Free with an Agensi account

    Requires

    ffmpeg 6+
    ffprobe

    Permissions

    Terminal / Shell
    Read Files

    File Scopes

    *.mp4
    *.mkv
    *.mov
    *.webm
    Listed27 days ago

    What's inside

    Frequently Asked Questions

    This skill eliminates the trial and error of video encoding by providing verified, platform-specific commands for YouTube, TikTok, and web, ensuring your files meet strict upload requirements on the first try.

    The skill is designed to work with any LLM or AI agent capable of executing Python-based logic and providing text output, such as ChatGPT, Claude, or custom AutoGPT setups.

    You will receive the Python-based preset selector script, a library of verified platform specifications, and the integration documentation to connect the skill to your preferred AI agent.

    No, this skill is a command generator; it provides the precise code for you to run locally, ensuring you maintain full control over your hardware resources and file safety.

    The preset library is updated periodically to reflect changes in social media upload requirements, such as new bitrate recommendations or codec support for platforms like TikTok and YouTube.

    Yes, the skill includes specific logic for orientation management, allowing you to choose between padding (letterboxing) or cropping when converting between landscape and portrait formats.

    New in Workflow Automation