binquery

    1

    Local CLI for splitting long videos and querying footage folders using OpenCLIP visual intent.

    Free

    1 useSecurity scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    binquery

    Example session with this skill installed

    I have a long recording of a city walk in ./raw/walk.mp4. Split it into 10-second clips, index them, and find shots of 'people crossing the street'.

    • Read your context and instructions
    • Compiled the binquery

    I have processed the video file, created the index, and queried for your specific intent. The long recording was split into segments, and the local index has been verified.

    Clip Shortlist: 'people crossing the street'

    PathScoreGateReasons
    ./split-out/walk_005.mp40.82pictorialHigh visual match for crowd movement at intersection.
    ./split-out/walk_012.mp40.79pictorialMatches urban crossing environment.
    ./split-out/walk_008.mp40.75person_clipMultiple subjects detected in motion across frame.
    ./split-out/walk_021.mp40.71pictorialDistant view of pedestrian crossing.
    ./split-out/walk_003.mp40.68pictorialStreet level view with active foot traffic.
    ./split-out/walk_015.mp40.65motion_labelHandheld movement following subjects across street.
    ./split-out/walk_009.mp40.62pictorialFrame includes crosswalk markings and pedestrians.
    ./split-out/walk_022.mp40.59pictorialNear-miss; shows street traffic with some pedestrians.

    Next steps

    • Review the clips in ./split-out/ to confirm the best takes for your edit.
    • Run binquery list to see if any frozen director intents match your next scene.
    • Use binquery query with a different intent sentence to find specific lighting or angles.

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

    About this skill

    Searching through hours of raw footage for a specific shot or breaking a long recording into manageable chunks is a manual bottleneck for editors. binquery automates the local clip management workflow by providing a CLI-based shortlist generator that ranks footage based on your visual intent.

    What it does

    • Time-grid splitting breaks one long local video file into segments using ffmpeg.
    • Local indexing generates CLIP vectors for a folder of videos without using cloud APIs.
    • Intent-based querying ranks 8–15 clips based on a single descriptive sentence.
    • Health monitoring verifies index integrity with a doctor command to prevent failed queries.
    • Multi-modal scoring provides results with a path, score, gate type, and logic-based reasons.

    How it works

    1. split: Run the command on a long recording to generate a folder of segments based on a time grid.
    2. index: Process the clip folder to create local vector embeddings and metadata.
    3. doctor: Verify the generated index files to ensure the query engine has the required data.
    4. query: Input a visual description to receive a ranked shortlist of local video paths.

    Frameworks & tools

    This tool requires Python 3.10+, ffmpeg, and ffprobe on the system PATH. It uses OpenCLIP (ViT-B-32) for local embedding generation.

    Why this beats prompting it yourself

    Writing a custom script to bridge ffmpeg and OpenCLIP requires significant boilerplate for frame extraction and vector management. This skill provides a structured CLI that handles the grid-splitting, local caching, and scoring logic out of the box.

    Use cases

    • Generate a shortlist of potential reaction shots from a streamer's VOD.
    • Find specific visual scenes within a large folder of dailies or rushes.
    • Break down a long master file into a grid for faster manual review.
    • Organize scene-sequence visual intents during a complex edit.

    Known limitations

    Does not perform highlight detection, silence cutting, or automatic timeline assembly. Requires local disk space for the index and an initial download for CLIP weights.

    Local machine only. No cloud API or auto-editing. Split is time-grid only, not highlight detection. Requires ffmpeg and ffprobe. First run requires internet for weights.

    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 1 month ago

    • Free with an Agensi account

    Requires

    Python

    Permissions

    No special permissions declared or detected

    Listed1 month ago

    What's inside

    Frequently Asked Questions

    binquery is a local CLI tool that automates the tedious process of chopping long video files into segments and using OpenCLIP to search through those clips using natural language descriptions.

    The skill requires Python 3.10+, ffmpeg, and ffprobe installed on your system; all processing, indexing, and querying occur locally on your machine without needing cloud-based AI subscriptions.

    While binquery can be run manually via CLI, it is designed to integrate with AI agents that support local shell execution, allowing you to ask an agent to "find all shots of a sunset in this folder."

    No, binquery uses the OpenCLIP ViT-B-32 model to generate local vector embeddings, ensuring your footage remains private and no data is sent to external servers during the search process.

    You will receive the full Python-based CLI package, the logic for grid-based ffmpeg splitting, and the indexing engine; please note that initial setup will trigger a one-time download of the CLIP weights.

    This tool identifies visual intent based on your descriptions (e.g., "person laughing"), but it does not perform automated highlight detection based on audio levels or automatic sequence assembly for NLEs.

    New in APIs & Backend