Video & Audio Production Skills

Adds visual descriptions to transcripts by extracting and analyzing video frames with ffmpeg. Creates visual transcript with periodic visual descriptions of the video clip. Use when all files have audio transcripts present (transcript) but don't yet have visual transcripts created (visualtranscript).

Backs up user libraries and all their contents (external video excluded). This skill can also be useful when you need to restore a library.

The ButterCut home menu — welcome the user back, then ask what they'd like to do (start a new cut, add footage to a library, a one-off task, or something else) and hand off to the right skill. Use as the front door when the user opens ButterCut, types "buttercut" or "bc", or asks "where do I start", "what can you do", or "help me get started".

Builds a contact sheet from a video clip — evenly spaced frames laid out in a single grid image, each with its hh:mm:ss timestamp burned in. Use when the user asks for a "contact sheet", "grid", "film strip", or wants a one-image overview of part of a clip.

Create a new ButterCut library. Gather library info (name, footage location, language, transcript proofreading) and scaffold the library. Use when the user wants to start a new library. Libraries are containers of footage and footage analysis (transcripts, contact sheets, etc). User's may also refer to Libraries as "projects" or similiar. Ask them to confirm if they want a new Library (footage container) or just a new cut (roughcut, select, etc) if unsure.

Build a cut from a library — scene, selects, roughcut, or custom task. Starts by asking what kind of cut the user wants, then works with them to determine what they want to create. Always exports a file for Final Cut, Premiere, or Resolve at the end. Use when the user asks for a "roughcut", "sequence", "scene", "selects", or any other cut-shaped output.

Plans a cut (roughcut, sequence, or scene) from a library's clip summaries. Reads all clip summaries, then talks with the user and iteratively creates a plan markdown file until both agent and user are happy and understand the plan.

Exports all dialogue from every clip in a library into a single text file. One clip per block — filename, then its spoken words. Use when the user asks for a "full transcript", "full script", or wants all the dialogue from a library in one place.

Help a user handle a one-off production related task that doesn't match perfectly to an existing skill. Examples, pull a clip's audio, extract a frame, transcribe a stray recording, draft notes, create a spreadsheet, convert a file from one type to another, etc. Use when the request doesn't map to other more obvious skills.

Skill for processing footage (video clips, sounds, photos, etc). Use this when creating a new library, adding new footage (videos) to an existing library, or resuming processing on an existing library.

Reset a library's visual analysis (contact sheets, summaries, legacy visualtranscripts) and re-run the current analyze-video pipeline on it. Keeps audio transcripts, cuts, plans, and library metadata. Use when a library was processed under the older pipeline and the user wants to bring it onto the contact-sheet-based one.

Builds a roughcut YAML and exported XML (Final Cut, Premiere, or Resolve) from an approved plan markdown file produced by cut-planner. Spins up a sub-agent that reads the library directly, builds the cut iteratively, reviews against format conventions, then returns paths plus conversational editorial notes. If the user asks for a "roughcut", "sequence", or "scene" and no plan exists yet, run cut-planner first.

Generates a short markdown summary of a video from its visual transcript. Covers overview, key visuals, notable dialogue, and b-roll. Run after analyze-video as the final footage analysis step; summaries become a required field on every video before any roughcut can be created. Always launch this skill using the Haiku model.

Transcribes video audio using WhisperX, preserving original timestamps. Creates JSON transcript with word-level timing. Use when you need to generate audio transcripts for videos.

A skill to automatically download and install the latest ButterCut version from GitHub while preserving libraries. Use when user wants to check for updates or update their installation for new features.