roughcut_skill

This skill creates a rough cut YAML from transcripts and exports it to XML for your editor, streamlining video sequence generation.
  • Ruby

124

GitHub Stars

4

Bundled Files

2 months ago

Catalog Refreshed

4 months ago

First Indexed

Readme & install

Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.

Installation

Preview and clipboard use veilstrat where the catalogue uses aiagentskills.

npx veilstrat add skill barefootford/buttercut --skill roughcut

  • agent_instructions.md4.2 KB
  • combine_visual_transcripts.rb1007 B
  • export_to_fcpxml.rb3.3 KB
  • SKILL.md2.8 KB

Overview

This skill creates a video rough cut YAML file for use with the Buttercut gem and exports a Final Cut Pro XML sequence. It concatenates visual transcripts with file markers, makes editorial clip selections, and outputs a ready-to-import timeline. Use it to generate scenes, sequences, or full rough cuts from transcribed footage.

How this skill works

The skill validates that every video in the library has both audio and visual transcripts before proceeding. It launches a specialized roughcut agent that reads library context, analyzes visual transcripts, selects clips and in/out ranges, and writes a structured YAML rough cut. Finally it converts the YAML into an XML timeline file and stores both YAML and XML in the library.

When to use it

  • You need a first-pass edit (rough cut, scene, or short sequence) from transcribed footage.
  • You want a structured YAML representation of clip decisions for iterative editing.
  • You plan to import an automated timeline into Final Cut Pro or another editor via XML.
  • You have completed transcripts and want faster editorial assembly.
  • You want a reproducible, versioned rough cut stored alongside your media library.

Best practices

  • Confirm every video entry in libraries/[library-name]/library.yaml has both transcript and visual_transcript fields populated before launching.
  • Provide clear user context and editorial intent (tone, pacing, target length) in the library or request.
  • Name rough cuts clearly using descriptive roughcut_name plus datetime to avoid collisions.
  • Review the generated YAML to tweak clip selections before making final edits in the NLE.
  • Keep backups of the library; the skill will trigger a backup step after export.

Example use cases

  • Generate a 30–60 second social media sequence from interviews with visual transcript-driven selects.
  • Create a multi-minute rough cut for a documentary episode using concatenated visual descriptions and audio alignment.
  • Produce a scene assembly for review that editors can import into Final Cut Pro via XML.
  • Automate first-pass timeline creation for long-form footage to accelerate offline editing.

FAQ

The skill stops and prompts to complete transcript processing; you can choose to run transcript and visual analysis first and then re-run the rough cut.

Where are the outputs saved?

YAML and XML are saved under libraries/{library_name}/roughcuts/ with a timestamped filename; the XML path is reported when the agent finishes.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational