home / skills / barefootford / buttercut / roughcut

roughcut skill

/.claude/skills/roughcut

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

npx playbooks add skill barefootford/buttercut --skill roughcut

Review the files below or copy the command above to add this skill to your agents.

Files (4)
SKILL.md
2.8 KB
---
name: roughcut
description: Creates video rough cut yaml file for use with Buttercut gem. Concatenates visual transcripts with file markers, creates a roughcut yaml with clip selections, then exports to XML format. Use this skill when users want a "roughcut", "sequence" or "scene" generated. These are all the same thing, just with different lengths.
---

# Skill: Create Rough Cut

This skill handles the editorial process of creating rough cut timeline scripts from transcribed video footage. It launches a specialized agent that analyzes transcripts, makes editorial decisions, outputs a structured YAML rough cut, and exports it to Final Cut Pro XML format.

**Note:** This skill is used for both full-length rough cuts (multiple minutes) and short sequences (30-60 seconds).

## Prerequisites Check

Before launching the roughcut agent, verify all transcripts are complete:

1. **Check library exists:**
   ```bash
   ls libraries/[library-name]/library.yaml
   ```

2. **Verify visual transcripts:**
   Read `libraries/[library-name]/library.yaml` and check that every video entry has both:
   - `transcript` populated (audio transcript filename)
   - `visual_transcript` populated (visual descriptions filename)

   If any visual transcripts are missing:
   - Inform user that transcript processing must be completed first
   - Ask if they want Claude to finish transcript processing using the `transcribe-audio` and `analyze-video` skills
   - Do not proceed with roughcut creation until all transcripts are complete

## Launch Roughcut Agent

Once prerequisites are verified, launch the roughcut creation agent using the Task tool:

```
Task tool with:
- subagent_type: "general-purpose"
- description: "Create rough cut from visual transcripts"
- prompt: [See agent prompt template below]
```

### Agent Prompt Template

When launching the agent, provide a detailed prompt with all necessary context:

```
You are a video editor AI agent creating a rough cut or sequence for the "{library_name}" library.

USER REQUEST: {what_user_asked_for}

LIBRARY CONTEXT:
{paste relevant content from library.yaml - footage_summary, user_context, etc.}

YOUR TASK:
1. Read the roughcut creation instructions from .claude/skills/roughcut/agent_instructions.md
2. Follow those instructions to create the rough cut
3. Return the paths to the created YAML and XML files when complete

DELIVERABLES:
- Rough cut YAML file at: libraries/{library_name}/roughcuts/{roughcut_name}_{datetime}.yaml
- Exported XML file for user's chosen video editor
- Backup created via backup-library skill

Begin by reading the agent instructions file.
```

## After Agent Completes

When the agent returns:
1. Inform the user of the created roughcut file (the xml file, not the yaml file) and its location
2. Confirm the rough cut is ready to import into their video editor

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

What happens if a visual transcript is missing?

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.