Video Creator Skill

Manages the complete video creation pipeline from script input to final video components.

Execution Modes

Determine which workflow to follow based on user input:

Mode 1: Execute Video Step

When: Immediately read when user wants to execute a specific workflow step (audio, direction, assets, design, or coding). Workflow: execute-video-step.md

Mode 2: Execute Regenerate Scenes Step

When: Immediately read when user wants to regenerate specific scenes for a step (design or coding) with scenes parameter. Workflow: execute-regen-scenes-step.md

Mode 3: Resume Video

When: Immediatly read when user wants to continue an existing video workflow from where it left off or check the status of an in-progress video Workflow: resume-video.md

Mode 4: Create Video

When: User wants to create a completely new video from scratch, starting with script input and style selection Workflow: create-video.md

Step References

Individual step implementations (referenced by execution modes):

• user-input-step.md – Gather script and video style
• audio-step.md – Generate audio from script
• direction-step.md – Create video direction
• assets-step.md – Generate SVG assets
• design-step.md – Generate design specifications
• code-step.md – Create video components
• regenerate-design-step.md – Regenerate design for specific scenes
• regenerate-code-step.md – Regenerate code for specific scenes

Utility Scripts

video-status.py: Manages workflow state and step progression

Available actions:

• create-video-status-file: Initialize new video workflow and return first step
• get-incomplete-step: Get current pending step
• complete-step: Mark step done and advance to next

Output Format:

All actions output a single line

list-topics.py: Get all topics with video workflows

Usage:

python .claude/skills/video-creator/scripts/list-topics.py

When user doesn’t specify a topic, use this script to get all available topics, display them to the user, and ask them to specify which topic they want to work with