Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
Generates videos from the terminal using the Bazaar AI composition engine. Supports multi-track layering, timing choreography, voiceovers, and cloud rendering. A mandatory 5-phase workflow gates progress from context setup through generation, review, verification, and export.
Combines AI scene composition, multi-track choreography, and cloud rendering in a single CLI with built-in quality gates, replacing the need for separate design, editing, and rendering tools.
When to use it
- Automating product announcement video generation in a CI pipeline
- Building branded explainer videos without a GUI video editor
- Iterating on AI-generated scenes until all requirements pass verification
- Scripting video exports for recurring marketing content
- Generating voiceover-narrated demos from terminal prompts
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Create a 30-second product feature announcement with purple branding and a CTA
- 1Create a project with baz project create and set goal, requirements, and brand context via baz context add
- 2Add choreography instructions to context to prevent lockstep scene transitions
- 3Generate scenes with baz prompt, specifying durations, animations, and layout per scene
- 4Run baz review --json and baz verify --criteria with all requirements to confirm passedAll is true
- 5Run baz export start --wait --json to render and receive the hosted video URL
Rendered video URL on Bazaar CDN, shareable immediately
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.