asset-generation-skill

Generates and submits image asset and storyboard jobs through a unified async media job system.

Updated Aug 12, 2026
One-click install
npx skills add https://github.com/VANTSU-1874/woods-video-studio --skill asset-generation-skill-vantsu-1874
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: asset-generation-skill
Source: https://github.com/VANTSU-1874/woods-video-studio/tree/main/template/.agents/skills/asset-generation-skill
Command: npx skills add https://github.com/VANTSU-1874/woods-video-studio --skill asset-generation-skill-vantsu-1874

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Producing character, scene, prop, and storyboard images for a short-drama episode requires tracking many asynchronous image generation jobs, reference-image dependencies, and file save locations. This Skill coordinates that pipeline so assets are generated in the right order, saved to the correct paths, and recorded in a consistent registry without manual tracking. ## Core Features & Use Cases - Ordered Asset Generation: Generates prop, scene, then character assets, using the first variant as a reference image for later variants to preserve visual identity. - Unified Job Tracking: Creates and submits jobs through the project's media job system, recording task IDs, retry counts, local paths, and checksums in the asset registry. - Episode Asset Locking: After all images complete, locks an immutable per-episode asset snapshot so scripts, storyboards, and videos reference consistent visuals. - Use Case: After costume/prop/set design is approved for episode 1, run the skill to submit all image jobs, wait for completion, then lock the episode asset snapshot before director analysis begins. ## Quick Start Ask the assistant to generate all asset images for episode 1 and confirm when they are ready to lock.

Frequently Asked Questions about asset-generation-skill

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate character, scene, and prop images for a video episode?

Run the asset generation flow which syncs the asset registry, creates jobs per episode, and dispatches each ready job to a media worker. Assets generate in prop, scene, then character order, with later variants using the first variant as a reference image.

How do I keep image variants consistent across a character or scene?

The first variant acts as the baseline reference image, and dependent variants pass its local path as a reference input. Dependent jobs wait until the baseline file exists on disk before submission, so generation never falls back to unreferenced text-to-image.

Does this image generation workflow require an OpenAI API key?

No. The default codex-image provider uses the signed-in Codex session with built-in gpt-image-2, so no OPENAI_API_KEY is needed. A direct OpenAI Images API provider remains available if you configure a local key.

Why did my image job fail with an Invalid URL or ENOENT file error?

These errors indicate a malformed media invocation, not a generation failure. Rebuild and revalidate the invocation parameters, then retry the job instead of marking it failed.

When can generated assets be used for storyboards and video production?

Only after all episode images complete and the user confirms, the asset snapshot lock command freezes immutable image copies for that episode. Director analysis, storyboards, and video generation must reference the locked snapshot.