screen-reference

Solid

Generate and validate a full-screen visual reference for scene direction and evaluation, without producing a runtime asset.

AI & Automation 495 stars 43 forks Updated today NOASSERTION

Install

View on GitHub

Quality Score: 79/100

Stars 20%
90
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
94
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Screen Reference Asset Use this skill for full-screen scene references and visual evaluation targets. It is reference-only: it does not create a runtime Godot resource, has no `godot_artifact`, and must not enter worker runtime handoff. ## Invocation Accept one asset request matching the shared Asset Skill request schema in `skills/assets/_shared/schema/asset-skill-request.schema.json`. Require `asset_type` to be `screen-reference`. Validate the returned document against the shared result schema and checker before returning it. This skill can be invoked directly or by an orchestrator with the same contract. Do not read or write `ASSETS.md`, tags, stage state, generated manifests, or worker dispatch state. ## Produce 1. Use the brief and visible references to describe the game genre, scene purpose, camera or viewpoint, gameplay-visible objects, approximate layout, requested HUD or UI elements, style language, target aspect, and orientation. 2. Generate one source image per requested scene. Do not add labels, callouts, debug overlays, or unrequested objects. 3. Finalize the accepted image at `references/<asset_id>.png` after checking the requested aspect and dimensions. 4. Preserve it as a visual reference only. Do not compile it to `Texture2D`, `AtlasTexture`, or any other native runtime resource. ## Result Return the shared generic result with one `reference` output, no `godot_type`, and no runtime outputs: ```json { "asset_type": "screen-reference...

Details

Author
RandallLiuXin
Repository
RandallLiuXin/GodotMaker
Created
3 months ago
Last Updated
today
Language
Python
License
NOASSERTION

Similar Skills

Semantically similar based on skill content — not just same category