hashgraph-online/awesome-codex-plugins / plugins/AUN-PN/unity-agent-workflows/skills/unity-agent-workflows
unity-agent-workflows
VerifiedUse for AI-assisted Unity work that needs live repo discovery, project-derived routing, runtime-owner proof, runtime-visible output hard stops, runtime numeric proof for repeated visible-output failures, state-step guards, multi-agent scope ownership, modular C#/asmdef safety, UI/scene/visual asset gates, data-first content changes, validation, cleanup proof, or durable workflow rules. Best when agents must prove the actual folder/module/scene/prefab/runtime owner before editing, especially runtime UI, generated assets, code graphs, tutorial/state flows, guided selection/action flows, overlay/dim source-bound mistakes, coordinate conversions, focus/highlight/marker/HUD alignment, predictive lead aiming, ballistic trajectories, spatial IoU verification, or repeated "fix still not visible" failures.
references/runtime-visible-output.md
View on GitHub# Runtime Visible Output
Use for runtime-visible output drawn, positioned, blocked, aimed, anchored, masked, followed, measured, or converted from a live Unity target. Broader than tutorial focus UI.
Examples include UI overlays, selection outlines, input blockers, drag targets, HUD markers, objective arrows, world-to-UI labels, damage numbers, nameplates, health bars, safe-area-dependent UI, camera targets, RenderTexture-driven UI, world-space canvases, and hardcoded layout used as a substitute for a live target.
For extracted UI items, textless UI sprites, generated slices, or design manifests, the visible source can be the extracted item bounds rather than a live scene object. In that case, load `references/ui-and-visual-assets.md` and use the Extracted UI Item Assembly Gate before overlay text/button placement.
## Runtime Visible Output Hard Stop
Do not edit coordinates, anchors, offsets, padding, scale, layout timing, camera conversion, or fallback constants until this proof exists:
```text
user-visible output
-> active source object
-> selected source bounds: markerRect / visualRect / interactiveRect / logicRect
-> source parent chain
-> source owner script/component
-> runtime writer after creation/layout
-> source space and camera/canvas
-> destination root/canvas/space
-> conversion API path
-> converted output rect/position
-> validation method
```
If any link is unknown, stay read-only or inspect deeper. Do not patch from semantic similarity, object center, first-name lookup, screenshot proximity, or a previously edited constant.
## Hardcoded Layout Guard
```text
visible target -> runtime object -> runtime bounds -> converted coordinate space -> overlay
```
Hardcoded layout is not runtime object proof. Use hardcoded values only as a named fallback after runtime target resolution fails, and report residual risk.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation). | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply. | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |
| frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults. | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |
| mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |