Skip to content

hashgraph-online/awesome-codex-plugins / plugins/AUN-PN/unity-agent-workflows/skills/unity-agent-workflows

unity-agent-workflows

Verified

Use 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/asset-source-lock.md

View on GitHub
# Asset Source Lock

Use before changing directional sprites, model poses, animation frames, sprite/model selectors, visual factories, fallback visuals, generator IDs, source asset IDs, or exact asset/surface locks.

## Asset Variant Availability Gate

Before editing, prove:

```text
requested visual state:
expected variants:
actual asset paths/names found:
factory/selector lookup path:
active runtime asset/sprite/model name:
fallback when variant missing:
callers using the selector/factory:
surface-local fallback possible: yes/no
```

If variants are missing, do not assume a code patch will make a visible change. Add a surface-local fallback only after caller blast-radius proof, generate/obtain the missing asset through the approved asset workflow, or stop and ask.

## Source Asset / ID Lock

When the user names a generator ID, asset ID, sprite sheet, prefab, scene, screen, runtime object, or exact surface, that value is a hard scope lock.

- Do not replace it with a nearby asset/source.
- Do not generate from another source ID.
- Do not apply the new asset path to global gameplay/runtime factories unless the requested surface is proven as the only caller.
- If the source is missing, inaccessible, or incompatible, stop and ask before substituting.
- Closeout must include the exact source ID/path/name used and where it is called at runtime.
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: 322kUpdated Claude CodeCodexVerifiedInstall
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: 197kUpdated Claude CodeCodexVerifiedInstall
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: 197kUpdated Claude CodeCodexVerifiedInstall
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: 197kUpdated Claude CodeCodexVerifiedInstall