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/visible-object-identity.md
View on GitHub# Visible Object Identity
Use before Unity visual, model, sprite, source asset, prefab, or animation integration when the visible target may differ from the feature name, source asset, factory, semantic module, or first search result.
## Visible Object Identity Lock
Before editing, prove:
```text
user-visible target:
screen/scene/surface:
exact runtime GameObject name:
scene/prefab/runtime creator:
owner presenter/controller/component:
writer/update method:
asset/model/factory dependency:
nearby semantic owner candidates:
rejected candidates and reason:
validation:
```
If the user-visible target and semantic feature name disagree, stop before patching. Continue single-agent investigation only if you can reject competing owners with file-backed proof, or ask the user to approve read-only sub-agent discovery.
Example failure mode: the request mentions a gameplay unit, but the visible object is a menu preview object. Do not patch gameplay factories or contracts until the menu/runtime object, creator, writer, and factory dependency chain are proven.
## Single-Agent Anti-Anchoring Guard
Use before patching a visible/runtime Unity target when naming is ambiguous.
Required when:
- feature name, asset name, scene object, and visible surface do not point to the same owner.
- the first candidate is a factory/helper/registry/bridge/global selector.
- search results show both scene/prefab objects and feature code owners.
- the requested object appears in multiple UI surfaces.
Required output before edit:
```text
primary candidate:
competing candidates:
why primary is runtime-visible:
why rejected candidates are not owners:
proof still missing:
```
If competing candidates cannot be rejected with file-backed proof, do not patch. Ask to continue single-agent investigation or to use read-only sub-agent discovery.
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: 198k | 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: 198k | 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: 198k | Updated | Claude CodeCodex | Verified | Install |