# Unity AI Audit

> Use to audit a Unity project's AI/ML stack: packages, models, scripts, configs, and release risks. Start here for "what AI does this game use?"

- Skill: `rachitkumarrastogi/unity-ai-audit` (Agent Skill)
- Install (CLI): `npx skillmds@latest add rachitkumarrastogi/unity-ai-audit`
- Raw SKILL.md: https://api.skillmd.com/api/skills/rachitkumarrastogi/unity-ai-audit/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Security
- Author: rachitkumarrastogi (https://skillmd.com/u/rachitkumarrastogi)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/rachitkumarrastogi/unity-ai-audit

---

# Unity AI stack audit

## One-shot

Run `get_ai_stack_summary` with `include_prompt_assets: true`.

## Deep dive order

| Step | Tool | Why |
|------|------|-----|
| 1 | `get_ai_ml_package_inventory` | Official Unity AI packages & versions |
| 2 | `list_ml_model_assets` | ONNX and other models in repo |
| 3 | `list_ml_agents_training_configs` | RL training YAMLs |
| 4 | `find_ai_related_scripts` | Code-level AI APIs |
| 5 | `list_ai_prompt_or_config_assets` | Prompt/RAG JSON or docs |
| 6 | `get_build_size_estimate` | Model weight in shipping build |
| 7 | `get_release_readiness` | Broken refs + cycles + large assets |

## Bundled skills

Call `list_ai_skills` (returns `category`) then `read_ai_skill`.

Skills follow Unity Editor domains — see `skills/README.md`. Highlights:

- **Scenes:** `unity-scenes-workflow`
- **Model-agnostic:** `unity-model-agnostic-inference`
- **Vendor-specific:** `unity-ml-agents`, `unity-sentis-inference`, `unity-llm-integration`
- **Gameplay AI:** `unity-navmesh-npc`
- **Performance:** `unity-runtime-performance`, `unity-build-size-optimization`, `unity-memory-asset-pressure`

## Report template

```markdown
## AI stack summary
- Packages: ...
- Models: N ONNX, ...
- Scripts: N files (top labels: ...)
```