Project ScoutSAFE

AI automation skills specifically designed for Unity

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: unity-project-scout
description: Advise on reconnoitering an existing Unity project
---

> **Before calling any skill in this module:** if you are about to call a skill with parameters guessed from its name or description, STOP — read this file (or fetch its schema via `GET /skills/recommend?includeSchema=true`) first. If you already have the parameter definitions from recommend/schema, you may proceed straight to dryRun.

## Triggers
- First approaching an unfamiliar project
- Before proposing structural changes
- Auditing existing setup
- 初次接触陌生项目、在提结构性改动前、盘点现有配置

# Unity Project Scout

Use this before recommending architecture changes in an existing project.

## Inspect First

Collect only the information needed to avoid clashing with the current project:

- Unity version and render pipeline
- Installed packages and notable dependencies
- `asmdef` layout, if any
- Folder structure under `Assets/`
- Whether the project already uses:
  - `ScriptableObject` config
  - service/singleton patterns
  - event-driven flows
  - custom inspectors/property drawers
  - tests
- Existing naming and code organization style

## Suggested Tools / Inputs

- Unity project info and project settings
- Script/file search for patterns
- Local inspection of `Packages/manifest.json`, `Assets/`, and `*.asmdef`

## Output Format

- Technical baseline
- Existing architectural signals
- Existing conventions worth preserving
- Existing risks or inconsistencies
- Constraints for future suggestions
- Unknowns that still need confirmation

## Guardrails

> **Mode**: Documentation only — no REST skills to gate; load freely under any operating mode (Approval / Auto / Bypass).

- Do not propose a clean-slate architecture if the project already has a consistent pattern.
- Do not recommend new dependencies until the current stack is clear.

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

What the source does

Filesystem

none-observed

Network

none-observed

Shell

none-observed

Dependencies

pinned

Secrets in source

none-found

Findings (0)

No findings outside the package's declared scope.

Gates applied: no_behavioural_pass.