AdrSAFE

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-adr
description: Record Unity architecture decisions (ADR) with rationale
---

> **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
- Choosing between technical approaches
- Comparing libraries or patterns
- Documenting design rationale
- 技术方案选型、库/模式对比、记录设计决策来龙去脉

# Unity ADR

Use this when architecture choices may be revisited later or when multiple plausible options exist.

## Output Format

- Decision
- Context
- Options considered
- Chosen option
- Why this option won
- Consequences
- Revisit triggers

## Example Use Cases

- Coroutine vs UniTask
- Direct reference vs event-driven communication
- ScriptableObject config vs in-scene authoring
- One assembly vs multiple `asmdef`
- Runtime logic in `MonoBehaviour` vs pure C# service

## Guardrails

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

- Keep ADRs short.
- Record only decisions that materially affect code generation or architecture direction.

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.