| name | agent-work-auditor |
| description | Unified auditing skill for AI agent workflows. Provides change-type-aware, artifact-adaptive auditing with self-fix capabilities. Works standalone or with spec-driven extensions. Three-layer architecture: core (always active), modules (per-type), extensions (auto-detected).
|
agent-work-auditor
A unified, modular auditing framework for AI agent workflows. Provides adversarial audits designed to find gaps and block premature approval. Every audit must switch the agent from author mode to critic mode and force specific, named weaknesses to be surfaced.
Activation
Load this skill when:
- User asks to audit code, a PR, or a change set
- Spec-driven Code Review requires auditing
- User mentions "are you sure?" after producing work
- User wants verification of completeness or correctness
Three-Layer Architecture
Layer 1: Core (Always Active)
Universal dimensions evaluated for every audit:
| Dimension | Question | Auto-Fix |
|---|
| Completeness | Is everything present? | Yes |
| Correctness | Is it right? | Yes |
| Consistency | Does it fit patterns? | Yes |
| Traceability | Can we trace it? | Partial |
| Safety | Could it cause harm? | No |
| Maintainability | Will future devs thank us? | Partial |
| Rigorous Against Prompt/Spec | Does it match the original intent? | Partial |
Layer 2: Change-Type Modules (Per-Invocation)
Loaded based on detected change type:
