architecture-review

architecture-review is a Codebase structure & module boundaries skill for AI agents, published by Shubchynskyi in the garda-agent-orchestrator repository on GitHub. Skillspace rates architecture-review C (72/100) and it passed the safety scan; the rating is based on static analysis only.

Reviews cross-module and system-design changes for boundary violations, coupling drift, failure-mode gaps, data-ownership conflicts, deployment blast radius, and mismatch between stated architecture and actual changed code. Use when a task touches service boundaries, module public APIs, cross-cutting shared code, integration points, infra topology, or data-ownership contracts. Trigger phrases: arch review, design review, system review, boundary review, module review. Do NOT use for single-module internal refactors that do not alter any public surface or dependency direction.

Grade

C

Quality

72 / 100

Safety

Passed

GitHub stars

24

Unproven: rated by static analysis only, not yet compared head-to-head.

Not launch-quality. It is graded C with a clean safety verdict, but our quality filters exclude it: it is a near-duplicate variant of another skill; it looks written only for the repository it lives in. So it is not in our launch-quality set, the skills our MCP server searches and recommends. How launch-quality is decided

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.