Architecture review

Skill eooo-io/ai-native-engineering-doctrine/04-agent-skills/architecture-review

AI-native engineering harness: doctrine-only, fork-and-curate scaffold for standards, agent skills, tool adapters, and review rubrics.

Install

npx -y skills add eooo-io/ai-native-engineering-doctrine --skill architecture-review

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Review architecture decisions, boundaries, trade-offs, scalability, and operational risk.

SKILL.md

1.1 KB, 201 tokens by cl100k_base, as published. Nobody here has run it

Architecture Review

Purpose

Evaluate whether a proposed or existing design fits the problem, the constraints, the team, and the operational environment. The output is structured feedback a designer can act on, not a verdict.

Checklist

Problem statement is clear.
Main constraints are explicit.
Boundaries are defined.
Data ownership is clear.
Failure modes are considered.
Security and authorization are addressed.
Observability is included.
Deployment and rollback are realistic.
Alternatives were considered.

Output format

## Architecture summary

## Strengths

## Risks

## Trade-offs

## Missing decisions

## Recommended next step

Rules

Tie each risk and trade-off to a constraint, not to taste.
Mark uncertainty explicitly; don't smuggle assumptions past the reader.
Prefer "missing decision" over "wrong decision" when the design hasn't named the trade-off yet.
Do not invent product or business requirements.