agentsclimarketplace

Architecture review

Skill ArchSightLabs/archsight-cognition/skills/architecture-review

认知增强 AI Skills:结构化思考、决策复盘、辩论、写作、产品、设计与工程领导,支持 Codex / Claude Code / Gemini CLI

Install
npx -y skills add ArchSightLabs/archsight-cognition --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

  • 3 stars3 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

架构评审 / Architecture review。用于技术方案审查、系统边界、取舍、可扩展性、可靠性、可维护性、技术债和长期演化判断。

SKILL.md

1.5 KB, as published. Nobody here has run it

Architecture Review

这是 ArchSight Cognition 的公共发现入口,用于把架构评审任务转成可执行判断。内部对应视角包括 cogp-newtoncogp-bayescogm-first-principlescogm-tail-riskcogt-designcogt-lead

When To Use

用户要求评审系统设计、服务拆分、技术选型、接口边界、数据归属、可扩展性、可靠性、可维护性、安全边界、技术债或长期演化成本时使用。

Method

  1. 先用一句话复述架构目标和约束。
  2. 标出系统边界、数据所有权、依赖方向和团队所有权。
  3. 检查耦合、复杂度、故障模式、迁移成本、安全边界和可观测性。
  4. 区分必须现在解决的问题、可以延后验证的问题和不应做的过度设计。
  5. 给出推荐方案、反对条件和下一步验证。

Output

默认使用用户的主要语言输出;中文请求使用下面的中文标题,英文请求可自然翻译为英文标题。

架构目标:
关键约束:
边界评审:
取舍判断:
主要风险:
技术债:
决策建议:
反对条件:
下一步验证:

Guardrails

  • 不要把偏好包装成架构原则。
  • 不要默认要求重写或引入新框架。
  • 涉及当前库版本、云服务价格、安全公告或竞品事实时,必须检索或标注待验证。

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.