agentsclimarketplace

Architecture evaluator

Skill morning-start/agent-skills/process/software-design/skills/architecture-evaluator

现有架构评估与改进建议子技能。当用户需要审查现有代码/系统、检测反模式、评估技术债务、提出重构或改进建议时调用。From its SKILL.md

Install
npx -y skills add morning-start/agent-skills --skill architecture-evaluator

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

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 1 stars1 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.

SKILL.md

4.8 KB, ~1.9k tokens by cl100k_base, as published. Nobody here has run it

架构评估与改进 (Architecture Evaluator)

任务目标

本子技能帮助用户评估现有系统架构的质量,识别问题根因,并提供可执行的重构或改进建议。覆盖反模式检测、质量指标打分、技术债务评估和演进路线图制定。


四阶段评估流程

数据收集 → 多维评分 → 问题诊断 → [用户确认] → 改进方案 → 路线图

阶段 1: 数据收集

必填信息

  • 当前系统的核心业务目标(原始文档或口头描述)
  • 代码库概况(语言、框架、代码行数、模块数量)
  • 当前遇到的具体痛点(性能瓶颈?维护困难?bug 频发?)

选填信息(缺失则基于代码分析推断):

  • 架构文档 / 设计文档(如有)
  • 测试覆盖率数据
  • 线上监控数据(延迟、错误率、资源使用)
  • 团队规模和开发流程

阶段 2: 多维评分

按 P0-P4 优先级对现有架构进行评分(1-10 分):

维度权重评分说明
业务对齐度P0?/10代码是否仍反映原始业务目标?
可维护性P1?/10模块独立性、重复代码、圈复杂度
可扩展性P1?/10新增需求是否需要大改?OCP 遵从度
性能P2?/10慢查询、资源瓶颈、缓存命中率
安全性P3?/10OWASP Top 10 风险
成本效率P4?/10资源利用率、云成本

评分说明

  • 1-3:严重问题,需立即处理
  • 4-6:需改进,计划内修复
  • 7-8:较好,有优化空间
  • 9-10:优秀

阶段 3: 问题诊断

3.1 反模式检测清单

类别反模式检测线索严重度
架构级上帝类 (God Class)单个类 > 1000 行🔴 P0
架构级循环依赖A→B→A 的模块依赖链🔴 P0
架构级散弹式修改改一个需求需要改 N 个文件🟠 P1
架构级依恋情结一个方法过度依赖另一个类的数据🟡 P2
代码级过长函数单个函数 > 50 行🟡 P2
代码级过多参数函数参数 > 4 个🟢 P3
代码级魔法数字硬编码 0.8、3600 等无解释常量🟢 P3
代码级重复代码相同逻辑出现 3+ 处🟠 P1

3.2 技术债务评估

graph LR
    subgraph "技术债务分布"
        A[架构债务 45%] --> D[Total]
        B[代码债务 30%] --> D
        C[测试债务 15%] --> D
        E[文档债务 10%] --> D
    end

评估维度:

  • 修复所需人天:估算
  • 风险等级:低 / 中 / 高 / 危急
  • 对业务的影响:阻塞新功能?降低开发速度?

阶段 4: 改进方案与路线图

4.1 改进建议(每个建议必须包含权衡分析)

示例

建议将 God Class 拆分为多个单一职责类
优点可维护性提升 60%,新增功能无需修改核心类
缺点 / 成本需要 3-5 人天,可能影响现有功能稳定性
前置条件需要有足够的测试覆盖(当前覆盖率 30%,建议先补测试)
不适用场景系统即将重写或废弃时,不值得投入

4.2 分阶段演进路线图

gantt
    title 架构改进路线图
    dateFormat  YYYY-MM-DD
    section Phase 1 (Quick Wins)
    添加缺失的测试覆盖      :a1, 2026-07-01, 5d
    提取魔法数字为常量      :a2, after a1, 3d
    section Phase 2 (核心重构)
    拆分 God Class          :b1, after a2, 10d
    打破循环依赖            :b2, after b1, 7d
    section Phase 3 (架构演进)
    引入消息队列解耦        :c1, after b2, 14d
    模块化拆分              :c2, after c1, 21d

输出模板

高层执行摘要(默认必显)

# 架构评估报告:{项目名称}

## 总体评分
可维护性: 5/10 | 性能: 7/10 | 安全性: 6/10 | 成本: 8/10

## 核心发现
🔴 严重: God Class `OrderManager` 1200 行,修改风险极高
🟠 警告: 模块间存在循环依赖 (A→B→C→A)
🟢 建议: 多处魔法数字需提取

## 推荐动作
1. [立即] 拆分 OrderManager (5 人天)
2. [短期] 打破循环依赖 (7 人天)
3. [中期] 补测试覆盖至 80% (10 人天)

## 风险提示
如果不对 God Class 进行处理,每新增一个功能将增加 2-3 天的修改成本。

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most architecture codebase skills give in ~1.9k tokens

Counted across 811 of the 1,134 authors here whose files we hold, read 2026-08-07

  • Ask the user which candidate to explorein 45 of 811, across 15 files
  • Apply the deletion test to suspected shallow modulesin 43 of 811, across 15 files
  • Read any relevant architecture decision records firstin 31 of 811, across 8 files
  • Use exact glossary terms in every suggestionin 30 of 811, across 10 files
  • Accept dependencies instead of creating themin 24 of 811, across 5 files
  • Include before and after visualisations for each candidatein 24 of 811, across 5 files
  • Read the domain glossary before exploringin 24 of 811, across 6 files
  • Return results instead of producing side effectsin 23 of 811, across 4 files
  • Explore the codebase for shallow modules and frictionin 23 of 811, across 3 files
  • Introduce seams only where things varyin 22 of 811, across 3 files
  • Reduce the number of methodsin 21 of 811, across 2 files
  • Design deep modules with small interfacesin 21 of 811, across 3 files

Said here and by no other author read

  • collect business goals codebase details and pain points
  • score architecture across six dimensions using one to ten scale
  • assess technical debt across four areas
  • estimate required person-days and risk levels for technical debt
  • include trade-off analysis for each improvement suggestion
  • include pros cons prerequisites and exclusions for each suggestion

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 326,736. 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.