跳到正文
cccskills
免费在 GitHub 公开

kent-beck-review

Code review from the Kent Beck Simple Design 4 Rules perspective. God Object splitting, SRP, duplication removal, naming, cyclomatic complexity. Triggered by "kent beck", "simple design", "simplify", "refactoring" ("리팩토링"), "refactor", "god object", "SRP" keywords.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(1)

  • SKILL.md2.9 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Kent Beck Code Review Lens

"Make the change easy, then make the easy change."

Four Rules of Simple Design (in priority order)

  1. Passes tests — Tests pass
  2. Reveals intention — Names and structure reveal intent
  3. No duplication — Eliminate idea-level duplication
  4. Fewest elements — Minimal components

Review Checklist

File Size

# Detect 500+ line files (God Object candidates)
find core/ -name "*.py" -exec wc -l {} + | sort -rn | head -20

File size identifies inspection candidates, not a split requirement. Trace responsibilities, callers, and reasons to change before proposing extraction. Do not carry a dated file-size snapshot forward as current implementation status.

Method Size & Complexity

Inspect the actual function and its callers. Function length, nesting, and branch counts do not by themselves justify a Strategy, dispatch table, or new module. Prefer an early return or an existing helper when it resolves the identified failure without obscuring domain behavior.

Reveals Intention

Anti-patternImprovement
def process(data)def score_analyst_response(response)
result = fn(x, y, z)Use meaningful variable names
# This function does XReveal through function name, remove comment
magic number 0.7CONFIDENCE_THRESHOLD = 0.7

No Duplication

Detect idea-level duplication (not just copy-paste but missing abstractions):

Trace repeated decisions through their shared owner. Unify behavior that must change together; keep similar-looking paths separate when their contracts differ. Neither repetition count nor structural similarity alone requires a factory, Protocol, or generic abstraction.

Fewest Elements

Unnecessary ElementCriteria
Unused parametersWrappers that only pass **kwargs
ABC with single implementationCheck the substitution contract; a concrete class may be sufficient
Empty __init__.pyCheck package, distribution, discovery, and import contracts before removal
Unused importsAuto-detected by ruff F401

Scope and Verification

A review does not authorize refactoring. Follow the workflow for requested changes and the deletion gate before removing code, tests, or package files. Use verification gates for targeted checks and evidence reuse. Report concrete findings with current file/line evidence; no finding is preferable to a speculative simplification.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Audit agent runtimes and their tests for lifecycle inference, capability overload, context pollution, correlated verification, prompt-only control, false success, dead compatibility paths, test-only seams, and complexity without contribution. Use for whole-repository agent audits, slop or dead-code triage, test contribution reviews, large refactors, tool/context simplification, and cleanup requests that need proof before deleting code or tests.

中文简介正在准备中。当前显示原文说明。

mangowhoiscloud/geode152026年10月22日 更新

Diagnose agent operational failures through default-policy checks, multi-gap analysis, explicit service ownership, request-context lifetime, and degradation-versus-correctness checks.

中文简介正在准备中。当前显示原文说明。

mangowhoiscloud/geode152026年10月22日 更新

Align, run, audit, and publish GEODE benchmark comparisons against Agent-World arXiv 2604.18292v1 across MCP-Mark, BFCL V4, and tau2-bench. Use for Agent-World or AgentWorld comparison requests, cross-suite agent benchmark design, Tau2 comparator/profile diagnosis, paired thin-runtime-versus-GEODE experiments, mean-accuracy@8 replication, or benchmark comparability and artifact reviews.

中文简介正在准备中。当前显示原文说明。

mangowhoiscloud/geode152026年10月22日 更新

Verification checklist to prevent fake success. Detects test deletion/disabling, coverage regression, lint bypass, secret exposure. Triggered by "deception", "fake" ("가짜"), "fake success", "verification" ("검증"), "checklist" ("체크리스트"), "deletion detection" ("삭제 탐지"), "regression" keywords.

中文简介正在准备中。当前显示原文说明。

mangowhoiscloud/geode152026年10月22日 更新

Implement proven backend architecture patterns including Clean Architecture, Hexagonal Architecture, and Domain-Driven Design. Use when architecting complex backend systems or refactoring existing applications for better maintainability.

中文简介正在准备中。当前显示原文说明。

mangowhoiscloud/geode152026年10月22日 更新

Auto-search and summarize latest AI/agent papers.

中文简介正在准备中。当前显示原文说明。

mangowhoiscloud/geode152026年10月22日 更新

查看 mangowhoiscloud 的全部技能

报告此技能的问题