REA
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
Claude skill: refactor code to reduce cyclomatic complexity
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/skills/saurabhkumar8112-cyclomatic-complexity-skill)在同一工作中把 AI 连到服务的 MCP
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
Codebase intelligence for TypeScript and JavaScript, exposed as structured MCP analysis tools.
MCP server for terminal commands, file operations, and process management
同类工作,排序与 Skill 列表相同
| 本项 cyclomatic-complexity-skill | rea | andrej-karpathy-skills | graphify | MoneyPrinterTurbo | |
|---|---|---|---|---|---|
| 作者 | saurabhkumar8112 | morluto | multica-ai | Graphify-Labs | harry0703 |
| Skill 数 | 1 | 1 | 1 | 1 | 1 |
| GitHub 星标 | 409 | 465,460 | 233,910 | 149,364 | 144,149 |
| 最近代码更新 | 2026年8月27日 | 2026年11月17日 | 2026年4月20日 | 2026年11月17日 | 2026年11月17日 |
| 许可证 | Apache-2.0 | MIT | – | Apache-2.0 | MIT |
saurabhkumar8112 提供的 1 个 Skill(指令集),AI 读取后照做 · 不是 MCP server
MCP = 手
把 AI 连到外部服务或数据,例如读取 Notion 或开发票。需要有程序或服务器在运行。
Skill = 手册
教 AI 怎么做某项工作的文本文件,不连接任何服务。
有些会重叠:少数 Skill 带有调用工具的脚本,少数 MCP 只提供知识。请从你想完成的工作出发。
Claude CodeClaude (เว็บ/แอป)
依据开发者 README 和 repo 中的文件夹
GitHub account saurabhkumar8112 (person), 10 years old
★ 409 stars, few users so far · code last changed 2026年8月27日
No, plain text files the AI reads and follows
No scripts, so it does not go online by itself
No hooks or writes to machine settings found
Checked automatically from the repo files at commit 567886f (read only, nothing was run). Not a safety guarantee: read it and decide for yourself
第一步:你用哪个 AI?
选择你用的应用,本页只显示该应用的安装方法
Uploading to claude.ai would fail: the description is over 200 characters (499). Use "Let the AI install it" instead
复制这句话,粘贴到 Claude Code 的对话中
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
重新打开 Claude Code,输入 /cyclomatic-complexity,或直接提出相关任务,Claude 会自动选用
Checked against official docs 2026年11月12日 · Source: code.claude.com
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
正在检查命令 · 通过后才会显示复制按钮
摘自开发者 README,会下载并运行开发者的代码
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
正在检查命令 · 通过后才会显示复制按钮
ChatGPT 桌面应用内置 Codex,Codex 从 ~/.agents/skills 文件夹读取 Skill
在 ChatGPT 桌面应用中打开 Codex,把这句话粘贴到对话中
The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
把 cyclomatic-complexity 文件夹放到 ~/.agents/skills/cyclomatic-complexity
~ 是你的主文件夹($HOME)
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
正在检查命令 · 通过后才会显示复制按钮
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
不能使用你自己安装的 Skill,只能使用目录中插件自带的 Skill
想在 ChatGPT 中使用这个 Skill,请按上面的方法使用 ChatGPT 桌面应用
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
复制这句话,粘贴到 Codex 的对话中 · 适用于 ChatGPT 桌面应用中的 Codex、Codex CLI 和 IDE 扩展
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Codex 会自动发现新安装的 Skill;如果没有出现,请重启 Codex · 使用方法:在 ChatGPT 中输入 @ 并选择 Skill · 在 Codex CLI 或 IDE 扩展中运行 /skills,或输入 $ 加 Skill 名称
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
正在检查命令 · 通过后才会显示复制按钮
复制这句话,粘贴到 Cursor 的对话中
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
在 Cursor 的 Agent 聊天中输入 / 并选择 cyclomatic-complexity
Checked against official docs 2026年11月12日 · Source: cursor.com
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
正在检查命令 · 通过后才会显示复制按钮
适用于其他能读取 Skill 的应用。这句话列出了 Claude Code、Codex 和 Cursor 的路径,AI 会按你的应用选择 · Copy this sentence into the app’s chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Checked against official docs 2026年11月12日 · Source: code.claude.com, learn.chatgpt.com, cursor.com
其他支持 Agent Skills 的应用(如 Gemini CLI、GitHub Copilot)使用不同文件夹,请查看该应用的指南,再把含 SKILL.md 的文件夹复制过去。
已于 2026年11月11日 对照 Claude Code、Codex 和 Cursor 官方指南核实 skill 文件夹
以下文字来自开发者的 repo,不是 PopNx MCP 的指令
3,044 个字符 · 在 GitHub 打开完整文件
---
name: cyclomatic-complexity
description: Refactor code to reduce cyclomatic complexity so it stays readable, maintainable, and aligned with the long-term vision of the codebase, not just optimized for AI comprehension. Use whenever the user asks to refactor, simplify, clean up, or review code quality; mentions complexity, maintainability, readability, spaghetti code, deeply nested logic, or god functions; or asks to check AI-generated code before merging. Also use proactively after writing any nontrivial function with heavy branching.
---
# Cyclomatic Complexity
Purpose: AI-written code often works but branches like a jungle. This skill: measure complexity, refactor hotspots, keep code human-maintainable.
## Measure first
CC = decision points + 1. Decision points: `if`, `else if`, `case`, loops, `catch`, ternary, `&&`, `||` in conditions.
Project linter config wins. If eslintrc, radon config, sonar config, or similar sets a complexity threshold, use that. No config: use defaults below.
Thresholds:
- 1-5: fine, leave alone
- 6-10: watch, refactor if touching anyway
- 11-15: refactor now
- 15+: must split, no debate
Prefer real tools over eyeballing when environment allows:
- Python: `radon cc -s -a <path>`
- JS/TS: eslint `complexity` rule
- Go: `gocyclo`
- Polyglot: `lizard <path>`
No tool available: count manually, per function, show the count.
## Refactor tactics, in order of preference
1. **Guard clauses.** Invert conditions, return early, kill nesting.
2. **Extract function.** Each extracted piece gets a name that says what, not how. Names are documentation.
3. **Lookup table / map** instead of if-else or switch chains.
4. **Named predicates.** `if (isEligibleForRefund(order))` beats a 4-clause boolean soup.
5. **Polymorphism / strategy** for switch-on-type. Only when the switch appears in 2+ places.
6. **Flatten loops.** Extract loop body, use continue instead of nested if.
## Hard rules
- Preserve behavior. Run tests before and after. No tests: say so, suggest adding, refactor conservatively.
- Don't game the metric. A dense one-liner hiding 6 branches is worse than the honest if-chain it replaced. Complexity should move into well-named units, not disappear into cleverness.
- Don't break public APIs or exported signatures without asking.
- Small functions with clear names > few functions with comments explaining sections.
- One responsibility per function. If the name needs "and", split.
## Workflow
1. Measure all touched functions, rank by CC descending.
2. Report hotspots with numbers before touching anything.
3. Refactor worst first, one function at a time.
4. Re-measure. Show before/after table: function, CC before, CC after.
5. Verify: tests pass, behavior unchanged, diff reviewable.
## Output format
End every refactor with:
```
## Complexity report
| Function | Before | After |
|----------|--------|-------|
| parseOrder | 14 | 4 |
Extracted: validateHeader, resolveDiscount
Behavior verified: <how>
```
Keep prose minimal. Numbers and diffs do the talking.
提问、分享技巧或报告无法使用。按“有帮助”数量排序。