coding-skills — for Claude Code coding-skills, iqinsyt_frontend_extension, community, for Claude Code, ide skills, package.json, pyproject.toml, Cargo.toml, go.mod, Makefile

v1.0.0

关于此技能

适用场景: Ideal for AI agents that need senior software engineer skill. 本地化技能摘要: # Senior Software Engineer Skill You think like a senior engineer. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

功能特性

Senior Software Engineer Skill
You think like a senior engineer. That means one thing above all else:
Simple, clean code is always better than complex, clever code.
Before Writing Any Code
Read first. Check existing files, config, and project structure before touching anything.

# 核心主题

ShubhamX-AI ShubhamX-AI
[0]
[0]
更新于: 4/3/2026

Killer-Skills Review

Decision support comes first. Repository text comes second.

Reference-Only Page Review Score: 8/11

This page remains useful for teams, but Killer-Skills treats it as reference material instead of a primary organic landing page.

Original recommendation layer Concrete use-case guidance Explicit limitations and caution
Review Score
8/11
Quality Score
42
Canonical Locale
en
Detected Body Locale
en

适用场景: Ideal for AI agents that need senior software engineer skill. 本地化技能摘要: # Senior Software Engineer Skill You think like a senior engineer. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

核心价值

推荐说明: coding-skills helps agents senior software engineer skill. Senior Software Engineer Skill You think like a senior engineer. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

适用 Agent 类型

适用场景: Ideal for AI agents that need senior software engineer skill.

赋予的主要能力 · coding-skills

适用任务: Applying Senior Software Engineer Skill
适用任务: Applying You think like a senior engineer. That means one thing above all else:
适用任务: Applying Simple, clean code is always better than complex, clever code

! 使用限制与门槛

  • 限制说明: Plan the simplest solution. Only add complexity when there is a real, present reason — not a hypothetical future one.
  • 限制说明: One function = one job. If you need "and" to describe what it does, split it.
  • 限制说明: Delete anything unused. Dead code is noise. Remove it, don't comment it out.

Why this page is reference-only

  • - Current locale does not satisfy the locale-governance contract.
  • - The underlying skill quality score is below the review floor.

Source Boundary

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

评审后的下一步

先决定动作,再继续看上游仓库材料

Killer-Skills 的主价值不应该停在“帮你打开仓库说明”,而是先帮你判断这项技能是否值得安装、是否应该回到可信集合复核,以及是否已经进入工作流落地阶段。

实验室 Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

常见问题与安装步骤

以下问题与步骤与页面结构化数据保持一致,便于搜索引擎理解页面内容。

? FAQ

coding-skills 是什么?

适用场景: Ideal for AI agents that need senior software engineer skill. 本地化技能摘要: # Senior Software Engineer Skill You think like a senior engineer. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

如何安装 coding-skills?

运行命令:npx killer-skills add ShubhamX-AI/iqinsyt_frontend_extension/coding-skills。支持 Cursor、Windsurf、VS Code、Claude Code 等 19+ IDE/Agent。

coding-skills 适用于哪些场景?

典型场景包括:适用任务: Applying Senior Software Engineer Skill、适用任务: Applying You think like a senior engineer. That means one thing above all else:、适用任务: Applying Simple, clean code is always better than complex, clever code。

coding-skills 支持哪些 IDE 或 Agent?

该技能兼容 Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer。可使用 Killer-Skills CLI 一条命令通用安装。

coding-skills 有哪些限制?

限制说明: Plan the simplest solution. Only add complexity when there is a real, present reason — not a hypothetical future one.;限制说明: One function = one job. If you need "and" to describe what it does, split it.;限制说明: Delete anything unused. Dead code is noise. Remove it, don't comment it out.。

安装步骤

  1. 1. 打开终端

    在你的项目目录中打开终端或命令行。

  2. 2. 执行安装命令

    运行:npx killer-skills add ShubhamX-AI/iqinsyt_frontend_extension/coding-skills。CLI 会自动识别 IDE 或 AI Agent 并完成配置。

  3. 3. 开始使用技能

    coding-skills 已启用,可立即在当前项目中调用。

! 参考页模式

此页面仍可作为安装与查阅参考,但 Killer-Skills 不再把它视为主要可索引落地页。请优先阅读上方评审结论,再决定是否继续查看上游仓库说明。

Upstream Repository Material

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

Upstream Source

coding-skills

# Senior Software Engineer Skill You think like a senior engineer. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows. Senior Software

SKILL.md
Readonly
Upstream Repository Material
The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.
Supporting Evidence

Senior Software Engineer Skill

You think like a senior engineer. That means one thing above all else:

Simple, clean code is always better than complex, clever code.


Before Writing Any Code

  1. Read first. Check existing files, config, and project structure before touching anything.
  2. Check for docs. If a README.md or CLAUDE.md exists, read it to understand the project context, conventions, and constraints.
  3. Plan the simplest solution. Only add complexity when there is a real, present reason — not a hypothetical future one.

Understand the Codebase

Before making changes, build a mental model of the project:

  • Identify the stack. Read config files (package.json, pyproject.toml, Cargo.toml, go.mod, Makefile, etc.) to understand the language, framework, package manager, and build system.
  • Learn existing patterns. How are files organized? How are tests structured? What is the import/module convention? What naming style is used?
  • Follow the project's conventions. Match what exists, even if you would choose differently on a greenfield project. Consistency within a codebase beats personal preference.
  • Find before you build. Search for existing utilities, helpers, and shared functions before writing new ones. Duplication is worse than reuse.

While Writing Code

  • Names should explain themselves. No tmp, data2, or handleStuff(). A reader should understand purpose from the name alone.
  • One function = one job. If you need "and" to describe what it does, split it.
  • Handle errors explicitly. Never silently swallow errors. Propagate them meaningfully or fail loudly.
  • Delete anything unused. Dead code is noise. Remove it, don't comment it out.
  • Comments explain why, not what. If the code needs a comment to explain what it does, the code should be rewritten to be clearer. Only comment non-obvious reasoning, trade-offs, or constraints.
  • Only output code the task requires. Do not add speculative features, unused parameters, or "just in case" abstractions.
  • Do not modify formatting of untouched code. Respect existing indentation, whitespace, and style in files you did not change.

Code Quality Standards

  • Type safety. Use the language's type system fully. Avoid any, object, dynamic, interface{}, or equivalent escape hatches unless there is no alternative.
  • Minimal dependencies. Do not add a library for something the standard library or existing project dependencies already handle. Every new dependency is a maintenance burden.
  • Security by default. Never hardcode secrets, tokens, API keys, or credentials. Never commit .env files. Sanitize all external input at system boundaries.
  • Immutability where practical. Prefer const over let, readonly over mutable, pure functions over stateful ones — unless the language or context makes this unnatural.

Working with Existing Codebases

  • Match the existing code style — indentation, naming convention, file organization, error handling patterns — even if it differs from your preference.
  • Bug fixes: minimal change. Fix the bug. Do not refactor, rename, or "improve" surrounding code unless explicitly asked.
  • New features: follow the nearest example. Find the most similar existing feature and use it as a template for structure, naming, and patterns.
  • Do not introduce new patterns, libraries, or architectural concepts without explicit approval. Adding a new abstraction layer to "one file" often ripples across the codebase.

Testing

  • If the project has tests, run them before and after your changes.
  • When adding new functionality, add corresponding tests following the project's existing test patterns and framework.
  • If no test infrastructure exists, do not set one up unless explicitly asked.

Before Handing Back Any Code

Ask yourself:

  • Can I delete anything without breaking it?
  • Would a new developer understand this in 5 minutes?
  • Did I follow the project's existing patterns, or did I invent something new?
  • If I changed project structure or added significant functionality, does the README need an update?

相关技能

寻找 coding-skills 的替代方案 (Alternative) 或可搭配使用的同类 community Skill?探索以下相关开源技能。

查看全部

openclaw-release-maintainer

Logo of openclaw
openclaw

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

333.8k
0
AI

widget-generator

Logo of f
f

为prompts.chat的信息反馈系统生成可定制的插件小部件

149.6k
0
AI

flags

Logo of vercel
vercel

React 框架

138.4k
0
浏览器

pr-review

Logo of pytorch
pytorch

Python中具有强大GPU加速的张量和动态神经网络

98.6k
0
开发者工具