coding-rules — for Claude Code coding-rules, agentic-code, community, for Claude Code, ide skills, agent-skills, agentic-ai, agentic-workflow, ai-agents, developer-tools

v1.0.0

关于此技能

适用场景: Ideal for AI agents that need language-specific references. 本地化技能摘要: Agentic coding framework powered by AGENTS.md — systematic, test-first workflows with quality gates for Cursor, Codex, Gemini CLI, and AI coding agents. It covers agent-skills, agentic-ai, agentic-workflow workflows.

功能特性

Language-Specific References
For language-specific rules, also read:
TypeScript : references/typescript.md
✅ Aggressive Refactoring
Continuously improve code structure and readability

# 核心主题

shinpr shinpr
[38]
[3]
更新于: 3/23/2026

Killer-Skills Review

Decision support comes first. Repository text comes second.

Reference-Only Page Review Score: 10/11

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 Quality floor passed for review
Review Score
10/11
Quality Score
51
Canonical Locale
en
Detected Body Locale
en

适用场景: Ideal for AI agents that need language-specific references. 本地化技能摘要: Agentic coding framework powered by AGENTS.md — systematic, test-first workflows with quality gates for Cursor, Codex, Gemini CLI, and AI coding agents. It covers agent-skills, agentic-ai, agentic-workflow workflows.

核心价值

推荐说明: coding-rules helps agents language-specific references. Agentic coding framework powered by AGENTS.md — systematic, test-first workflows with quality gates for Cursor, Codex, Gemini CLI, and AI coding agents.

适用 Agent 类型

适用场景: Ideal for AI agents that need language-specific references.

赋予的主要能力 · coding-rules

适用任务: Applying Language-Specific References
适用任务: Applying For language-specific rules, also read:
适用任务: Applying TypeScript : references/typescript.md

! 使用限制与门槛

  • 限制说明: Don't write code for hypothetical future requirements
  • 限制说明: Keep codebase lean and focused on current needs
  • 限制说明: No Historical Information : Do not record development history in comments

Why this page is reference-only

  • - Current locale does not satisfy the locale-governance contract.

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.

精选合集复核

这个技能已进入哪些精选合集的复核范围

这部分展示的是 Killer-Skills 如何在精选合集里收录、复核和维护这个技能,帮助你看到它在真实选择路径中的位置,而不只是继续放大上游 README。

已复核合集

优先安装的开发工作流工具

复核于 2026-04-17

已于 2026-04-17 按编码工作流适配度、安装清晰度、评审与测试价值以及发布护栏完成复核。现在这页被重新定位为“安装优先”的开发工作流入口,而不是模糊的工具盘点。

之所以优先强化这页,是因为带着开发意图进来的用户,通常需要的是一套能先安装、验证,并在真实编码闭环里证明可用的工具链,再决定是否在团队内标准化。

收录 12 项 由 Killer-Skills 内容审核流程维护,重点核验安装、文档与开发工作流可用性。
已复核合集

优先安装的 Codex 工作流工具

复核于 2026-04-17

已于 2026-04-17 按安装清晰度、维护者可靠性、仓库评审覆盖度与协作衔接就绪度完成复核。我们保留的是那些能帮助 Codex 操作员从首次安装走向稳定日常使用的工具。

来到这页的大多数用户已经知道自己要在 Codex 里工作。他们下一步需要的不是更大的集成目录,而是一份围绕评审、协作衔接与终端执行场景缩小过的候选清单。

收录 10 项 由 Killer-Skills 编辑审查与每月合集复查共同维护。
已复核合集

优先安装的 Agent 工作流自动化工具

复核于 2026-04-17

已于 2026-04-17 按工作流自动化适配度、安装清晰度、团队协作适配和生产可用性完成复核。现在这页被改造成“安装优先”的入口,而不是泛化自动化工具清单。

之所以优先强化这页,是因为自动化意图用户应该尽快从比较进入安装与验证,而不是被困在宽泛的工具调研里。

收录 9 项 由 Killer-Skills 内容审核流程维护,重点核验安装、文档与工作流可用性。
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-rules 是什么?

适用场景: Ideal for AI agents that need language-specific references. 本地化技能摘要: Agentic coding framework powered by AGENTS.md — systematic, test-first workflows with quality gates for Cursor, Codex, Gemini CLI, and AI coding agents. It covers agent-skills, agentic-ai, agentic-workflow workflows.

如何安装 coding-rules?

运行命令:npx killer-skills add shinpr/agentic-code/coding-rules。支持 Cursor、Windsurf、VS Code、Claude Code 等 19+ IDE/Agent。

coding-rules 适用于哪些场景?

典型场景包括:适用任务: Applying Language-Specific References、适用任务: Applying For language-specific rules, also read:、适用任务: Applying TypeScript : references/typescript.md。

coding-rules 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-rules 有哪些限制?

限制说明: Don't write code for hypothetical future requirements;限制说明: Keep codebase lean and focused on current needs;限制说明: No Historical Information : Do not record development history in comments。

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 shinpr/agentic-code/coding-rules。CLI 会自动识别 IDE 或 AI Agent 并完成配置。

  3. 3. 开始使用技能

    coding-rules 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-rules

安装 coding-rules,这是一款面向AI agent workflows and automation的 AI Agent Skill。查看评审结论、使用场景与安装路径。

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

Development Rules

Language-Specific References

For language-specific rules, also read:

Basic Principles

Aggressive Refactoring

  • Continuously improve code structure and readability
  • Make code changes in small, safe steps
  • Prioritize maintainability over initial implementation speed

Unused "Just in Case" Code - YAGNI principle

  • Don't write code for hypothetical future requirements
  • Delete unused functions, variables, and imports immediately
  • Keep codebase lean and focused on current needs

Comment Writing Rules

  • Function Description Focus: Describe what the code "does", not how it works
  • No Historical Information: Do not record development history in comments
  • Timeless: Write only content that remains valid whenever read
  • Conciseness: Keep explanations to necessary minimum
  • Explain "Why": Comments should explain reasoning, not implementation details

Function Design

Parameter Management

  • 0-2 parameters maximum: Use structured data (object/struct/dict) for 3+ parameters
    ✅ Good: createUser({name, email, role})
    ❌ Avoid: createUser(name, email, role, department, startDate)
    
    Note: Use your language's idiomatic approach for grouping parameters

Dependency Injection

  • Inject external dependencies explicitly: Ensure testability and modularity
  • Pass dependencies as parameters (functions, constructors, or other language-appropriate mechanisms)
  • Avoid global state, direct instantiation, or implicit dependencies
  • Prefer interfaces/contracts over concrete implementations where applicable

Error Handling

Absolute Rule: Error suppression prohibited. All errors must have log output and appropriate handling.

Layer-Specific Error Handling

  • Presentation Layer: Convert errors to user-friendly messages, log excluding sensitive information
  • Business Layer: Detect business rule violations, propagate domain-specific errors
  • Data Layer: Convert technical errors to domain errors

Structured Logging and Sensitive Information Protection Never include sensitive information in logs:

  • Passwords, tokens, API keys, secrets
  • Credit card numbers, personal identification numbers
  • Any personally identifiable information (PII)

Asynchronous Error Handling

  • Use appropriate error handling mechanisms for your language
  • Always log and appropriately propagate errors
  • Set up global error handlers where applicable

Clean Code Principles

Recommended Practices

  • Delete unused code immediately
  • Remove debug statements and temporary logging
  • Use meaningful variable and function names
  • Keep functions small and focused on single responsibility

Avoid These Practices

  • Commented-out code (use version control for history)
  • Magic numbers without explanation
  • Deep nesting (prefer early returns)
  • Functions that do multiple unrelated things

Refactoring Techniques

Basic Policy

  • Small Steps: Maintain always-working state through gradual improvements
  • Safe Changes: Minimize the scope of changes at once
  • Behavior Guarantee: Ensure existing behavior remains unchanged while proceeding

Implementation Procedure

  1. Understand Current State
  2. Make Gradual Changes
  3. Verify Behavior
  4. Final Validation

Priority Order

  1. Duplicate Code Removal
  2. Large Function Division
  3. Complex Conditional Branch Simplification
  4. Architecture Improvement

Performance Considerations

General Principles

  • Measure before optimizing (avoid premature optimization)
  • Focus on algorithmic complexity over micro-optimizations
  • Consider memory usage, especially with large datasets
  • Use appropriate data structures for the use case

Resource Management

  • Properly close files, connections, and other resources
  • Be mindful of memory leaks in long-running applications
  • Use efficient algorithms for data processing

Code Organization

File Structure

  • Group related functionality together
  • Separate concerns (business logic, data access, presentation)
  • Use consistent naming conventions throughout the project
  • Keep configuration separate from business logic

Modularity

  • Write small, focused modules/functions
  • Minimize dependencies between modules
  • Use clear interfaces between components
  • Follow single responsibility principle

相关技能

寻找 coding-rules 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