Community Скиллы Разработка

Claude Code Guide

Claude Code
Открыть источник ↗ GitHub ↗
Установка 
npx claude-code-templates@latest --skill ai-research/claude-code-guide

Описание

claude-code-guide — скилл эффективного использования Claude Code: конфигурация — шаблоны настройки, промтинг — стратегии и ключевые слова для мышления, отладка — техники диагностики с агентом, практики — лучшие подходы к взаимодействию. Для разработчиков, желающих получать от Claude Code максимум вместо поверхностного использования.

Что умеет:
— настраивать Claude Code по шаблонам;
— применять стратегии промтинга;
— отлаживать с помощью агента;
— использовать лучшие практики взаимодействия.

Claude Code Guide

Purpose

To provide a comprehensive reference for configuring and using Claude Code (the agentic coding tool) to its full potential. This skill synthesizes best practices, configuration templates, and advanced usage patterns.

Configuration (CLAUDE.md)

When starting a new project, create a CLAUDE.md file in the root directory to guide the agent.

Template (General)


# Project Guidelines

## Commands

- Run app: `npm run dev`
- Test: `npm test`
- Build: `npm run build`

## Code Style

- Use TypeScript for all new code.
- Functional components with Hooks for React.
- Tailwind CSS for styling.
- Early returns for error handling.

## Workflow

- Read `README.md` first to understand project context.
- Before editing, read the file content.
- After editing, run tests to verify.

Advanced Features

Thinking Keywords

Use these keywords in your prompts to trigger deeper reasoning from the agent:

  • “Think step-by-step”
  • “Analyze the root cause”
  • “Plan before executing”
  • “Verify your assumptions”

Debugging

If the agent is stuck or behaving unexpectedly:

  • Clear Context: Start a new session or ask the agent to “forget previous instructions” if confused.
  • Explicit Instructions: Be extremely specific about paths, filenames, and desired outcomes.
  • Logs: Ask the agent to “check the logs” or “run the command with verbose output”.

Best Practices

  • Small Contexts: Don’t dump the entire codebase into the context. Use grep or find to locate relevant files first.
  • Iterative Development: Ask for small changes, verify, then proceed.
  • Feedback Loop: If the agent makes a mistake, correct it immediately and ask it to “add a lesson” to its memory (if supported) or CLAUDE.md.

Reference

Based on Claude Code Guide by zebbern.