Repolode
shanraisshan

shanraisshan/claude-code-best-practice

A curated, continuously updated best-practices guide and reference collection for using Anthropic's Claude Code, covering subagents, commands, skills, hooks, memory and workflows.

Stars
67,813
Forks
6,753
Open issues
25
Last commit
10 hours ago

What is it?

This repository is a structured guide to Claude Code, Anthropic's agentic coding tool. It organizes every major concept, including subagents, slash commands, skills, hooks, MCP servers, settings, memory files and sessions, into a table that links each feature to its location in a project and to a best-practice write-up and a working implementation.

Beyond the feature reference, it collects development workflows that combine commands, agents and skills into repeatable pipelines, such as research, plan, execute, review and ship. It also covers cross-model setups that call Codex, Gemini or other providers from Claude Code through plugins, MCP or routers, and it indexes community skill and agent collections plus a long list of practical tips attributed to their authors.

The content is aimed at developers who already use Claude Code and want concrete conventions for CLAUDE.md, context management, planning and session handling, rather than a general introduction to AI coding.

Key features

  • 01Reference table covering subagents, commands, skills, hooks, MCP servers, settings and memory
  • 02Linked best-practice articles and implementation examples for key features
  • 03Orchestration pattern chaining commands, agents and skills
  • 04Cross-model workflows using Codex, Gemini and other providers via plugins, MCP or routers
  • 05Curated index of community skill and agent collections
  • 06Practical tips on context management, planning and session handling

Use cases

  • Learning how to structure CLAUDE.md, rules and settings for a team's Claude Code projects
  • Choosing between subagents, commands and skills for a new automation
  • Setting up a repeatable plan-execute-review workflow with Claude Code
  • Finding community skill or agent libraries to adapt for your own repository

Quick start

  1. 1

    Read the How to Use section of the README

  2. 2

    Browse the best-practice guides and implementation examples in the repo

Things to know

  • This is a collection of guides and reference examples rather than installable software.
  • Content tracks fast-moving Claude Code features, and many listed features are marked beta.

Topics

FAQ

What is claude-code-best-practice?
A curated, continuously updated best-practices guide and reference collection for using Anthropic's Claude Code, covering subagents, commands, skills, hooks, memory and workflows. This repository is a structured guide to Claude Code, Anthropic's agentic coding tool. It organizes every major concept, including subagents, slash commands, skills, hooks, MCP servers, settings, memory files and sessions, into a table that links each feature to its location in a project and to a best-practice write-up and a working implementation.
Is claude-code-best-practice free to use? What license does it have?
claude-code-best-practice is open source under the MIT license. Check the license terms before using it in commercial products.
Is claude-code-best-practice still maintained?
Actively maintained. The last commit to claude-code-best-practice was on Oct 20, 2026.
What can I use claude-code-best-practice for?
Learning how to structure CLAUDE.md, rules and settings for a team's Claude Code projects Choosing between subagents, commands and skills for a new automation Setting up a repeatable plan-execute-review workflow with Claude Code Finding community skill or agent libraries to adapt for your own repository
How do I install claude-code-best-practice?
Read the How to Use section of the README Browse the best-practice guides and implementation examples in the repo
Where can I get claude-code-best-practice?
The source code and installation instructions are on GitHub: https://github.com/shanraisshan/claude-code-best-practice

Summary generated by AI from the project's README. GitHub stats refresh daily.

Related projects