$ show shanraisshan/claude-code-best-practice
This repository is a comprehensive knowledge base and reference implementation for Claude Code best practices, curated by Shayan Rais. It is not a standalone application but rather a living documentation and configuration library that demonstrates how to effectively use Claude Code CLI through agents, skills, commands, hooks, and workflows. The core architecture follows a Command → Agent → Skill orchestration pattern, with working examples such as a weather reporter system and a structured RPI (Research-Plan-Implement) development workflow. The repository includes reusable configuration patterns (YAML frontmatter schemas for agents and skills), a cross-platform Python hook script for lifecycle events, detailed changelogs that track drift against official Claude Code documentation, and extensive reference guides covering settings, environment variables, MCP servers, and startup flags. While primarily a documentation and reference project, it contains runnable Claude Code configurations that can be directly adopted or adapted by other projects.
The LLM identified 3 files worth highlighting for reuse:
A Python script that handles 30+ Claude Code lifecycle events (session start/stop, tool use, permission requests, etc.) with platform-specific audio playback (afplay on macOS, paplay on Linux, winsound on Windows). It is configurable via a JSON configuration file and demonstrates a clean, extensible pattern for adding deterministic behavior to Claude Code sessions. This script is self-contained, requires no internal imports from the repo, and can be extracted and reused in any Claude Code project with minimal modification.
A Claude Code command that orchestrates a structured planning phase using multiple specialist subagents (requirement-parser, product-manager, senior-software-engineer, technical-cto-advisor, constitutional-validator, documentation-analyst-writer). It demonstrates a reusable pattern for breaking complex development tasks into a phased pipeline with role-based agents, each with specific responsibilities and context isolation. The pattern can be adapted to any project by replacing the agent definitions and adjusting the workflow steps.
A skill definition that demonstrates the progressive disclosure pattern for Claude Code skills: a concise SKILL.md with YAML frontmatter (name, description, allowed-tools, model, context) and markdown body, paired with a reference.md (detailed API documentation) and examples.md (usage examples). This pattern allows skills to be loaded on-demand without bloating the context window, and the structure is reusable for encapsulating any domain knowledge or tool usage pattern.