This article explains the purpose and layered structure of the .claude/ directory in Claude Code projects, detailing what files belong in CLAUDE.md, settings.json, hooks, commands, skills, and agents, and how to organize project‑level versus user‑level configurations for reliable, maintainable AI‑assisted development.
The article explains how the .claude/ directory serves as Claude Code’s control center—detailing its two‑level structure, the role of CLAUDE.md, rules, commands, skills, agents, and settings.json, and provides a step‑by‑step guide to configure and extend it for team and personal workflows.
This guide explains the full structure and purpose of the .claude directory, covering project‑level and global configurations, the essential CLAUDE.md file, custom commands, modular rules, reusable skills, specialized agents, and the settings.json permission model, plus a step‑by‑step onboarding workflow.
This guide explains why VS Code needs a proxy for Google Gemini, then shows safe one‑line commands for macOS/Linux (using jq) and Windows (PowerShell) to edit settings.json, verify the change, and handle common SSL or GUI alternatives.
