Evaluator-Optimizer in Claude Code: From Pattern to Skill
How I turned an Agentic AI pattern into a reusable Claude Code skill with evidence-based evaluation.
Claude Code
From zero to pro with Claude Code. In-depth guides and tips you can apply today.
8 articles · 33 tips
Articles
Claude Code Hooks: Practical Guide with Real Examples
Practical guide to Claude Code hooks: 3 hook types, 5 essential hooks, advanced patterns and common pitfalls. With copy-paste ready examples.
Claude Code Skills: Build Reusable Workflows with Custom Commands
Skills are the fastest way to create repeatable workflows in Claude Code. A markdown file, a slash command, and predictable steps with human intervention.
Automated Code Review with Claude Code, Playwright, and Notion (MCP)
Learn how to connect Claude Code with Playwright and Notion via MCP to create an automated UI and code review system.
Claude Code Subagents: Practical Guide with Real Agent Configs
Learn to create and manage subagents in Claude Code. Divide complex tasks, avoid context contamination, and scale your AI development.
Claude Code Guide: Professional Setup, Configuration & Workflows (2026)
The definitive Claude Code guide (2026). Installation, CLAUDE.md configuration, hooks, skills, subagents, and professional workflows for developers.
MCP in Claude Code: The Practical Setup Guide (2026)
Understand what the Model Context Protocol (MCP) is and how to use it in Claude Code to connect your LLM with real tools (GitHub, Linear, Databases).
Quick Tips
Claude Code Effort Level: Adjust Reasoning Depth on the Fly
Use /model + arrow keys to adjust effort on the fly. Or configure it permanently with effortLevel in settings or the CLAUDE_CODE_EFFORT_LEVEL environment variable.
Claude Code Permissions: Deny Rules, Modes & Wildcards
Deny rules always win. Modes change everything. And the Tool(specifier) syntax supports wildcards and gitignore patterns.
Run Shell Commands Without Leaving Claude Code
Type ! followed by any command to run it directly in your shell without leaving Claude Code. Use Ctrl+B for background processes.
The 6 Extension Points in Claude Code Everyone Confuses
Skills, Hooks, MCP, Sub-agents, Agent Teams, and Plugins: a quick map to know when to use each one.
Create Reusable Commands with Skills in Claude Code
Skills are markdown files that Claude Code executes as slash commands. Create a SKILL.md, invoke it with /name, and Claude follows the steps. Conversational, predictable, reusable.
Claude Code Fast Mode: How to Get 2.5x Faster Responses
Fast mode prioritizes speed over cost on Opus 4.6: up to 2.5x faster responses with the same intelligence. Learn how to toggle it with /fast.
Claude Code Context Window: Track Token Usage with /context
The /context command breaks down how many tokens each component of your session consumes, giving you full visibility into the context window before it fills up.
Claude Code Rewind: Undo Changes Instantly with Checkpoints
Every prompt creates an automatic checkpoint. If Claude breaks something, press Esc twice and rewind to any previous state in seconds.
Claude Code Status Line: Customize Your Terminal Status Bar
Claude Code lets you customize the bottom status bar with a shell script — think PS1, but for your AI coding session.