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.
From zero to pro with Claude Code. In-depth guides and tips you can apply today.
8 articles · 33 tips
How I turned an Agentic AI pattern into a reusable Claude Code skill with evidence-based evaluation.
Practical guide to Claude Code hooks: 3 hook types, 5 essential hooks, advanced patterns and common pitfalls. With copy-paste ready examples.
Skills are the fastest way to create repeatable workflows in Claude Code. A markdown file, a slash command, and predictable steps with human intervention.
Learn how to connect Claude Code with Playwright and Notion via MCP to create an automated UI and code review system.
Learn to create and manage subagents in Claude Code. Divide complex tasks, avoid context contamination, and scale your AI development.
The definitive Claude Code guide (2026). Installation, CLAUDE.md configuration, hooks, skills, subagents, and professional workflows for developers.
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).
Enable /voice, hold Space and speak. Claude Code transcribes in streaming with development-optimized vocabulary.
Use /rename and /color to give your Claude Code sessions visual identity. Name + color = find any session instantly.
A Claude Code plugin isn't anything new. It's packaging skills, subagents, hooks, and MCP into a shareable format with a single command.
Control Claude Code from Telegram or Discord with Channels. Text it from your phone, it executes in your terminal, and replies through the same channel.
Control your Claude Code session from your phone with Remote Control. Step-by-step guide with claude --rc, server mode, and QR code.
Opus 4.6 includes 1M context tokens on Max, Team, and Enterprise plans. 5x more than before, at no extra cost. But more context doesn't mean better results.
Use /btw to ask quick questions while Claude Code is working. No interruption, no history pollution.
Create specialized agents as Markdown files and launch sessions with claude --agent. Each agent has its own system prompt, tools, and model.
A Stop hook + a script that checks the focused app = sound only when you're in another app. Zero annoying notifications.
With the -p flag, Claude Code becomes a headless agent you can schedule with cron. Combined with --allowedTools, you get autonomous AI automation.
Claude Code writes notes about your project as you work and reads them at the start of every session — remembering build commands, debugging patterns, and architecture decisions.
Most CLAUDE.md files are packed with information Claude can already infer. Learn to document what actually matters: business decisions, team conventions, and the why behind every rule.