claude-code-handbook

Name: claude-code-handbook
Rating: 74 (1 reviews)
Author: ThamJiaHe

MCP Server

ThamJiaHe/claude-code-handbook

The Claude Code Handbook is a comprehensive, continuously updated guide and skills catalog for mastering Claude Code, prompt engineering, and Model Context Protocol integrations.

198 22MITUpdated 2026-04-19

Good

View on GitHub Open source file

Overview

This repository provides extensive documentation, guides, templates, and a curated catalog of over 100 skills for Claude Code v2.1.83 and Claude 4.x models (Opus, Sonnet, Haiku). It covers advanced agentic features such as hook events, agent teams, subagents, adaptive thinking, and MCP configurations, designed to help developers and power users maximize their AI engineering workflows.

Capabilities

▸Claude Code mastery and CLI usage
▸Prompt engineering framework and optimization
▸Agent teams and multi-agent coordination setup
▸Hook configuration (session, tool use, cwd changes)
▸Skills catalog navigation and curation

Best for

Learning advanced prompt engineering techniques for Claude models, Configuring Claude Code CLI, hooks, rules, and subagents, Discovering and implementing curated skills and plugins, Integrating Model Context Protocol (MCP) servers into developer workflows

Works with

Claude CodeChatGPT

Evoa Score breakdown= Σ (score × weight)

Task usefulness20%88 → +17.6

実タスクにどれだけ役立つか（機能の豊富さ・用途の明確さ）。 — AIによるcapabilities/use-cases解析

Code quality15%90 → +13.5

実装・指示の品質。 — AIによるSKILL.md/README解析

Maintenance15%70 → +10.5

リポジトリがどれだけ活発に保守されているか。 — GitHub 最終push日時の新しさ

Documentation12%40 → +4.8

ドキュメントの充実度・分かりやすさ。 — README/独自要約の情報量

Security15%80 → +12.0

危険・不審な挙動が無いか。 — AIによるセキュリティレビュー

Originality10%85 → +8.5

ありふれたラッパーではない独自性。 — AIによる独自性判定

Popularity8%60 → +4.8

コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）

Compatibility5%50 → +2.5

対応AIエージェントの広さ。 — AIによる対応エージェント判定

Weighted total74.2 / 100

ライセンス不明/制限あり（Red）のSkillは総合スコアに0.85倍の補正を適用します。ランキングはこのScoreのみで決まり、広告で変わりません。算出方法の詳細 →

Security considerations

Standard developer documentation repository with no direct execution risks, though custom hook scripts or plugins should be reviewed before running locally.