cwc-workshops
anthropics/cwc-workshops
Educational workshop materials and practical examples from Anthropic's Code with Claude sessions, covering agent architecture, evaluations, and memory primitives.
2k 557Apache-2.0Updated 2026-06-26
76
GreatOverview
This repository contains comprehensive workshop guides, codebases, and tutorials from Anthropic's Code with Claude events. It serves as an educational curriculum for developers learning how to build, evaluate, and optimize AI agents using Claude Code, Model Context Protocol (MCP), and Claude Managed Agents. The modules range from model selection strategies and multi-agent decomposition to production-ready research desks and memory persistence patterns.
Capabilities
- ▸Multi-agent decomposition and coordination
- ▸Eval-driven agent development and testing loops
- ▸Memory store integration and dreaming services
- ▸Model auditing and cost-performance sweeping
- ▸Tool and MCP server configuration
Best for
Learning how to design and compose multi-agent systems using skills and MCP, Implementing evaluation-driven agent development with programmatic grading, Building agents with cross-session persistence and memory consolidation, Configuring automated research desks and production-grade incident dashboards
Works with
Claude Code
Evoa Score breakdown= Σ (score × weight)
76Task 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%85 → +12.8
実装・指示の品質。 — AIによるSKILL.md/README解析
Maintenance15%85 → +12.8
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%31 → +3.7
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%90 → +9.0
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%87 → +7.0
コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）
Compatibility5%25 → +1.3
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 total76.0 / 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
The repository contains code examples and workshop materials intended for educational purposes. Users should handle API keys securely and review sandbox configurations when running automated agent scripts.
Categories
Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.