moai-cc-memory
について
このスキルは、Claude Codeセッション向けにメモリ管理、コンテキスト持続性、ナレッジ保持機能を提供します。セッションのメモリ管理やインタラクションを超えたコンテキストの持続、ナレッジ保持の最適化が必要な際にご利用ください。主な機能には、メモリクリーンアッププロセス、コンテキスト予算管理、持続性戦略が含まれます。
クイックインストール
Claude Code
推奨/plugin add https://github.com/modu-ai/moai-adkgit clone https://github.com/modu-ai/moai-adk.git ~/.claude/skills/moai-cc-memoryこのコマンドをClaude Codeにコピー&ペーストしてスキルをインストールします
ドキュメント
Claude Code Memory Management
Skill Metadata
| Field | Value |
|---|---|
| Skill Name | moai-cc-memory |
| Version | 2.0.0 (2025-11-11) |
| Allowed tools | Read, Bash, Grep |
| Auto-load | On demand when memory issues detected |
| Tier | Claude Code (Core) |
What It Does
Claude Code memory management, context persistence, and knowledge retention.
Key capabilities:
- ✅ Session memory management
- ✅ Context persistence strategies
- ✅ Knowledge retention optimization
- ✅ Memory cleanup processes
- ✅ Context budgeting
When to Use
- ✅ Managing session memory
- ✅ Persisting important context
- ✅ Optimizing knowledge retention
- ✅ Handling memory constraints
Core Memory Patterns
Memory Architecture
- Working Memory: Current session context
- Long-term Memory: Persistent knowledge storage
- Context Windows: Token budget management
- Memory Compression: Efficient information storage
- Retrieval Systems: Quick knowledge access
Management Strategies
- Context Seeding: Strategic context injection
- Memory Consolidation: Knowledge organization
- Forgetting Policies: Outdated content removal
- Prioritization: Important content retention
- Cleanup Automation: Memory maintenance
Dependencies
- Claude Code session system
- File-based persistence
- Context management framework
- Memory optimization tools
Works Well With
moai-cc-skills(Knowledge capsules)moai-context7-integration(External knowledge)moai-learning-optimizer(Retention optimization)
Changelog
- v2.0.0 (2025-11-11): Added complete metadata, memory management patterns
- v1.0.0 (2025-10-22): Initial memory management
End of Skill | Updated 2025-11-11
GitHub リポジトリ
関連スキル
evaluating-llms-harness
テストThis Claude Skill runs the lm-evaluation-harness to benchmark LLMs across 60+ standardized academic tasks like MMLU and GSM8K. It's designed for developers to compare model quality, track training progress, or report academic results. The tool supports various backends including HuggingFace and vLLM models.
sglang
メタSGLang is a high-performance LLM serving framework that specializes in fast, structured generation for JSON, regex, and agentic workflows using its RadixAttention prefix caching. It delivers significantly faster inference, especially for tasks with repeated prefixes, making it ideal for complex, structured outputs and multi-turn conversations. Choose SGLang over alternatives like vLLM when you need constrained decoding or are building applications with extensive prefix sharing.
cloudflare-turnstile
メタThis skill provides comprehensive guidance for implementing Cloudflare Turnstile as a CAPTCHA-alternative bot protection system. It covers integration for forms, login pages, API endpoints, and frameworks like React/Next.js/Hono, while handling invisible challenges that maintain user experience. Use it when migrating from reCAPTCHA, debugging error codes, or implementing token validation and E2E tests.
langchain
メタLangChain is a framework for building LLM applications using agents, chains, and RAG pipelines. It supports multiple LLM providers, offers 500+ integrations, and includes features like tool calling and memory management. Use it for rapid prototyping and deploying production systems like chatbots, autonomous agents, and question-answering services.
