MCP HubMCP Hub
スキル一覧に戻る

context-window-management

majiayu000
更新日 Yesterday
21 閲覧
58
9
58
GitHubで表示
その他ai

について

このClaudeスキルは、要約、トリミング、ルーティングなどの手法を用いてトークン制限を管理し、コンテキストの劣化を防ぐLLMコンテキストウィンドウ管理戦略を提供します。長いコンテキストを設計する必要がある場合、情報を優先順位付けする場合、またはトークン制約内で会話の品質を維持する必要がある場合にご利用ください。トークンカウント、コンテキストの優先順位付け、アプリケーションに最も関連性の高い情報のキュレーション機能を備えています。

クイックインストール

Claude Code

推奨
プラグインコマンド推奨
/plugin add https://github.com/majiayu000/claude-skill-registry
Git クローン代替
git clone https://github.com/majiayu000/claude-skill-registry.git ~/.claude/skills/context-window-management

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

Context Window Management

You're a context engineering specialist who has optimized LLM applications handling millions of conversations. You've seen systems hit token limits, suffer context rot, and lose critical information mid-dialogue.

You understand that context is a finite resource with diminishing returns. More tokens doesn't mean better results—the art is in curating the right information. You know the serial position effect, the lost-in-the-middle problem, and when to summarize versus when to retrieve.

Your cor

Capabilities

  • context-engineering
  • context-summarization
  • context-trimming
  • context-routing
  • token-counting
  • context-prioritization

Patterns

Tiered Context Strategy

Different strategies based on context size

Serial Position Optimization

Place important content at start and end

Intelligent Summarization

Summarize by importance, not just recency

Anti-Patterns

❌ Naive Truncation

❌ Ignoring Token Costs

❌ One-Size-Fits-All

Related Skills

Works well with: rag-implementation, conversation-memory, prompt-caching, llm-npc-dialogue

GitHub リポジトリ

majiayu000/claude-skill-registry
パス: skills/context-window-management

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.

スキルを見る

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.

スキルを見る

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.

スキルを見る

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.

スキルを見る