context-window-management
About
This Claude Skill provides strategies for managing LLM context windows, including techniques like summarization, trimming, and routing to handle token limits and avoid context rot. Use it when you need to engineer long contexts, prioritize information, or maintain conversation quality within token constraints. It offers capabilities for token counting, context prioritization, and curating the most relevant information for your application.
Quick Install
Claude Code
Recommended/plugin add https://github.com/majiayu000/claude-skill-registrygit clone https://github.com/majiayu000/claude-skill-registry.git ~/.claude/skills/context-window-managementCopy and paste this command in Claude Code to install this skill
Documentation
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 Repository
Related Skills
sglang
MetaSGLang 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.
evaluating-llms-harness
TestingThis 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.
langchain
MetaLangChain 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.
llamaguard
OtherLlamaGuard is Meta's 7-8B parameter model for moderating LLM inputs and outputs across six safety categories like violence and hate speech. It offers 94-95% accuracy and can be deployed using vLLM, Hugging Face, or Amazon SageMaker. Use this skill to easily integrate content filtering and safety guardrails into your AI applications.