Context Optimization
技能 已验证 活跃This skill should be used when the user asks to "optimize context", "reduce token costs", "improve context efficiency", "implement KV-cache optimization", "partition context", or mentions context limits, observation masking, context budgeting, or extending effective context capacity.
To teach users how to maximize LLM effectiveness and reduce costs by intelligently managing and optimizing the information within the context window.
功能
- Context compaction strategies
- Observation masking for verbose outputs
- KV-cache optimization for prompt stability
- Context partitioning for large tasks
- Token budget management and monitoring
使用场景
- Reducing token costs in long conversations or with large documents
- Improving agent latency by optimizing context efficiency
- Implementing production-grade agent systems at scale
- Handling complex tasks that push context window limits
非目标
- Implementing specific LLM models or inference engines
- Replacing prompt engineering; rather, it complements it
- Providing a direct API for automated context manipulation (focus is on guidance)
安装
请先添加 Marketplace
/plugin marketplace add muratcankoylan/Agent-Skills-for-Context-Engineering/plugin install Agent-Skills-for-Context-Engineering@context-engineering-marketplace质量评分
已验证类似扩展
Latent Briefing
75This skill should be used when the user asks to "share memory between agents", "KV cache compaction for multi-agent", "orchestrator worker context", "latent briefing", "reduce worker tokens", "cross-agent memory without summarization", or discusses Attention Matching compaction, recursive language models with workers, or token explosion in hierarchical agents.
Context Compression
100This skill should be used when the user asks to "compress context", "summarize conversation history", "implement compaction", "reduce token usage", or mentions context compression, structured summarization, tokens-per-task optimization, or long-running agent sessions exceeding context limits.
Init
100创建或优化存储库的 AGENTS.md 文件，提供最少、高信号的说明，涵盖代理无法从代码库推断的不可发现的编码约定、工具怪癖、工作流偏好和项目特定规则。在为新存储库设置代理说明或 Claude 配置时，当现有的 AGENTS.md 文件过长、通用或过时，当代理反复犯可避免的错误，或当存储库工作流发生变化且需要修剪代理配置时使用。应用可发现性过滤器—省略 Claude 可从 README、代码、配置或目录结构中学到的任何内容—并应用质量门，以验证每行是否仍然准确且具有操作意义。
Skill Template
99Template for creating new Agent Skills for context engineering. Use this template when adding new skills to the collection.
Digital Brain
99This skill should be used when the user asks to "write a post", "check my voice", "look up contact", "prepare for meeting", "weekly review", "track goals", or mentions personal brand, content creation, network management, or voice consistency.
Cost Mode
99成本意识强的 Claude Code 模式。通过强制执行简洁的响应、智能的模型路由和高效的工作流模式，将输出 token 减少 40-70%，并将总体成本降低 30-60%。保持完整的技术准确性。使用 /cost-mode 或“enable cost mode”激活。