Context Compression

用于会话内上下文压缩:当用户要压缩长对话、做运行摘要、做 compaction、减少 token 消耗但保持任务连续性时使用。Prefer `memory-systems` for 跨会话长期记忆,Prefer `context-fundamentals` for 上下文工程基础概念;Do not use for 需要跨会话持久化事实或偏好存储的问题。

hebertzhu fd2d3a2 1.3 KB Updated

File contents

context-compression

Intent

  • 用于会话内上下文压缩:当用户要压缩长对话、做运行摘要、做 compaction、减少 token 消耗但保持任务连续性时使用。Prefer memory-systems for 跨会话长期记忆,Prefer context-fundamentals for 上下文工程基础概念;Do not use for 需要跨会话持久化事实或偏好存储的问题。

Default operating pattern

  1. Separate short-term context from durable memory or documentation.
  2. Define the minimum information model that must survive the current session.
  3. Choose storage, compression, retrieval, and update boundaries deliberately.
  4. Call out trade-offs, failure modes, and evaluation signals.
  5. Recommend the smallest next architecture or workflow improvement.

Pack fit

  • Included in: context-systems
  • Keep examples generic, privacy-safe, and portable across hosts.

Boundary

  • Do not present a short summary as a durable memory system.

hebertzhu/agent-foundry/tree/main/skills/context-compression commit fd2d3a218a

Frequently asked questions

npx skillmds@latest add hebertzhu/context-compression