Claude 策略性压缩技能：智能管理上下文，提升AI编程效率与性能

strategic-compact by affaan-m/everything-claude-code

1,500 周安装量

102,100 GitHub Stars

GitHub

安装命令

npx skills add https://github.com/affaan-m/everything-claude-code --skill strategic-compact

AI/机器学习开发生产力

🇨🇳中文介绍

策略性压缩技能

建议在工作流的关键节点手动使用 /compact 命令，而非依赖随机的自动压缩。

何时激活

运行长时间会话，接近上下文限制时（20万+ tokens）
处理多阶段任务时（研究 → 规划 → 实施 → 测试）
在同一会话中切换不相关的任务时
完成一个重要里程碑并开始新工作时
当响应变慢或连贯性下降时（上下文压力）

为何选择策略性压缩？

自动压缩会在任意时间点触发：

经常在任务中途触发，丢失重要上下文
无法识别任务的逻辑边界
可能中断复杂的多步骤操作

在逻辑边界进行策略性压缩：

探索之后，执行之前 — 压缩研究上下文，保留实施计划
完成里程碑之后 — 为下一阶段提供全新起点
重大上下文切换之前 — 在不同任务开始前清理探索上下文

工作原理

suggest-compact.js 脚本在 PreToolUse（编辑/写入）时运行，并执行以下操作：

跟踪工具调用 — 统计会话中的工具调用次数
阈值检测 — 在可配置的阈值处给出建议（默认：50次调用）
定期提醒 — 达到阈值后，每25次调用提醒一次

钩子设置

添加到你的 ~/.claude/settings.json 文件中：

广告位招租

在这里展示您的产品或服务

触达数万 AI 开发者，精准高效

联系我们

阶段转换	是否压缩？	原因
研究 → 规划	是	研究上下文庞大；规划是提炼后的输出
规划 → 实施	是	规划已在 TodoWrite 或文件中；为代码释放上下文
实施 → 测试	可能	如果测试引用近期代码则保留；如果切换焦点则压缩
调试 → 下一个功能	是	调试痕迹会污染不相关工作的上下文
实施过程中	否	丢失变量名、文件路径和部分状态代价高昂
尝试失败的方法后	是	在尝试新方法前清理死胡同的推理过程

压缩后保留的内容

了解哪些内容会保留有助于你自信地进行压缩：

保留的内容	丢失的内容
CLAUDE.md 指令	中间推理和分析过程
TodoWrite 任务列表	你之前读取的文件内容
记忆文件（`~/.claude/memory/`）	多轮对话上下文
Git 状态（提交、分支）	工具调用历史和计数
磁盘上的文件	口头陈述的细微用户偏好

规划后压缩 — 一旦计划在 TodoWrite 中确定，就压缩以重新开始
调试后压缩 — 在继续之前清理错误解决上下文
不要在实施过程中压缩 — 为相关更改保留上下文
阅读建议 — 钩子告诉你何时，你决定是否
压缩前写入 — 在压缩前将重要上下文保存到文件或记忆中
使用 /compact 并附带摘要 — 添加自定义消息：/compact 接下来专注于实施认证中间件

长篇指南 — Token 优化部分
记忆持久化钩子 — 用于在压缩后保留状态
continuous-learning 技能 — 在会话结束前提取模式

🇺🇸English

Strategic Compact Skill

Suggests manual /compact at strategic points in your workflow rather than relying on arbitrary auto-compaction.

When to Activate

Running long sessions that approach context limits (200K+ tokens)
Working on multi-phase tasks (research → plan → implement → test)
Switching between unrelated tasks within the same session
After completing a major milestone and starting new work
When responses slow down or become less coherent (context pressure)

Why Strategic Compaction?

Auto-compaction triggers at arbitrary points:

Often mid-task, losing important context
No awareness of logical task boundaries
Can interrupt complex multi-step operations

Strategic compaction at logical boundaries:

After exploration, before execution — Compact research context, keep implementation plan
After completing a milestone — Fresh start for next phase
Before major context shifts — Clear exploration context before different task

How It Works

The suggest-compact.js script runs on PreToolUse (Edit/Write) and:

Tracks tool calls — Counts tool invocations in session
Threshold detection — Suggests at configurable threshold (default: 50 calls)
Periodic reminders — Reminds every 25 calls after threshold

Hook Setup

Add to your ~/.claude/settings.json:

{
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "Edit",
        "hooks": [{ "type": "command", "command": "node ~/.claude/skills/strategic-compact/suggest-compact.js" }]
      },
      {
        "matcher": "Write",
        "hooks": [{ "type": "command", "command": "node ~/.claude/skills/strategic-compact/suggest-compact.js" }]
      }
    ]
  }
}

Configuration

Environment variables:

COMPACT_THRESHOLD — Tool calls before first suggestion (default: 50)

Compaction Decision Guide

Use this table to decide when to compact:

Phase Transition	Compact?	Why
Research → Planning	Yes	Research context is bulky; plan is the distilled output
Planning → Implementation	Yes	Plan is in TodoWrite or a file; free up context for code
Implementation → Testing	Maybe	Keep if tests reference recent code; compact if switching focus
Debugging → Next feature	Yes	Debug traces pollute context for unrelated work
Mid-implementation	No	Losing variable names, file paths, and partial state is costly
After a failed approach	Yes	Clear the dead-end reasoning before trying a new approach

What Survives Compaction

Understanding what persists helps you compact with confidence:

Persists	Lost
CLAUDE.md instructions	Intermediate reasoning and analysis
TodoWrite task list	File contents you previously read
Memory files (`~/.claude/memory/`)	Multi-step conversation context
Git state (commits, branches)	Tool call history and counts
Files on disk	Nuanced user preferences stated verbally

Best Practices

Compact after planning — Once plan is finalized in TodoWrite, compact to start fresh
Compact after debugging — Clear error-resolution context before continuing
Don't compact mid-implementation — Preserve context for related changes
Read the suggestion — The hook tells you when , you decide if
Write before compacting — Save important context to files or memory before compacting
Use/compact with a summary — Add a custom message: /compact Focus on implementing auth middleware next

The Longform Guide — Token optimization section
Memory persistence hooks — For state that survives compaction
continuous-learning skill — Extracts patterns before session ends

Weekly Installs

1.0K

Repository

affaan-m/everyt…ude-code

GitHub Stars

72.1K

First Seen

Jan 22, 2026

Security Audits

Gen Agent Trust HubPass SocketPass SnykPass

Installed on

opencode829

codex796

gemini-cli781

claude-code778

github-copilot700

cursor695