strategic-compact

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Strategic Compact Skill

策略性压缩技能

Suggests manual

/compact

at strategic points in your workflow rather than relying on arbitrary auto-compaction.

建议在工作流的关键策略节点手动执行

/compact

命令，而非依赖任意触发的自动压缩。

When to Activate

激活场景

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)

运行接近上下文限制的长会话（200K+令牌）
处理多阶段任务（研究→规划→实现→测试）
在同一会话中切换不相关任务
完成重要里程碑并开始新工作时
响应变慢或连贯性下降时（上下文压力）

Why Strategic Compaction?

为什么选择策略性压缩？

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

自动压缩会在任意节点触发：

常发生在任务进行中，丢失重要上下文
无法识别逻辑任务边界
可能中断复杂的多步骤操作

在逻辑边界进行策略性压缩：

探索完成后，执行前——压缩研究上下文，保留实现规划
完成里程碑后——为下一阶段提供全新开始
重大上下文切换前——在切换到不同任务前清理探索上下文

How It Works

工作原理

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

suggest-compact.js

脚本在PreToolUse（编辑/写入）阶段运行：

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（默认：50次调用）时建议压缩
定期提醒——达到阈值后每25次调用提醒一次

Hook Setup

钩子设置

Add to your

~/.claude/settings.json

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" }]
      }
    ]
  }
}

添加到你的

~/.claude/settings.json

：

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

配置

Environment variables:

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

环境变量：

```
COMPACT_THRESHOLD
```
——首次建议压缩前的工具调用次数（默认：50）

Compaction Decision Guide

压缩决策指南

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

使用下表决定何时压缩：

阶段转换	是否压缩？	原因
研究→规划	是	研究上下文冗余，规划是提炼后的核心输出
规划→实现	是	规划已存入TodoWrite或文件，释放上下文用于代码编写
实现→测试	视情况而定	若测试需参考近期代码则保留；若切换焦点则压缩
调试→下一功能	是	调试痕迹会污染无关工作的上下文
实现过程中	否	丢失变量名、文件路径和部分状态代价高昂
尝试失败方案后	是	在尝试新方案前清理无效推理内容

What Survives Compaction

压缩后保留的内容

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

了解压缩后保留的内容能让你更放心地执行压缩：

保留内容	丢失内容
CLAUDE.md 指令	中间推理和分析过程
TodoWrite 任务列表	你之前读取过的文件内容
内存文件（ `~/.claude/memory/` ）	多步骤对话上下文
Git 状态（提交、分支）	工具调用历史和计数
磁盘上的文件	口头提及的细微用户偏好

Best Practices

最佳实践

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

规划完成后压缩——一旦规划在TodoWrite中定稿，压缩以全新开始
调试完成后压缩——在继续工作前清理错误排查上下文
实现过程中不要压缩——保留上下文以支持相关变更
查看建议信息——钩子提示你时机，由你决定是否执行
压缩前先保存——在压缩前将重要上下文保存到文件或内存中
带摘要使用
/compact
——添加自定义消息：
```
/compact Focus on implementing auth middleware next
```
（接下来专注于实现认证中间件）

Token Optimization Patterns

令牌优化模式

Trigger-Table Lazy Loading

触发表懒加载

Instead of loading full skill content at session start, use a trigger table that maps keywords to skill paths. Skills load only when triggered, reducing baseline context by 50%+:

Trigger	Skill	Load When
"test", "tdd", "coverage"	tdd-workflow	User mentions testing
"security", "auth", "xss"	security-review	Security-related work
"deploy", "ci/cd"	deployment-patterns	Deployment context

不要在会话开始时加载完整技能内容，使用触发表将关键词映射到技能路径。技能仅在触发时加载，可减少50%以上的基线上下文：

触发词	技能	加载时机
"test", "tdd", "coverage"	tdd-workflow	用户提及测试时
"security", "auth", "xss"	security-review	处理安全相关工作时
"deploy", "ci/cd"	deployment-patterns	部署场景下

Context Composition Awareness

上下文组合感知

Monitor what's consuming your context window:

CLAUDE.md files — Always loaded, keep lean
Loaded skills — Each skill adds 1-5K tokens
Conversation history — Grows with each exchange
Tool results — File reads, search results add bulk

监控占用上下文窗口的内容：

CLAUDE.md 文件——始终加载，保持精简
已加载技能——每个技能增加1-5K令牌
对话历史——随每次交互增长
工具结果——文件读取、搜索结果会增加体积

Duplicate Instruction Detection

重复指令检测

Common sources of duplicate context:

Same rules in both
```
~/.claude/rules/
```
and project
```
.claude/rules/
```
Skills that repeat CLAUDE.md instructions
Multiple skills covering overlapping domains

重复上下文的常见来源：

```
~/.claude/rules/
```
和项目
```
.claude/rules/
```
中存在相同规则
重复CLAUDE.md指令的技能
覆盖重叠领域的多个技能

Context Optimization Tools

上下文优化工具

```
token-optimizer
```
MCP — Automated 95%+ token reduction via content deduplication
```
context-mode
```
— Context virtualization (315KB to 5.4KB demonstrated)

```
token-optimizer
```
MCP——通过内容去重实现95%以上的令牌减少
```
context-mode
```
——上下文虚拟化（已验证可从315KB降至5.4KB）