strategic-compact
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
Skill by Luohaothu
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/luohaothu-strategic-compact-b756a4
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: productivity
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions: not checked yet.
What's inside
- Skill name
strategic-compact- Description
- Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
- License
- MIT
- Instructions
- 60 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# 策略性壓縮技能
在工作流程的策略點建議手動 `/compact`,而非依賴任意的自動壓縮。
## 為什麼需要策略性壓縮?
自動壓縮在任意點觸發:
- 經常在任務中途,丟失重要上下文
- 不知道邏輯任務邊界
- 可能中斷複雜的多步驟操作
邏輯邊界的策略性壓縮:
- **探索後、執行前** - 壓縮研究上下文,保留實作計畫
- **完成里程碑後** - 為下一階段重新開始
- **主要上下文轉換前** - 在不同任務前清除探索上下文
## 運作方式
`suggest-compact.sh` 腳本在 PreToolUse(Edit/Write)執行並:
1. **追蹤工具呼叫** - 計算工作階段中的工具呼叫次數
2. **門檻偵測** - 在可設定門檻建議(預設:50 次呼叫)
3. **定期提醒** - 門檻後每 25 次呼叫提醒一次
## Hook 設定
新增到你的 `~/.claude/settings.json`:
```json
{
"hooks": {
"PreToolUse": [{
"matcher": "tool == \"Edit\" || tool == \"Write\"",
"hooks": [{
"type": "command",
"command": "~/.claude/skills/strategic-compact/suggest-compact.sh"
}]
}]
}
}
```
## 設定
環境變數:
- `COMPACT_THRESHOLD` - 第一次建議前的工具呼叫次數(預設:50)
## 最佳實務
1. **規劃後壓縮** - 計畫確定後,壓縮以重新開始
2. **除錯後壓縮** - 繼續前清除錯誤解決上下文
3. **不要在實作中途壓縮** - 為相關變更保留上下文
4. **閱讀建議** - Hook 告訴你*何時*,你決定*是否*
## 相關
- [Longform Guide](https://x.com/affaanmustafa/status/2014040193557471352) - Token 優化章節
- 記憶持久性 hooks - 用於壓縮後存活的狀態From Luohaothu/everything-codex, MIT.
More from Luohaothu/everything-codex
- 0.493score
architect
Luohaothu
Software architecture specialist for system design, scalability, and technical decision-making.
SkillDFreshness: D★ 26Claude Code +9 - 0.493score
build-fix
Luohaothu
Build and compilation error resolution specialist.
SkillDFreshness: D★ 26Claude Code +9 - 0.490score
code-review
Luohaothu
Expert code review for quality, security, and maintainability.
SkillDFreshness: D★ 26Claude Code +9 - 0.490score
checkpoint
Luohaothu
Create or verify workflow checkpoints using git commits and state tracking.
SkillDFreshness: D★ 26Claude Code +9 - 0.487score
tdd-workflow
Luohaothu
在编写新功能、修复错误或重构代码时使用此技能。强制执行测试驱动开发,包含单元测试、集成测试和端到端测试,覆盖率超过80%。
SkillDFreshness: D★ 26Claude Code +9 - 0.487score
springboot-security
Luohaothu
Java Spring Boot 服务中关于身份验证/授权、验证、CSRF、密钥、标头、速率限制和依赖安全的 Spring Security 最佳实践。
SkillDFreshness: D★ 26Claude Code +9 - 0.487score
springboot-tdd
Luohaothu
使用JUnit 5、Mockito、MockMvc、Testcontainers和JaCoCo进行Spring Boot的测试驱动开发。适用于添加功能、修复错误或重构时。
SkillDFreshness: D★ 26Claude Code +9 - 0.487score
springboot-patterns
Luohaothu
Spring Boot 架构模式、REST API 设计、分层服务、数据访问、缓存、异步处理和日志记录。适用于 Java Spring Boot 后端工作。
SkillDFreshness: D★ 26Claude Code +9 - 0.484score
jpa-patterns
Luohaothu
Spring Boot中的JPA/Hibernate实体设计、关系、查询优化、事务、审计、索引、分页和连接池模式。
SkillDFreshness: D★ 26Claude Code +9 - 0.484score
postgres-patterns
Luohaothu
基于Supabase最佳实践的PostgreSQL数据库模式,用于查询优化、架构设计、索引和安全。
SkillDFreshness: D★ 26Claude Code +9 - 0.484score
eval-harness
Luohaothu
克劳德代码会话的正式评估框架,实施评估驱动开发(EDD)原则
SkillDFreshness: D★ 26Claude Code +9 - 0.484score
continuous-learning-v2
Luohaothu
基于本能的学习系统,通过钩子观察会话,创建具有置信度评分的原子本能,并将其演化为技能/命令/代理。
SkillDFreshness: D★ 26Claude Code +9
Signals
- Stars
- 26
- Forks
- 5
- Open issues
- 0
- Last commit (this folder)
- Jan 29, 2026 (9 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Luohaothu/everything-codex
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
- 0.767score
strategic-compact
sangrokjung
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
SkillBFreshness: B★ 863Claude Code +9 - 0.400score
strategic-compact
GGGODLIN
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
SkillAFreshness: A★ 72Claude Code +9 - 0.399score
strategic-compact
Fmarzochi
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
SkillAFreshness: A★ 67Claude Code +9 - 0.347score
strategic-compact
mturac
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
SkillCFreshness: C★ 83Claude Code +9 - 0.344score
strategic-compact
ysyecust
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
SkillCFreshness: C★ 59Claude Code +9 - 0.299score
strategic-compact
marshall0524
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
SkillDFreshness: D★ 41Claude Code +9 - 0.281score
strategic-compact
Infopibe
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
SkillDFreshness: D★ 8Claude Code +9 - 0.257score
strategic-compact
ashutoshrathi0909-oss
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
SkillDFreshness: D★ 1Claude Code +9 - 0.244score
strategic-compact
sumitkashyape2
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
SkillDFreshness: DClaude Code +9 - 0.243score
strategic-compact
vibeeval
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
SkillDFreshness: D★ 540Claude Code +9 - 0.241score
strategic-compact
bh679
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
SkillDFreshness: DClaude Code +9
More from Luohaothu
- 0.493score
architect
Luohaothu
Software architecture specialist for system design, scalability, and technical decision-making.
SkillDFreshness: D★ 26Claude Code +9 - 0.493score
build-fix
Luohaothu
Build and compilation error resolution specialist.
SkillDFreshness: D★ 26Claude Code +9 - 0.490score
code-review
Luohaothu
Expert code review for quality, security, and maintainability.
SkillDFreshness: D★ 26Claude Code +9 - 0.490score
checkpoint
Luohaothu
Create or verify workflow checkpoints using git commits and state tracking.
SkillDFreshness: D★ 26Claude Code +9 - 0.487score
springboot-patterns
Luohaothu
Spring Boot 架构模式、REST API 设计、分层服务、数据访问、缓存、异步处理和日志记录。适用于 Java Spring Boot 后端工作。
SkillDFreshness: D★ 26Claude Code +9 - 0.487score
springboot-security
Luohaothu
Java Spring Boot 服务中关于身份验证/授权、验证、CSRF、密钥、标头、速率限制和依赖安全的 Spring Security 最佳实践。
SkillDFreshness: D★ 26Claude Code +9
Cite this page
strategic-compact skill. Agent Mart. https://agentmart.dev/skills/luohaothu-strategic-compact-b756a4 (last updated 2026-10-24)