Token导航 LogoToken导航

Agent Skill · 研究检索

context-compression(上下文压缩)

context-compression 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

context-compression 是研究检索类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为需要联网;许可证为 MIT-0,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 2,745。

总安装 55,290周安装 2,327GitHub Stars 4下载 19,361核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
3.13.3

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:context-compression(上下文压缩)
来源仓库:https://github.com/lifei68801/context-compression
安装命令:
openclaw skills install context-compression
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install context-compression

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

上下文压缩技能通过智能截断与记忆保留防止对话溢出,提升长会话稳定性。适合处理多轮复杂任务、知识库检索或需要持续记忆的交互流程。安装后自动分析会话密度,按需压缩历史并保留关键信息供后续引用。注意压缩策略可能影响细节完整性,重要上下文建议手动备份。需确认是否支持自定义保留字段或关键事件标记功能。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install context-compression;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

context-compression 怎么安装?

在终端执行 openclaw skills install context-compression。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

context-compression 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

context-compression 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

context-compression 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

context-compression 用的人多吗?

公开数据是累计安装 55,290 次,近一周安装 2,327 次,下载 19,361 次,GitHub 4 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

context-compression 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
context-compression

上下文压缩 · 本页

55,2904需要联网MIT-0通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

name
context-compression
version
3.13.3
description
Prevent context overflow with automatic session truncation and memory preservation.
license
MIT-0
author
lifei68801
metadata
openclaw
requires
bins
["bash", "jq", "sed", "grep", "head", "tail", "wc", "date", "tr", "cut"]
configPaths
permissions
installDir
~/.openclaw/workspace/skills/context-compression
fileLayout
behavior
modifiesLocalFiles
true
network
local
telemetry
none
credentials
none
settings
~/.openclaw/workspace/.context-compression-config.json
description
Reads and trims local session files. Writes identified facts to MEMORY.md and daily notes. The optional AI-assisted fact identification invokes the local openclaw agent CLI (network depends on user's OpenClaw config). No scripts make external HTTP calls directly.

Context Compression

Keep conversations within limits. Never lose important context.

⚡ After installing, run the interactive setup wizard to generate your config file, then add the suggested cron entry with crontab -e. See Quick Start below for commands.

Quick Start

File location: ClawHub installs this skill to ~/.openclaw/workspace/skills/context-compression/. All scripts are placed here directly. This is the standard OpenClaw skill install path — no manual file placement needed.
# 1. Install and configure (interactive)
bash ~/.openclaw/workspace/skills/context-compression/configure.sh

# 2. Verify config exists
cat ~/.openclaw/workspace/.context-compression-config.json

# 3. Set up crontab (example: every 10 minutes)
*/10 * * * * ~/.openclaw/workspace/skills/context-compression/truncate-sessions-safe.sh

How It Works

Session Truncation (truncate-sessions-safe.sh)

  • Scheduling: System crontab (e.g., */10 * * * *)
  • Action: Reads .jsonl session files under ~/.openclaw/agents/*/sessions/, trims each file to the configured size
  • Safety: Skips files with a matching .lock file (active session)
  • Integrity: Keeps JSONL line boundaries intact — never splits a line
  • Strategy: priority-first scans for important keywords before trimming and preserves matching lines

Fact Identification

  • Keyword-based: identify-facts.sh — scans truncated content for keywords (重要, 决定, TODO, 偏好, deadline, must remember, etc.) and appends findings to memory/YYYY-MM-DD.md
  • AI-assisted: identify-facts-enhanced.sh — calls openclaw agent --agent main --message with the trimmed content to semantically identify important facts. Only used when openclaw CLI is available on PATH.
  • Triggered by: truncate-sessions-safe.sh calls one of these before each truncation cycle

Preference Lifecycle (check-preferences-expiry.sh)

  • Scheduling: Once daily via crontab
  • Mechanism: Reads MEMORY.md preference entries tagged with @YYYY-MM-DD, removes expired ones
  • Tiers: Short-term (1-7 days), Mid-term (1-4 weeks), Long-term (permanent)

Scripts

ScriptPurposeScheduling
truncate-sessions-safe.shTrim session JSONL filescrontab, every 10 min
identify-facts.shKeyword-based fact detectionCalled by truncate script
identify-facts-enhanced.shAI-assisted fact detectionCalled by truncate script
check-preferences-expiry.shRemove expired preferencescrontab, once daily
configure.shInteractive setup wizardManual, one-time
session-start-hook.shLoad context at session startCalled by AGENTS.md
session-end-hook.shSave context at session endCalled by AGENTS.md
check-context-health.shReport current context statusManual / on-demand

Configuration

File: ~/.openclaw/workspace/.context-compression-config.json

{
  "version": "2.3",
  "maxChars": 40000,
  "frequencyMinutes": 10,
  "skipActive": true,
  "strategy": "priority-first",
  "useAiIdentification": false,
  "priorityKeywords": [
    "重要", "决定", "记住", "TODO", "偏好",
    "important", "remember", "must", "deadline"
  ]
}
FieldTypeDefaultDescription
maxCharsnumber40000Max chars to keep per session file
frequencyMinutesnumber10How often crontab runs truncate
skipActivebooleantrueSkip sessions with .lock files
strategystringpriority-firstTruncation strategy
useAiIdentificationbooleanfalseSet true to use AI-assisted fact identification (may send content to remote LLMs)
priorityKeywordsstring[](see above)Keywords to preserve during truncation

Troubleshooting

ProblemSolution
Context still exceededReduce maxChars in config
Memory not persistingCheck that AGENTS.md includes session-start-hook
Crontab not runningVerify PATH in crontab includes node/openclaw binary location

Safety

Data Protection

  • No deletion: Truncation writes the trimmed portion back to the same file. It does not delete files.
  • Backup before trim: truncate-sessions-safe.sh creates a .pre-trim backup of each file before modification. Backups are cleaned up after a successful write.
  • Line integrity: Truncation only cuts at JSONL line boundaries. Partial lines are never written.
  • Active sessions protected: Files with a matching .lock (currently in use) are always skipped, even if oversized.

Safe Defaults

All configuration values have conservative defaults:

  • skipActive: true — never touches a running session
  • maxChars: 40000 — keeps substantial history per session
  • strategy: priority-first — preserves lines matching priority keywords before trimming anything
  • No direct network access from scripts. The optional AI fact identification uses your local openclaw CLI — network activity depends on your OpenClaw configuration.

User Control

  • Crontab: The user creates and manages all scheduled tasks. No script auto-installs crontab entries.
  • Configuration: All settings live in a single JSON file. The configure.sh wizard runs interactively and requires user input.
  • Opt-out: Remove the crontab entry to stop all automated truncation. The skill has no background daemon of its own.
  • Scope: Only reads/writes files under ~/.openclaw/agents/main/ and ~/.openclaw/workspace/memory/. Never touches system files, other agents' data, or other users' data.

Privacy Notice

  • AI-assisted fact identification (identify-facts-enhanced.sh) is disabled by default. It invokes the local openclaw agent CLI, which may send session content to remote LLM services depending on your OpenClaw configuration. Only enable it if you understand and accept this data flow. To enable, set "useAiIdentification": true in the config file.
  • Keyword-based identification (identify-facts.sh) is the default and runs entirely locally with no external data transmission.
  • Unattended cron execution: If you enable cron jobs, the scripts run without interactive consent. Review the scripts and test manually before enabling scheduled runs.

Related

平台分布

OpenClaw

72.38%
按下载量换算14,013

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills