← 返回 Skills 市场
77
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install agent-memory-optimizer
功能描述
Archives older daily memory notes into month folders to keep active memory lean and reduce prompt token usage. Use when users want lower token overhead, clea...
使用说明 (SKILL.md)
Agent Memory Optimizer
Optimize active memory context by archiving old daily notes into month-based folders.
What it does
- Scans
memory/*.md - Moves files older than the current month into
memory/archive/YYYY-MM/ - Supports
--dry-runto preview changes - Safe to run repeatedly
Run
python3 scripts/agent_memory_optimizer.py --dry-run
python3 scripts/agent_memory_optimizer.py
Optional custom cutoff:
python3 scripts/agent_memory_optimizer.py --before 2026-05
Installation
Install into your workspace skills directory:
\x3Cworkspace>/skills/agent-memory-optimizer/
Or install from ClawHub after publishing.
安全使用建议
This skill appears to do what it says and only operates on local files, but review these points before installing: (1) Default memory directory is ~/.openclaw/workspace/memory — confirm that this is the folder you want to affect or pass --memory-dir. (2) Run with --dry-run first to preview changes. (3) The script will delete an existing destination file (dst.unlink()) before moving a source file, so if you have files with identical names in archive folders the existing archived file will be overwritten; back up if that is a concern. (4) The tool only moves files whose names match YYYY-MM(-DD).md; files not matching that pattern are ignored. (5) No network calls or credentials are used. If you require additional guarantees, inspect the included scripts yourself or run in a test workspace first.
能力评估
Purpose & Capability
Name/description match the included script and SKILL.md: the tool scans a local memory directory for YYYY-MM(-DD).md filenames and moves files older than the cutoff into memory/archive/YYYY-MM/. The only required binary is python3, which is appropriate.
Instruction Scope
The SKILL.md tells the agent to run the included Python script (with an optional --dry-run). The instructions operate only on the local memory directory (default ~/.openclaw/workspace/memory) and do not request other files, env vars, or external endpoints.
Install Mechanism
There is no install spec; this is an instruction-only skill with an included script. Nothing is downloaded or installed automatically, so no additional install risk is introduced.
Credentials
The skill requires no environment variables or credentials. Its default path is a user-local workspace directory, which is appropriate for its purpose.
Persistence & Privilege
The skill is not always-enabled and does not modify other skills or system-wide settings. It runs only when invoked and acts on the specified local files.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install agent-memory-optimizer - 安装完成后，直接呼叫该 Skill 的名称或使用
/agent-memory-optimizer触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
- Initial release of Agent Memory Optimizer.
- Archives outdated daily memory notes into organized month-based folders.
- Reduces prompt token usage by minimizing active memory file clutter.
- Includes dry-run support to preview archiving actions safely.
- Easy installation and compatible with standard Python3 environments.
元数据
常见问题
Agent Memory Optimizer 是什么？
Archives older daily memory notes into month folders to keep active memory lean and reduce prompt token usage. Use when users want lower token overhead, clea... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 77 次。
如何安装 Agent Memory Optimizer？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install agent-memory-optimizer」即可一键安装，无需额外配置。
Agent Memory Optimizer 是免费的吗？
是的，Agent Memory Optimizer 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Agent Memory Optimizer 支持哪些平台？
Agent Memory Optimizer 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Agent Memory Optimizer？
由 x3r081（@x3r081）开发并维护，当前版本 v1.0.0。
推荐 Skills