记忆秘书

智能管理与优化记忆文件，提供质量检查、重复任务检测、成功案例提取、工作模式分析和智能提醒。

Security Scan

The skill's description and docs claim a simple, read-only, zero-dependency analyzer, but the shipped files and runtime behavior contradict that (missing referenced modules/scripts, writes under your memory directory, and a push to ignore VirusTotal warnings), so installation deserves caution.

Purpose & Capability

The README/SKILL.md describe a local, read-only memory analysis tool with zero external deps, which roughly matches the core src/memory_secretary_lite.py. However __init__.py exports several modules (smart_adaptive, daily_check, pilot_check) and README/tests reference many scripts, config files and a 'scripts' directory that are not present in the package manifest. That mismatch (references to missing components) and the README/test expectations about workspace contents suggest the bundle is incomplete or expects external files in your workspace.

Instruction Scope

SKILL.md states the tool 'will not modify memory files' (read-only), yet the code initializes and creates a secretary_data_dir under the workspace/memory directory and saves reports (the quality check uses _save_report). The skill therefore writes files into your memory/ area despite claiming not to. Installation instructions (unzip into ~/.openclaw/skills/) are generic and the README encourages forcing install if VirusTotal flags it—this guidance is risky and inconsistent with 'from trusted source' practices.

Install Mechanism

No formal install spec is provided (instruction-only), but the package contains Python source and tests. The SKILL.md suggests manual unzip; there is no download URL in the manifest. Lack of an automated, verifiable install mechanism is not inherently malicious, but combined with the README's advice to use --force to bypass VirusTotal warnings increases risk.

Credentials

The skill declares no required credentials or env vars (good), but it accesses and writes under a workspace path (default '/home/admin/openclaw/workspace' or provided workspace_root). Tests and docs expect a 'memory' directory and 'scripts' — if those contain sensitive data, the skill will read them and it will also write report files under memory/secretary. The write behavior contradicts the claimed read-only scope and is disproportionate to the 'do not modify' assertion.

Persistence & Privilege

The skill does not request 'always: true' and uses normal autonomous invocation settings, which is fine. However it will create directories and persist reports under your workspace/memory, giving it persistent on-disk footprint. Combined with mismatches and the encouragement to bypass VirusTotal warnings, this persistent write access raises concern and warrants sandboxed testing before use.

What to consider before installing

This package is internally inconsistent: docs/tests reference many files and scripts that are not included, and the code—contrary to SKILL.md—creates and writes files under your workspace/memory. The README also tells users to force-install past VirusTotal warnings. Before installing, do the following: (1) inspect the full source yourself and confirm which files will be created under your workspace/memory and what they contain; (2) run the code in an isolated sandbox or VM with a backed-up test workspace (not your real memory data); (3) verify missing modules/scripts (smart_adaptive, daily_check, pilot_check, scripts/) — ask the author for a complete release or updated manifest; (4) do not use --force to bypass security warnings without code review; (5) if you proceed, point workspace_root to a dedicated test directory and check precisely what files are written. These contradictions are suspicious but do not prove intent to harm; require clarification or a corrected release.

记忆秘书 (Memory Secretary)

智能记忆管理与优化助手

技能信息

• 技能 ID: memory-secretary
• 显示名称: 记忆秘书
• 版本: 1.0.1
• 作者: 隐客
• 描述: 智能记忆管理与优化助手，提供主动记忆管理、智能提醒、模式识别等功能

核心功能

1. 记忆质量管理

检查记忆文件质量，发现潜在问题并提供优化建议。

2. 重复工作检测

查找相似任务，避免重复分析已解决的问题。

3. 成功案例提取

自动提取成功案例，建立经验库。

4. 工作模式识别

分析工作模式，发现高频问题和优化点。

5. 智能提醒生成

基于历史数据和当前任务，生成智能提醒。

6. 分享报告生成

生成可分享的系统状态报告。

安装方法

# 1. 下载技能包
cd ~/.openclaw/skills/

# 2. 解压
unzip memory-secretary.zip

# 3. 验证
ls memory-secretary/

使用方法

from memory_secretary import MemorySecretaryLite

# 初始化
secretary = MemorySecretaryLite(workspace_root="/your/workspace")

# 检查记忆质量
quality = secretary.check_memory_quality()

# 查找相似任务
similar = secretary.find_similar_tasks("任务名称")

# 提取成功案例
cases = secretary.extract_success_cases()

# 分析工作模式
patterns = secretary.analyze_work_patterns()

# 生成提醒
reminders = secretary.generate_reminders(["关键词"])

# 生成分享报告
report = secretary.generate_share_report()

技术特点

• ✅ 零外部依赖 - 仅使用 Python 标准库
• ✅ 小体积 - 总大小 <150KB
• ✅ 快速部署 - 复制文件即可使用
• ✅ 智能自适应 - 自动选择最佳技术方案
• ✅ 主动管理 - 主动提醒、智能推荐

系统要求

• Python 3.8+
• OpenClaw 工作空间
• 记忆文件目录 (memory/)

文件结构

memory-secretary/
├── SKILL.md              # 本文件
├── README.md             # 详细文档
├── src/                  # 源代码
├── tests/                # 测试文件
├── examples/             # 使用示例
└── config/               # 配置文件

测试

# 运行测试
cd memory-secretary/
python3 -m pytest tests/

更新日志

v1.0.0 (2026-04-14)

• 初始版本发布
• 核心功能实现（6 大功能）
• 智能自适应架构
• 基础测试覆盖
• 完整文档

常见问题

Q: 需要安装额外依赖吗？
A: 不需要！仅使用 Python 标准库。

Q: 支持哪些 Python 版本？
A: Python 3.8+，推荐 3.10+。

Q: 会修改我的记忆文件吗？
A: 不会，只读取不修改。

许可证

MIT License

支持

如有问题或建议，欢迎通过以下方式联系：

• GitHub Issues
• OpenClaw 社区论坛
• 邮件：示例@email.com

---

记忆秘书 - 你的智能记忆管理助手 🧠✨