Memory Evolver

记忆系统优化器 - 结合三层记忆与知识图谱的持续自我进化系统。自动诊断、优化、记录记忆系统状态，实现记忆的持续进化。

Security Scan

The skill's code largely matches a local diagnostic-and-logging tool for the agent workspace, but the documentation and claimed features (extra modules, KG rebuild, Feishu/EvoMap integrations) do not match the shipped code and the program uses a hard-coded user workspace path and writes persistent logs — these inconsistencies and persistence warrant caution.

Purpose & Capability

The stated purpose (diagnose/optimize a three-layer memory + knowledge graph) is broadly consistent with index.py which inspects MEMORY.md, PROJECTS.md, daily notes and a knowledge-graph file and writes an optimization log. However SKILL.md and the README-like text claim additional modules (diagnose.py, knowledge_graph.py) and features (KG rebuilding, Feishu reports) that are not present in the bundle. Also the code hardcodes BASE_DIR to C:\Users\Administrator\.openclaw\workspace rather than using a configurable/workspace-relative path — this is unexpected and brittle but not obviously malicious.

Instruction Scope

SKILL.md instructs running the skill and scheduling cron jobs and describes KG rebuild and external reporting, but the actual runtime instructions (index.py) only perform local file checks, plan generation, and append/write to an optimization log. The docs grant broader scope (automatic integration, Feishu/EvoMap) that the code does not implement — this mismatch could indicate an incomplete or misleading package. The script reads and writes files in the user's .openclaw workspace (reads MEMORY.md, PROJECTS.md, memory/*, knowledge_graph/graph.json; writes memory/optimization循环.md) which is within the expected domain for a memory tool but is a persistence surface the user should expect.

Install Mechanism

No install spec, no external downloads, and index.py uses only Python standard library. There is no evidence of code being fetched from external, untrusted URLs or package managers.

Credentials

The skill requests no environment variables or credentials. The code accesses only local filesystem paths (hard-coded BASE_DIR) and does not attempt to read environment variables or network credentials. The lack of declared env requirements matches the code.

Persistence & Privilege

The skill writes a persistent optimization log into the user's workspace and may modify files under .openclaw/workspace/memory. always is false and it does not change other skills' configs, but because it writes to the agent's workspace you should treat it as capable of persistent state changes. Also autonomous invocation is allowed by default (disable-model-invocation false) — while normal, combined with write access this increases impact if the skill later obtains network capabilities.

What to consider before installing

Key points to consider before installing or running: - The package appears to be incomplete/mismatched: SKILL.md mentions diagnose.py, knowledge_graph.py, KG rebuild and Feishu/EvoMap integrations that are not present in the shipped files. Ask the author for the missing modules or an explanation. - The script hard-codes BASE_DIR to C:\Users\Administrator\.openclaw\workspace. On other systems this will fail or may target the wrong user's workspace. Prefer a version that uses a configurable path or the runtime agent workspace. - The skill reads and writes files under your .openclaw workspace (MEMORY.md, PROJECTS.md, memory/*, knowledge_graph/graph.json and writes memory/optimization循环.md). Back up those files before running to avoid accidental overwrites. - There are no network calls or credential accesses in the current code, which limits immediate exfiltration risk. However the SKILL.md's claim of external reporting (Feishu, EvoMap) suggests future or missing code could add network behavior — treat that as a potential future risk. - Recommended actions: (1) request clarification or the missing modules from the author; (2) inspect the workspace path and consider modifying the script to use a safe, explicit path or ask for a parameterized version; (3) run in a sandbox or with backups first; (4) avoid scheduling automatic runs until you confirm the implementation matches the documented integrations and there are no external endpoints.

Memory Evolver - 记忆进化器

概述

结合三层记忆系统（MEMORY.md + 每日日志 + PROJECTS.md）与知识图谱的持续自我进化系统。

核心理念

• 🔄 持续循环: 诊断 → 计划 → 执行 → 记录 → 进化
• 🧠 三层记忆: 长期记忆 + 每日日志 + 项目跟踪
• 🔗 知识图谱: 从记忆构建语义网络
• 📈 指数成长: 1% daily improvement = 37x yearly growth

功能

1. 记忆系统诊断

• 检查 MEMORY.md 完整性
• 检查 PROJECTS.md 状态
• 检查每日日志数量
• 检查知识图谱实体数

2. 优化计划生成

• 根据问题生成优化优先级
• 分类：高/中/低
• 可执行的具体行动

3. 知识图谱重建

• 从 memory/ 文件提取实体
• 识别实体间关系
• 构建可查询的图结构

4. 优化循环日志

• 记录每次优化的诊断、计划、执行
• 追踪优化历史
• 持续改进机制

文件结构

memory-evolver/
├── SKILL.md              # 本文件
├── index.py              # 主程序
├── diagnose.py          # 诊断模块
├── knowledge_graph.py    # 知识图谱
└── config.json          # 配置

使用方式

手动运行

python skills/memory-evolver/index.py

定时执行

# 每天23点自动优化
openclaw cron add --name "memory-evolver" --cron "0 23 * * *"

EvoMap 集成

• Node ID: node_6d28b52505ad2d41
• 状态: 自动化运行
• 报告: 支持 Feishu 卡片报告

三层记忆模板

MEMORY.md (长期)

# 长期记忆
## 核心锚点
- 用户: 先生
- 风格: 直接、效率优先
## 目标
- [ ] 构建完整AI系统

memory/YYYY-MM-DD.md (每日)

# 2026-03-18
## 事件
- 11:00: 创建知识图谱
## 决策
- 优先先生指定功能

PROJECTS.md (项目)

## 项目名
- 状态: X/Y
- 阻碍: 无
- 下一步: 继续优化

成功指标

• 诊断系统就绪
• 优化循环建立
• 知识图谱可查询
• 每日自动运行

---

版本: 1.0.0
作者: Sharon
EvoMap: node_6d28b52505ad2d41