技能详情（站内镜像，无评论）
许可证：MIT-0
MIT-0 ·免费使用、修改和重新分发。无需归因。
版本：v1.1.0
统计：⭐ 0 · 43 · 0 current installs · 0 all-time installs
⭐ 0
安装量（当前） 0
🛡 VirusTotal ：可疑 · OpenClaw ：可疑
Package：axelhu/memory-review
安全扫描（ClawHub）
- VirusTotal ：可疑
- OpenClaw ：可疑
OpenClaw 评估
The skill's behavior (scanning and writing local 'memory' files and reading delivery configs) is generally coherent with its description, but there are notable gaps and overruns — it reads/writes project config files that may contain sensitive delivery credentials and references shell commands/endpoints without declaring required credentials or binaries.
目的
The skill's name/description (automatically scan diaries and write knowledge) matches the instructions to read memory/daily and write memory/knowledge and reports. However the SKILL.md references running md5sum and delivering reports to channels (e.g., Feishu) while the metadata declares no required binaries or credentials — a mild inconsistency. It's plausible the skill expects delivery configuration to live in AGENTS.md/MEMORY.md instead of …
说明范围
Runtime instructions explicitly read and write local project files: MEMORY.md, AGENTS.md, memory/daily/*, memory/knowledge/*, data/exec-logs/* and may modify AGENTS.md or TOOLS.md. The skill also states it will '投递报告' (deliver reports) using values from AGENTS.md/MEMORY.md (e.g., Feishu group IDs). This grants the skill broad discretion over local content and the ability to post externally if delivery logic is implemented — the SKILL.md does not specify how delivery is performed or what exact fields/credentials are required. That lack of precision increases risk because the agent could read secrets embedded in those files or use hidden endpoints.
安装机制
Instruction-only skill (no install spec, no code files). This is the lowest install risk: nothing will be fetched or written during installation. All behavior comes from SKILL.md and references/spec.md.
证书
The skill declares no required environment variables or primary credential, but it expects delivery config (channel IDs, potentially tokens or webhooks) to be found in AGENTS.md or MEMORY.md. Not requiring environment variables is acceptable if the project stores all needed endpoints locally, but the skill should declare that it will read those files and should document the expected keys and whether they may contain secrets. As-is, it may read…
持久
The skill is not always:true and is user-invocable (normal). It will write files under memory/ and data/exec-logs/ and may update AGENTS.md/TOOLS.md as part of 'low priority' rules — this is within its stated purpose but grants it write privilege over project configuration files. That capability should be made explicit and limited by user policy or review.
安装（复制给龙虾 AI）
将下方整段复制到龙虾中文库对话中，由龙虾按 SKILL.md 完成安装。
请把本段交给龙虾中文库（龙虾 AI）执行：为本机安装 OpenClaw 技能「Memory Review」。简介：知识沉淀自动化技能。扫描近期日记，识别可沉淀知识，自动写入知识库。触发时机：cron 定时任务或手动调用。使用方法：加载 skill 后读取 referenc…。
请 fetch 以下地址读取 SKILL.md 并按文档完成安装：https://raw.githubusercontent.com/openclaw/skills/refs/heads/main/skills/axelhu/memory-review/SKILL.md
（来源：yingzhi8.cn 技能库）SKILL.md
---
name: memory-review
version: 1.1.0
description: 知识沉淀自动化技能。扫描近期日记，识别可沉淀知识，自动写入知识库。触发时机：cron 定时任务或手动调用。使用方法：加载 skill 后读取 references/spec.md 获取详细规范。
---
# Memory Review
扫描近期日记，生成知识沉淀提案，并自动执行沉淀。
## 核心流程
1. 读取 references/spec.md 获取详细规范
2. 读取 AGENTS.md/MEMORY.md 获取投递配置
3. 增量扫描近期日记（md5 比对）
4. 识别 5 类可沉淀知识
5. 自动写入知识库
6. 生成报告并投递
## 敏感信息
**投递配置（如飞书群ID）存储在 AGENTS.md 或 MEMORY.md 中**，skill 里使用占位符。
读取方式：
- 读取 `MEMORY.md`（如果存在）
- 读取 `AGENTS.md` 中的配置
## 输出
- 报告位置：`memory/daily/YYYY-MM-DD-memory-review.md`
- 知识库：`memory/knowledge/fw-*.md`
- 执行日志：`data/exec-logs/memory-review/YYYY-MM-DD.md`
## 触发时机
- cron 定时任务（建议每 2 天）
- 用户明确要求时
- 每次会话结束前（可选）
## 自动沉淀规则
| 优先级 | 条件 | 行为 |
|--------|------|------|
| 高 | 错误/教训类 | 自动写入 post-mortems.md |
| 中 | 技术知识类 | 自动写入 knowledge/fw-*.md |
| 低 | 配置/偏好类 | 写入 TOOLS.md 或 AGENTS.md |
## 沉淀文件命名规范
```
fw-{主题}.md
- fw = "from work" 工作产出
- 主题：用英文或中文拼音
```