← Back to Skills Marketplace
66
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install memory-recall
Description
精准检索历史记忆，调取某天、某项目、某条对话记录。支持按日期、按关键词、按类型检索。用于用户说查找、找回、某天、某次、之前说过等场景。
README (SKILL.md)
记忆智能检索回溯系统
精准找回任何历史记忆：某天说了什么、某件事的结论是什么、某个项目当时的决策。
检索方式
1. 按日期检索
找到5月1日的所有对话记录
查看上周的所有日记
2. 按关键词检索
查找关于"数据库选型"的所有记忆
找回提到"小M"的所有记录
3. 按类型检索
找到所有决策记录
查看所有未解决的问题
列出所有项目
4. 自然语言检索
我们上次讨论部署方案是什么时候？
上次提到 xx 是在什么场景下？
这个项目的技术选型结论是什么？
工作原理
用户查询
├── 解析：用户想找什么？
├── 搜索：MEMORY.md（精确） + memory/*.md（日记）
├── 过滤：按日期/关键词/类型
├── 排序：最新最相关优先
└── 呈现：来源 + 内容 + 时间
检索策略
| 查询类型 | 优先搜索 |
|---|---|
| 偏好类 | MEMORY.md |
| 决策类 | MEMORY.md + 最新日记 |
| 事件类 | memory/YYYY-MM-DD.md |
| 项目类 | MEMORY.md 项目章节 |
| 人物类 | MEMORY.md 联系人章节 |
输出格式
检索结果统一呈现：
📅 2026-05-01 | 来源：MEMORY.md
找到的结论：当时决定用 PostgreSQL 而非 MongoSQL
原因：团队更熟悉 PG，事务支持更好
📅 2026-05-01 | 来源：memory/2026-05-01.md
对话片段：用户提到"我们的支付模块需要支持分布式事务"
与永久记忆系统的关系
- 永久记忆系统：写入记忆
- 本技能：从记忆中召回
两者配合 = 写入 + 召回 + 形成闭环。
安装
本技能无需额外配置，直接启用即可。
Usage Guidance
This skill appears safe to install for its stated purpose. Be aware that it is designed to retrieve information from stored memory and diary files, so invoke it only when you are comfortable having prior personal or project history brought into the current conversation.
Capability Analysis
Type: OpenClaw Skill
Name: memory-recall
Version: 1.0.0
The 'memory-recall' skill is a set of markdown instructions (SKILL.md) designed to guide an AI agent in searching and retrieving historical information from local files like MEMORY.md and the memory/ directory. It contains no executable code, network activity, or malicious prompt injection, and its behavior is entirely consistent with its stated purpose of managing user-related context.
Capability Assessment
Purpose & Capability
The stated purpose is to retrieve prior memories and conversations, and the instructions consistently focus on searching MEMORY.md and memory/*.md files.
Instruction Scope
The skill describes search, filtering, sorting, and presentation behavior; it does not instruct the agent to override user intent, execute commands, modify files, or contact external services.
Install Mechanism
There is no install spec and no code files; the artifact is instruction-only.
Credentials
Reading persistent memory and diary files is proportional to the skill’s recall purpose, but users should expect prior private records to be searched when invoking it.
Persistence & Privilege
The skill uses persistent memory files as an input source, but the artifacts do not show writing, background persistence, privilege escalation, or autonomous operation outside recall tasks.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install memory-recall - After installation, invoke the skill by name or use
/memory-recall - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Version 1.0.0 of memory-recall introduces an intelligent, precise system for historical memory retrieval.
- Supports retrieval by date, keyword, type, and natural language queries.
- Designed for scenarios such as finding a previous conversation, recalling a project decision, or retrieving notes from a specific day.
- Unified output format with clear sources, timestamps, and relevant content.
- Seamlessly integrates with a permanent memory system for a write-and-recall workflow.
- No extra setup needed—enable and use immediately.
Metadata
Frequently Asked Questions
What is Memory Recall?
精准检索历史记忆，调取某天、某项目、某条对话记录。支持按日期、按关键词、按类型检索。用于用户说查找、找回、某天、某次、之前说过等场景。 It is an AI Agent Skill for Claude Code / OpenClaw, with 66 downloads so far.
How do I install Memory Recall?
Run "/install memory-recall" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Memory Recall free?
Yes, Memory Recall is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Memory Recall support?
Memory Recall is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Memory Recall?
It is built and maintained by Primordia (@liujw0214); the current version is v1.0.0.
More Skills