According to AlphaMoat, as of 2026-10, 记忆系统框架 has 15,645 downloads and 6 stars — ranked by downloads #1,791 among 10,914 AI skills in this ranking, and #251 of 1,632 in AI Agent.
The list defaults to total downloads and can also be sorted by stars; detail-page rankings use total downloads.
| Platform | Downloads | Stars | Comments |
|---|---|---|---|
| SkillHub ↗ | 15.6K | 6 | — |
Platforms count differently and update at different times.
It describes using layered memory, a working buffer, decision records, error learnings, and daily reviews to organize long-term and current information, with a corresponding directory structure. It suits users building a persistent knowledge-management workflow; files and rules should be adapted to the project. Review the chosen file locations and sensitive information before creating or updating memory files.
Profile published 2026-10-29
Generated from the skill’s documentation as examples; not results of actual runs.
The counting method changed in 2026-09: skills with the same name are now counted separately by author, and the full catalog is covered. Dashed lines show months before the change; they are not compared with later months, and no growth is computed across the change.
| Month | Downloads | MoM | Stars |
|---|---|---|---|
| 2026-10 | 15.6K | — | 6 |
| 2026-09 | 6.1K | — | 6 |
| 2026-08 | 4.2K | +30.1% | 6 |
| 2026-07 | 3.2K | — | 4 |
| 2026-05 | 712 | — | - |
| 2026-03 | 193 | — | - |
The author’s original file, shown as plain text without edits or review by AlphaMoat. Links are not clickable; check commands before running them. Fetched 2026-10-23.
# Memory Framework - 记忆系统框架 **版本：** v1.0 **定位：** 通用记忆系统框架，基于OpenClaw改良 **适用：** 个人AI助手、团队协作，知识管理 --- ## 核心特性
- L1/L2/L3 三层记忆分层
- WAL Protocol - 决策先记后答
- Working Buffer - 上下文缓冲
- learnings系统 - 错误记录与复盘
- 每日复盘 - 持续优化
---
## 目录结构
```
memory-framework/
├── README.md
├── SKILL.md
├── manifest.json
├── brain/
│ ├── plan.md
│ ├── tasks/
│ │ ├── active.md
│ │ └── daily/
│ ├── me/
│ │ ├── identity.md
│ │ └── learned.md
│ ├── decisions/
│ ├── projects/
│ └── inbox.md
├── learnings/
│ ├── errors.json
│ └── recoveries.json
└── docs/
├── QUICK-START.md
└── TEMPLATES.md
```
---
## 快速开始
1. 编辑 brain/me/identity.md - 填入你的身份
2. 编辑 brain/plan.md - 填入你的目标
3. 编辑 brain/tasks/active.md - 填入当前任务
---
## 规则速查
| 场景 | 操作 |
|------|------|
| 用户纠正 | SESSION-STATE.md |
| 重大决定 | SESSION-STATE.md |
| 犯错 | learnings/errors.json |
| 上下文60% | working-buffer.md |
| 每天结束 | brain/tasks/daily/ |
---
## 版本
- v1.0 - 初始版本
---
**基于OpenClaw改良**
Records learnings, errors and corrections as Markdown files for later reuse and promotion into workspace memory.
Finds skills in local and remote catalogs from a plain-language request and recommends what to install.
A browser-automation command line skill for AI agents.
Turns corrections and self-review into tiered memory and promotes or archives it by use.
A workspace setup guide for planning proactive follow-up, working memory and review routines for an AI agent.
A guide to creating and updating effective Claude skills.
Reviews a third-party skill's source, permissions, and danger patterns against a checklist before it is installed.
以李白（701—762，字太白，号青莲居士，世称诗仙）的诗学观、意象系统与口吻，进行唐诗赏析、文学评论、考据问答与拟体创作。触发词：李白、李太白、太白、青莲居士、诗仙、谪仙人、将进酒、静夜思、蜀道难、唐诗、盛唐诗人、浪漫主义诗人、拟李白风格、以李白视角、李白会怎么写、用李白口吻。能力：诗词鉴赏与风格DNA解析、诗学观与文学谱系评述、诗句出处考据与真伪边界标注、以李白口吻答问、拟李白体旧体诗（必显式标注非原作）。适用边界：仅用于唐代文学与古典诗歌相关话题，非此类话题不触发；本 skill 为文学普及与研究辅助，不代表李白本人立场，所拟之作均非李白原作；涉及生平佚事、篇目归属等内容不构成学术定论，皆标存疑或待考。
Data as of 2026-10. Downloads and stars are aggregated monthly from public skill registries (ClawHub, SkillHub). See data methodology.