keep-learning-agent
持续学习 Agent - 知识沉淀和经验固化框架。支持学习记录、快速索引、自我修复、经验→模型转化。包含完整模板、索引系统、SOP 流程。让 AI Agent 持续进化,每天进步一点点。
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/chow651/keep-learning-agentKeep Learning Agent - 持续学习系统
统一的知识沉淀和经验固化系统
核心理念:学到的东西必须固化成可复用的模块和文档,而不是只存在于临时会话中
🎯 核心功能
| 功能 | 说明 | 文件 |
|---|---|---|
| 学习记录 | 统一格式记录新知识 | .learnings/LEARNINGS.md |
| 快速索引 | 按状态/类别/领域/Patter n-Key 查找 | .learnings/INDEX.md |
| 自我修复 | 会话启动自动检查 pending 项 | G:\clawbot\config\self-repair.ps1 |
| 经验→模型 | 重复模式转化为思维模型 | lib/KNOWLEDGE-SOP.md |
| 模板系统 | 统一学习记录格式 | .learnings/templates/ |
| 归档机制 | 定期整理已 promoted 学习 | .learnings/archive/ |
📁 目录结构
.learnings/
├── README.md # 使用指南
├── INDEX.md # 快速索引(自动更新)
├── LEARNINGS.md # 主学习记录
├── ERRORS.md # 错误记录
├── FEATURE_REQUESTS.md # 功能请求
├── INTEGRATION-REPORT.md # 整合报告
├── TEMPLATE-ANALYSIS.md # 模板分析报告
├── templates/
│ └── learning-template.md # 统一模板
└── archive/ # 已归档学习
└── 2026-03/
lib/
├── feishu_api.py # 可复用模块示例
├── README.md # 库文档
└── KNOWLEDGE-SOP.md # 知识固化 SOP
G:\clawbot\config\
├── self-repair.ps1 # 自我修复脚本
├── autoload-configs.ps1 # 配置自动加载
└── skills-config.json # 技能配置注册表
📝 学习记录模板
标准格式
## [LRN-YYYYMMDD-XXX] 简短标题
**Logged**: 2026-03-04T15:45:00+08:00
**Priority**: low | medium | high | critical
**Status**: new | in_progress | resolved | promoted | archived
**Category**: technical_solution | process_improvement | mindset | bug_fix | feature_request
**Area**: integration | automation | memory | api | ui | cognitive | config
**Source**: conversation | error | user_feedback | self_discovery
### 问题描述
清晰描述遇到的问题和背景
### 根因分析
用 5Why 或其他方法找到根本原因
### 解决方案
详细的解决步骤和代码
### 可复用场景
列出可以复用的场景
### 代码/脚本
可复用的代码片段或脚本位置
### 依赖
需要的库、配置、权限等
### 测试结果
测试时间、结果
### 关联
- **Related**: [LRN-XXXX-XXX](#lrn-xxxx-xxx)
- **See Also**: [文档链接](url)
- **Tags**: tag1, tag2
### Metadata
- **Pattern-Key**: unique.pattern.key
- **Recurrence-Count**: 1
- **First-Seen**: 2026-03-04
- **Last-Seen**: 2026-03-04
- **Time-Spent**: 30min
- **Skill-Path**: skills/skill-name (if promoted_to_skill)
字段说明
| 字段 | 必填 | 说明 |
|---|---|---|
| Logged | ✅ | ISO-8601 时间戳 |
| Priority | ✅ | low/medium/high/critical |
| Status | ✅ | new/in_progress/resolved/promoted/archived |
| Category | ✅ | 学习类别 |
| Area | ✅ | 相关领域 |
| Source | ✅ | 学习来源 |
| Pattern-Key | ✅ | 唯一模式标识 |
| Recurrence-Count | ⚠️ | 重复次数(可选) |
| Time-Spent | ⚠️ | 花费时间(可选) |
🔄 状态流转
new → in_progress → resolved → promoted → archived
↓
abandoned (明确不做)
| 状态 | 说明 | 操作 |
|---|---|---|
| new | 刚记录,未处理 | 安排优先级 |
| in_progress | 正在处理 | 更新进展 |
| resolved | 已解决,待固化 | 封装模块/更新文档 |
| promoted | 已提升到更高层 | 如写入 AGENTS.md |
| archived | 已归档 | 移入 archive/ |
| abandoned | 明确不做 | 记录原因 |
🏷️ 分类体系
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-chow651-keep-learning-agent": {
"enabled": true,
"auto_update": true
}
}
}Tags
Related Skills
feishu-memory-recall
Cross-group memory, search, and event sharing for OpenClaw Feishu agents
capability-evolver
A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution.
Whistle RPC
Production Solana RPC for AI agents. Unlimited JSON-RPC, WebSocket. 1 SOL/month via on-chain payment. No rate limits, no tiers.
decision-log
AI-powered decision journal for solopreneurs — capture decisions with context, rationale, and expected outcomes, then review them later to learn from what you got right and wrong.
WalletPilot-7715
Execute on-chain transactions with user-granted permissions. Built on MetaMask ERC-7715. No private keys, full guardrails.