learning

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Claude Learner - Self-Improvement Skill

Claude Learner - 自我提升技能

You have access to claude-learner, a system that turns corrections into permanent rules.

你可以使用claude-learner系统，它能将修正建议转化为永久规则。

When to Use

使用场景

User corrects you ("No, don't do X, do Y instead")
You make a repeated mistake
User expresses a preference
A better pattern is discovered

用户对你进行修正（例如：“不对，不要做X，应该做Y”）
你重复犯同一错误
用户表达了偏好
发现了更优的模式

Available Commands

可用命令

Command	What It Does
`/learner:status`	Check daemon and rules status
`/learner:rules`	List all rules
`/learner:approve <id>`	Approve a pending rule
`/learner:reject <id>`	Reject a pending rule
`/learner:start`	Start the learning daemon
`/learner:stop`	Stop the learning daemon

命令	功能
`/learner:status`	检查守护进程和规则状态
`/learner:rules`	列出所有规则
`/learner:approve <id>`	批准待审核规则
`/learner:reject <id>`	拒绝待审核规则
`/learner:start`	启动学习守护进程
`/learner:stop`	停止学习守护进程

MCP Tools

MCP工具

If MCP is connected, you have these tools:

```
log_correction
```
- Log a correction event
```
propose_rule
```
- Propose a new rule
```
get_rules
```
- Get active rules
```
get_pending_rules
```
- Get rules awaiting approval
```
approve_rule
```
- Approve a rule
```
reject_rule
```
- Reject a rule
```
get_stats
```
- Get learning statistics

如果已连接MCP，你可以使用以下工具：

```
log_correction
```
- 记录修正事件
```
propose_rule
```
- 提出新规则
```
get_rules
```
- 获取生效规则
```
get_pending_rules
```
- 获取待审核规则
```
approve_rule
```
- 批准规则
```
reject_rule
```
- 拒绝规则
```
get_stats
```
- 获取学习统计数据

Best Practices

最佳实践

Detect corrections automatically - When user says "actually...", "no, use...", "don't do X", log it
Propose rules for patterns - If you see repeated corrections, propose a rule
Check rules periodically - Use
```
get_rules
```
to remind yourself of learned behaviors
Don't over-rule - Not every correction needs a permanent rule

自动检测修正建议 - 当用户说“实际上...”、“不对，应该用...”、“不要做X”时，记录该事件
针对模式提出规则 - 如果发现重复的修正建议，提出规则
定期检查规则 - 使用
```
get_rules
```
来提醒自己已习得的行为
避免过度创建规则 - 并非每个修正建议都需要转化为永久规则

Example Flow

示例流程

User: "Don't use rm, use trash instead"

1. Log correction: log_correction({ 
     pattern: "using rm command",
     correction: "use trash instead of rm",
     context: "file deletion"
   })

2. If pattern repeats, propose rule: propose_rule({
     content: "Always use `trash` instead of `rm` for file deletion",
     trigger: "rm command usage"
   })

3. Rule goes to pending → user approves → permanently active

User: "Don't use rm, use trash instead"

1. Log correction: log_correction({ 
     pattern: "using rm command",
     correction: "use trash instead of rm",
     context: "file deletion"
   })

2. If pattern repeats, propose rule: propose_rule({
     content: "Always use `trash` instead of `rm` for file deletion",
     trigger: "rm command usage"
   })

3. Rule goes to pending → user approves → permanently active