learning
3
总安装量
1
周安装量
#58789
全站排名
安装命令
npx skills add https://github.com/unisone/claude-learner --skill learning
Agent 安装分布
mcpjam
1
claude-code
1
kilo
1
junie
1
zencoder
1
Skill 文档
Claude Learner – Self-Improvement Skill
You have access to claude-learner, a system that turns corrections into permanent rules.
When to Use
- 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
Available Commands
| 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 |
MCP Tools
If MCP is connected, you have these tools:
log_correction– Log a correction eventpropose_rule– Propose a new ruleget_rules– Get active rulesget_pending_rules– Get rules awaiting approvalapprove_rule– Approve a rulereject_rule– Reject a ruleget_stats– Get learning statistics
Best Practices
- 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_rulesto remind yourself of learned behaviors - Don’t over-rule – Not every correction needs a permanent rule
Example Flow
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 â user approves â permanently active