self-improve
Self-Improvement Engine - AI Agent that learns from mistakes and continuously improves. No more repeating the same errors.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/aptratcn/xiaobai-self-improveSelf-Improvement Engine 🔄
AI Agent that learns from mistakes and continuously improves. No more repeating the same errors.
The Problem
AI Agents make the same mistakes repeatedly:
- Forgot to verify before saying "done"
- Made incorrect time calculations
- Promised tasks but didn't execute
- Gave vague responses instead of concrete action
Each session starts fresh, learning nothing from past failures.
The Solution
Mistake Log
Track every mistake in memory/mistakes.json:
{
"mistakes": [
{
"date": "2026-04-21",
"type": "fake_completion",
"description": "Said 'cron task created' but only wrote to file",
"impact": "User didn't receive scheduled messages",
"lesson": "Always verify task exists via cron list before claiming done",
"rule": "MUST run verification command after any creation action"
},
{
"date": "2026-04-21",
"type": "time_calculation",
"description": "Said '1 minute later' when it was actually 1 hour",
"impact": "User got wrong expectation",
"lesson": "Never calculate time mentally - always use tools",
"rule": "Use session_status or date command for time, never mental math"
}
]
}
Improvement Rules
Based on mistakes, auto-generate rules in WORK_RULES.md:
## Learned Rules (from mistakes)
1. After creating any cron task → MUST run `openclaw cron list` to verify
2. Time calculations → MUST use `session_status` or Python, never mental
3. Multi-step task → MUST checkpoint after each step
4. Tool error → MUST report immediately, don't silently retry
Self-Audit Protocol
Every heartbeat or session start:
1. Read mistakes.json
2. Read WORK_RULES.md
3. Check: Am I about to violate any learned rule?
4. If yes → adjust behavior
5. If I make a mistake → log it immediately
Mistake Categories
| Type | Description | Prevention |
|---|---|---|
fake_completion | Said done but didn't do | EVR: Execute-Verify-Report |
time_calculation | Wrong time math | Use tools, never mental |
silent_failure | Tool failed, didn't tell user | Report immediately |
vague_promise | "I'll do it" without action | Execute first, then report |
forget_context | Lost important info | Use memory tools |
wrong_assumption | Guessed instead of checking | Verify before claiming |
Usage Examples
When you make a mistake:
User: "You said 1 minute but it's actually 1 hour"
I acknowledge this mistake. Let me log it:
- Type: time_calculation
- Lesson: Always use tools for time, never mental math
- New rule added to WORK_RULES.md
I will not make this mistake again.
When starting a task:
I need to create a cron task.
Checking WORK_RULES.md:
- Rule #1: After creating cron task → MUST verify with cron list
[Creates task]
[Runs openclaw cron list]
[Confirms task exists]
Task verified and confirmed. ✅
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-aptratcn-xiaobai-self-improve": {
"enabled": true,
"auto_update": true
}
}
}Tags
Related Skills
synapse-wiki
Synapse Wiki — 智能知识库管理系统。 自动摄取原始资料,增量构建持久化知识网络,支持智能查询和健康检查。 知识随时间复利积累,越用越聪明。 当用户提到 wiki、知识库、摄取资料、查询知识、整理文档时使用此技能。
undertow
Skill discovery engine for AI coding agents. Recommends and installs the right skill when you need it — code review, test generation, debugging, commit messages, PR preparation, security scanning, dependency audits, Docker setup, CI/CD pipelines, API documentation, refactoring, performance optimization, bundle analysis, git recovery, README generation, license compliance, migration guides, dead code removal, and secret detection. One install gives your agent access to a curated library of 20+ developer workflow skills. Use when the user asks for help with any development workflow, code quality, DevOps, security, testing, documentation, or project setup task.
context-compressor
Intelligently compress context — conversations, code, logs. Preserve key information while reducing token usage. Auto-detects content type and applies optimal compression.
daily-report-generator
Automatically generate daily/weekly work reports from git commits, calendar events, and task lists. Use when you need to quickly create professional work reports without manual effort.
auto-context
智能上下文卫生检查器。分析当前会话的上下文污染程度 (长对话、主题漂移、噪声累积),建议:continue、/fork、/btw 或新会话。 支持手动触发(/auto-context)和自动触发(响应层实现)。 基于 ArXiv 论文和认知心理学研究的多维度评估体系。