By xiuchengUpdated 2026-05-11xiucheng-self-improving-agent@clawhub_xiucheng/xiucheng-self-improving-agent
Prompt OptimizationContext ManagementMemory#Self Improving#Self Improvement#Learning#Growth#Optimization
According to AlphaMoat, as of 2026-10, Self Improving Agent has 174,120 downloads and 80 stars — ranked by downloads #147 among 10,914 AI skills in this ranking, and #32 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 |
|---|---|---|---|
| ClawHub ↗ | 50.2K | 60 | - |
| SkillHub ↗ | 174.1K | 80 | — |
Platforms count differently and update at different times.
The source lists these capabilities: evaluating how effective a conversation was, spotting areas to enhance, writing lessons into a learning log, producing periodic improvement summaries, and adjusting response strategy over time. Usage covers automatic analysis as well as manual logging, the latter calling log_improvement from Python with a note. A configuration table sets the log path, a personality anchor file, and whether analysis runs automatically. Review and redact entries before saving: conversation logs may persist private prompts, customer data, credentials or other sensitive information in the local workspace.
Profile published 2026-10-27
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 | 174.1K | — | 80 |
| 2026-09 | 79.4K | — | 78 |
| 2026-08 | 63.9K | +25.9% | 78 |
| 2026-07 | 50.7K | — | 78 |
| 2026-05 | 45.1K | — | 69 |
| 2026-03 | 33.7K | — | 50 |
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.
--- name: self-improving-agent description: Self-improving agent system that analyzes conversation quality, identifies improvement opportunities, and continuously optimizes response strategies. version: "1.0.0" author: xiucheng type: skill tags: [self-improvement, learning, optimization, reflection, growth] homepage: https://github.com/xiucheng/self-improving-agent license: MIT ---
# Self-Improving Agent
An intelligent self-improvement system for OpenClaw agents that analyzes conversation quality and continuously optimizes performance.
## Features
- 📊 **Quality Analysis**: Evaluates conversation effectiveness
- 🎯 **Improvement Tracking**: Identifies areas for enhancement
- 📝 **Learning Log**: Records insights and lessons learned
- 📈 **Weekly Reports**: Generates improvement summaries
- 🔄 **Strategy Optimization**: Adapts response patterns over time
## Installation
```bash
clawhub install self-improving-agent
```
## Usage
### Automatic Analysis
The skill automatically analyzes conversations after each session.
### Manual Improvement Logging
```python
from self_improving import SelfImprovingAgent
sia = SelfImprovingAgent()
sia.log_improvement("Need to be more concise in technical explanations")
```
### Generate Weekly Report
```python
report = sia.generate_weekly_report()
print(report)
```
## Configuration
| Setting | Default | Description |
|---------|---------|-------------|
| improvement_log | ./improvement_log.md | Learning log file |
| soul_file | ./SOUL.md | Personality anchor file |
| auto_analyze | true | Auto-analyze conversations |
## Integration
Works best with:
- `memory-manager`: For tracking improvement history
- Custom agent personalities (SOUL.md)
## License
MIT License - Help agents get better every day!
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.