A structured framework for AI agents to log, track, and resolve errors and learnings for continuous improvement.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install cpskilltest111
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install cpskilltest111 using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Self-Improvement AI Skill?
The Self-Improvement Skill is a sophisticated framework designed to provide AI coding agents with a persistent memory of their mistakes, successes, and user preferences. By capturing unexpected command failures, direct user corrections, and discovered best practices into dedicated markdown files, this skill ensures that agents evolve rather than repeating past errors. It is a vital component for developers leveraging Openclaw Skills who want to bridge the gap between transient chat sessions and permanent project knowledge by promoting temporary learnings into long-term configuration files like CLAUDE.md, AGENTS.md, or SOUL.md.
Self-Improvement AI Skill Use Cases
- Capturing unexpected command or tool failures to prevent future execution errors.
- Documenting direct user corrections when an agent provides outdated or incorrect information.
- Logging requested capabilities that are currently missing for future development.
- Tracking recurring architectural patterns to simplify and harden codebase logic.
- Promoting verified project-specific conventions to permanent documentation files.
How Self-Improvement AI Skill Works
- The agent identifies a trigger such as a failed bash command or a "No, that is wrong" correction from the user.
- The skill appends a structured entry with metadata (ID, Priority, Area) to the appropriate log file in the .learnings directory.
- Before starting new tasks, the agent reviews existing logs to ensure relevant past experiences are considered.
- High-value or recurring entries are promoted to workspace-level memory files to provide permanent guidance across all future sessions.
Self-Improvement AI Skill Setup
To integrate this capability into your Openclaw Skills environment, installation via ClawdHub is recommended:
clawdhub install self-improving-agent
For a manual installation, clone the repository into your local skills directory:
git clone https://github.com/peterskoett/self-improving-agent.git ~/.openclaw/skills/self-improving-agent
Ensure the workspace structure is initialized:
mkdir -p ~/.openclaw/workspace/.learnings
Self-Improvement AI Skill Data Schema & Taxonomy
The skill organizes its intelligence within a .learnings directory using a structured markdown taxonomy:
| File | Purpose | Metadata Fields |
|---|---|---|
| LEARNINGS.md | Corrections and best practices | Priority, Status, Area, Pattern-Key |
| ERRORS.md | Command and tool execution failures | Error Message, Context, Reproducibility |
| FEATURE_REQUESTS.md | User-requested enhancements | User Context, Complexity, Frequency |
Entries use a standardized ID format: TYPE-YYYYMMDD-XXX (e.g., LRN-20250115-001).
Self-Improvement AI Skill Advanced Features
- Skill Extraction: Automated scripts to transform high-value, resolved learnings into entirely new, reusable Openclaw Skills.
- Hook-Based Reminders: Configuration for UserPromptSubmit and PostToolUse hooks to trigger automatic performance evaluation.
- Inter-Session Messaging: Built-in tools like sessions_send and sessions_spawn to share critical learnings between active agent threads.
- Recurring Pattern Detection: Ingests data from the simplify-and-harden workflow to identify and resolve systemic issues.
- Multi-Agent Compatibility: Native support for OpenClaw workspace injection, Claude Code hooks, and GitHub Copilot instructions.
SKILL.md
Loading
Related Openclaw Skills
Self-Improvement Agent Skill
A sophisticated logging and promotion framework that enables AI agents to learn from errors, user feedback, and discovered best practices.
LaunchFast Product Research
A high-speed multi-keyword Amazon product scanner that identifies winning FBA opportunities using advanced A10-F1 grading and parallel data processing.
LaunchFast PPC Research
A specialized tool for Amazon sellers to perform bulk competitor keyword research and generate campaign-ready PPC upload files.
LaunchFast Full Research Loop
A comprehensive five-phase automation that executes product research, IP checks, supplier sourcing, and PPC analysis into a professional HTML report.
Xiaohongshu Long-form Publisher
An automated workflow for publishing long-form articles directly to the Xiaohongshu creator platform.
Voice Call
A versatile skill that enables AI agents to initiate, manage, and interact through voice calls using leading telephony providers.
Featured*
