self_improving_agent

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...

This skill appears to do what it says: add lightweight reminders and local logging of errors/learnings and offer a helper to scaffold new skills from those learnings. Before installing or enabling hooks: (1) verify the repository/source you clone matches the registry entry (the included _meta.json shows different metadata—confirm origin), (2) review the scripts (they only emit text and manipulate files in your workspace, but inspect extract-skill.sh before running to confirm it meets your expectations), (3) prefer project-level hook configuration rather than user-global if you want to avoid affecting all sessions, and (4) be aware that promoted files (CLAUDE.md, SOUL.md, etc.) are injected into agent context and will change agent behavior—treat that as a deliberate prompt-injection mechanism and review promoted content before making it global.

Type: OpenClaw Skill Name: selfimproving Version: 1.0.0 The self-improving skill bundle is designed to help an AI agent log errors, user corrections, and best practices into markdown files (e.g., .learnings/LEARNINGS.md) to improve future performance. It includes shell scripts (activator.sh, error-detector.sh, extract-skill.sh) for automated reminders and skill scaffolding, as well as OpenClaw hooks (handler.js) that inject reminders into the agent's bootstrap context. The code and instructions are transparent, lack obfuscation, and contain no evidence of data exfiltration or malicious intent; the behavior is entirely consistent with the stated goal of creating a feedback loop for agent self-improvement.