Self Improvement

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: remind agents to log learnings and optionally detect failed commands and scaffold new skills. Before installing or enabling hooks: 1) Review the hook and script files (hooks/openclaw/handler.{js,ts}, scripts/*.sh) to ensure you trust their content and the repo source; 2) Understand that enabling the hook injects a reminder into every session bootstrap (this intentionally modifies session context and can influence assistant behavior); 3) If you enable the PostToolUse hook, be aware the error-detector reads CLAUDE_TOOL_OUTPUT (tool outputs may include sensitive data), so limit that hook to project-level settings or add matcher filters if you don't want global activation; 4) The extract-skill.sh will create files under a relative ./skills path — run with --dry-run first and ensure file permissions are appropriate; 5) Prefer installing in a controlled user environment (project-level settings) rather than globally, and verify the upstream GitHub repository if you want an auditable source.

Type: OpenClaw Skill Name: self-improving-agent-6 Version: 0.1.0 The self-improving-agent skill bundle is a productivity tool designed to help AI agents log errors, learnings, and feature requests into a structured `.learnings/` directory. It includes utility shell scripts (`activator.sh`, `error-detector.sh`, `extract-skill.sh`) and OpenClaw hooks (`handler.js`) that facilitate a feedback loop where the agent can eventually promote verified patterns to workspace configuration files like `SOUL.md` or `AGENTS.md`. The implementation is transparent and includes security best practices, such as strict regex validation for skill names and path traversal checks in the extraction script to prevent writing outside the intended directory. No evidence of data exfiltration, malicious persistence, or harmful intent was found.