Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
Initial release of the self-improving-agent skill for OpenClaw and other agent environments. - Provides structured markdown logging for learnings, errors, and feature requests to enable continuous improvement. - Includes detailed templates and workflow recommendations for capturing corrections, failures, knowledge gaps, and user feedback. - Outlines promotion process for learnings to project memory files (e.g., CLAUDE.md, AGENTS.md, TOOLS.md). - Compatible with OpenClaw: supports workspace setup, session sharing tools, and optional hooks. - Offers generic guidance for integrating with other AI agents (Copilot, Claude Code, etc.). - Defines standardized ID generation, resolution tracking, and status management for all learnings.