self-improvement

Logs corrections and insights to YAML-formatted files in .learnings directory.

Updated Mar 3, 2026
One-click install
npx skills add https://github.com/Kushtrvedi/openclaw-standard --skill self-improvement-kushtrvedi
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: self-improvement
Source: https://github.com/Kushtrvedi/openclaw-standard/tree/main/skills/self-improving-agent-1.0.11
Command: npx skills add https://github.com/Kushtrvedi/openclaw-standard --skill self-improvement-kushtrvedi

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

Captures learnings, errors, and corrections to enable continuous improvement across OpenClaw sessions, ensuring valuable insights are retained and actionable.

Core Features & Use Cases

  • Logs learnings to the dedicated .learnings directory (LEARNINGS.md, ERRORS.md, and FEATURE_REQUESTS.md) to organize insights.
  • Promotes broadly applicable learnings to project memory (CLAUDE.md, AGENTS.md, and copilot-instructions.md) when ready.
  • Integrates with OpenClaw workspaces to share and apply lessons across sessions and tasks.

Quick Start

After completing a task, log the outcome to .learnings/ using the provided templates.

Frequently Asked Questions about self-improvement

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I log errors and learnings across different OpenClaw sessions?

To log errors and learnings across OpenClaw sessions, capture corrections and knowledge gaps into the .learnings directory using structured templates for continuous improvement.

What is the best way to retain knowledge gaps and feature requests in project memory?

Retain knowledge gaps and feature requests by logging them to dedicated files like FEATURE_REQUESTS.md, then promoting broadly applicable entries to project memory files when ready.

Can I promote logged corrections to CLAUDE.md or AGENTS.md?

Yes, you can promote logged corrections to CLAUDE.md, AGENTS.md, or copilot-instructions.md as optional promotion targets to share lessons across sessions and tasks.

How do .learnings templates support continuous improvement?

The .learnings templates support continuous improvement by providing a structured YAML format to organize errors, corrections, and feature requests into actionable insights.

Does capturing learnings require any external dependencies?

Capturing learnings requires no external dependencies, relying solely on internal scripts, references, and assets to manage logs within the OpenClaw workspace environment.

When should I not use a cross-session learning log?

Avoid a cross-session learning log for isolated, non-recurring tasks where errors or corrections will not be reused, as the overhead of maintaining insights outweighs the benefit.