self-improvement

Log learnings and errors to markdown files for continuous improvement.

Updated Aug 23, 2026

Search Tags:#templates #documentation #logging #learnings #errors #promotion #progressive-loading

Ready to run

npx skills add https://github.com/ederheisler/agent-skills --skill self-improvement-ederheisler

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: self-improvement
Source: https://github.com/ederheisler/agent-skills/tree/main/skills/self-improving-agent
Command: npx skills add https://github.com/ederheisler/agent-skills --skill self-improvement-ederheisler

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Agents often lack a structured mechanism to capture and recall learnings, corrections, and mistakes, leading to repeated issues and slower improvement cycles.

Core Features & Use Cases

Centralized logging of learnings, errors, corrections, and feature requests to a dedicated .learnings/ store for progressive loading.
Templates and references in assets/ and references/ to ensure consistent entries and rapid promotion to project memory (CLAUDE.md or AGENTS.md).
Promotion workflow: promote broadly applicable learnings to CLAUDE.md or AGENTS.md to scale knowledge across the codebase.

Quick Start

Create the .learnings directory and log your first entry using the provided templates, then follow the progressive-loading workflow.

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 to markdown files for continuous improvement?▼

You log learnings and errors by creating a dedicated `.learnings/` store using provided templates, which enforces progressive-loading to capture corrections, failures, and feature requests for continuous improvement.

What is progressive-loading of learnings and how does it work?▼

Progressive-loading is a workflow that maintains entries in a `.learnings/` store, allowing agents to incrementally capture and recall mistakes without overwhelming context windows, fueling structured continuous improvement.

How do I promote broadly applicable learnings to CLAUDE.md or AGENTS.md?▼

You promote broadly applicable learnings to CLAUDE.md or AGENTS.md using the promotion workflow, which scales captured knowledge across the codebase by elevating critical entries from the `.learnings/` store.

Does this logging approach work without external dependencies?▼

Yes, the logging approach works without external dependencies, relying solely on markdown files, a `.learnings/` directory, and built-in templates in `assets/` and `references/` to structure entries.

When do I need to capture corrections and feature requests during development?▼

You need to capture corrections and feature requests during development, debugging, and user feedback workflows when agents repeat issues or lack a structured mechanism to recall past mistakes and improvements.

What's the best way to structure development learnings and avoid repeated mistakes?▼

The best way to structure development learnings is using centralized logging with consistent templates in a `.learnings/` store, enabling progressive-loading and promotion of critical knowledge to project memory files like CLAUDE.md.