skills.rest
wjlmrzd
wjlmrzdCOMMUNITY
Explore all skills by this author →
GitHub

self-improvement

Record developer learnings, errors, and feature requests into persistent markdown logs.

Updated Aug 27, 2026
Search Tags:#automation#self-improvement#hooks#learnings#openclaw#skill-extraction#error-logging
One-click install
npx skills add https://github.com/wjlmrzd/OpenClaw-Wren --skill self-improvement-wjlmrzd
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: self-improvement
Source: https://github.com/wjlmrzd/OpenClaw-Wren/tree/main/skills/self-improving-agent
Command: npx skills add https://github.com/wjlmrzd/OpenClaw-Wren --skill self-improvement-wjlmrzd

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Captures developer and agent learnings, command failures, and user corrections into a structured, durable log so knowledge gaps and recurring issues are discovered, tracked, and prevented from repeating.

Core Features & Use Cases

  • Structured Logs: Provides standardized templates and files (.learnings/LEARNINGS.md, ERRORS.md, FEATURE_REQUESTS.md) for consistent entries.
  • Hooked Reminders & Detection: Lightweight activator and error-detector scripts to remind agents to record learnings and surface command errors.
  • Skill Extraction & Promotion: Helper scripts and templates to scaffold new skills from verified, recurring learnings and promote high-value items to project memory files (CLAUDE.md, AGENTS.md, TOOLS.md).
  • Use Case: After a failed command or a user correction, record a concise entry with summary, context, suggested fix, and metadata so the issue can be triaged, promoted, or extracted into a reusable skill.

Quick Start

Log a correction by adding a concise learning entry to .learnings/LEARNINGS.md with category correction, a one-line summary, and a suggested action.

Frequently Asked Questions about self-improvement

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

FAQPage Schema
How do I log developer errors and corrections into structured markdown files?▼

Log developer errors and corrections by adding concise entries to persistent .learnings markdown files. The skill provides standardized templates in LEARNINGS.md, ERRORS.md, and FEATURE_REQUESTS.md to capture summaries, context, and suggested fixes for recurring issues.

What is the best way to track recurring command failures across agent workflows?▼

Track recurring command failures using lightweight activator and error-detector shell scripts that surface errors and remind agents to record learnings. This approach captures failures into durable markdown logs for continuous improvement across development sessions.

How do I promote verified learnings into reusable project memory files?▼

Promote verified learnings into project memory files like CLAUDE.md, AGENTS.md, and TOOLS.md using built-in helper scripts. The skill scaffolds new skills from high-value entries and integrates them directly into your project's persistent memory configuration.

Do I need to initialize a specific directory structure before logging agent learnings?▼

You need to initialize a .learnings directory containing LEARNINGS.md, ERRORS.md, and FEATURE_REQUESTS.md markdown files before logging agent learnings. This structured setup ensures consistent entry templates and persistent storage for developer corrections and best-practice discoveries.

Can I extract and scaffold new skills from recurring developer errors?▼

You can extract and scaffold new skills from recurring developer errors using the skill's extraction helper scripts and templates. This promotes high-value learnings from your structured markdown logs into reusable skill components for future agent workflows.

What limitations exist when using shell scripts for continuous improvement logging?▼

Shell-based continuous improvement logging relies on manual initialization of the .learnings directory structure and consistent agent adherence to entry templates. The lightweight activator scripts provide reminders but depend on workflow integration to successfully capture and triage command failures.

Related Skills

Explore More Software Engineering Skills→
LongTermSupportLongTermSupport

phpstan-fixer

Parse PHPStan error logs and apply fixes to modified files.

Official
Intermediate
g-lokg-lok
1

self-improving-agent

Organize learnings, errors, and feature requests into persistent markdown logs.

Community
Advanced
viably-labsviably-labs

self-improvement

Log learnings, errors, and feature requests to .learnings files.

Official
Advanced
791994545791994545
4

self-improving

Capture and log errors, learnings, and feature requests in Python and markdown.

Community
Advanced