self-improve

Log mistakes and lessons to a local JSONL store via CLI.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/leonardofhy/openclaw-workspace --skill self-improve-leonardofhy
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: self-improve
Source: https://github.com/leonardofhy/openclaw-workspace/tree/main/exports/starter-kit/skills/self-improve
Command: npx skills add https://github.com/leonardofhy/openclaw-workspace --skill self-improve-leonardofhy

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires shared.jsonl_store, and includes scripts (resource) components.

What problem does it solve?

Logs mistakes and lessons to improve future sessions and prevent repeated errors.

Core Features & Use Cases

  • Tracks corrections, knowledge gaps, and best practices with recurrence; enables review of pending items and promotion of insights to permanent files.
  • Enables search across past learnings and errors to identify patterns and derive actionable improvements.
  • Provides a CLI to log, review, resolve, and promote learning entries across sessions.

Quick Start

Log a correction after a command fails and review recurring items to promote them into permanent files.

Frequently Asked Questions about self-improve

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

FAQPage Schema
How do I log command failures and corrections to prevent recurring errors?

You can log command failures and corrections using a CLI that records mistakes and lessons to a local JSONL store, tracking recurrence to prevent repeated errors across future sessions.

What is the process for promoting recurring mistakes to permanent files?

Promoting recurring mistakes to permanent files happens automatically when recurrence thresholds are met, elevating frequent errors and lessons from pending logs into permanent records.

Can I search past learnings and errors to identify patterns in my workflow?

Yes, you can search across past learnings and errors stored in the JSONL file to identify recurring patterns and derive actionable improvements for your workflow.

Do I need a local JSONL store to track knowledge gaps and best practices?

Yes, a local JSONL store is required to log mistakes, track knowledge gaps, and record best practices, serving as the persistent backend for reviewing and resolving learning entries.

How do I review and resolve pending learning entries across sessions?

You can review and resolve pending learning entries across sessions using the provided CLI, which interfaces with the JSONL store to log, manage, and promote insights when recurrence thresholds are met.