pskoett/self-improving-agent

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

All-time #2099 First seen Feb 18, 2026

8-week activity · all time api

Installation

$ npx skills add https://github.com/pskoett/self-improving-agent

View on skills.sh ↗ GitHub repository ↗

Feature your product here Skill page unit · reach builders installing agent skills View pricing →

Summary

Captures learnings, errors, and corrections to enable continuous improvement across agent sessions.
Logs failures, user corrections, knowledge gaps, and API errors to structured markdown files ( .learnings/LEARNINGS.md , ERRORS.md , FEATURE_REQUESTS.md ) with consistent ID, priority, and status tracking Supports promotion of broadly applicable learnings to project memory files ( CLAUDE.md , AGENTS.md , .github/copilot-instructions.md ) and workspace files in OpenClaw ( SOUL.md , TOOLS.md ) Includes OpenClaw workspace integration with automatic session injection, inter-session communication tools, and optional startup hooks for learning reminders Provides skill extraction workflow to convert recurring, verified learnings into reusable agent skills with quality gates and multi-agent support