Self Improvement

Logs errors, user corrections, and feature requests into structured markdown files so you can build institutional memory across agent sessions. Creates three files in .learnings/ with timestamped entries that track what went wrong, what you learned, and what users asked for. The real value is in the promotion workflow: once a learning proves broadly applicable, you distill it into CLAUDE.md or AGENTS.md so future agents inherit the knowledge without re-learning. The simplify and harden integration uses pattern keys to deduplicate recurring issues. Most useful in long-running projects where the same agent (or team of agents) needs to get smarter over time instead of making the same mistakes in every new conversation.

skills.sh installs: 2.1K
GitHub stars: 331
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add pskoett/pskoett-ai-skills --skill self-improvement --agent claude-code

Installs into .claude/skills of the current project.

Files

Self-Improvement Skill

Log learnings and errors to markdown files for continuous improvement. Coding agents can later process these into fixes, and important learnings get promoted to project memory.

For installation commands, see references/installation.md. For optional agent activation and hooks, see references/hooks-setup.md. Read these only when installing or configuring the skill.

Pair with self-healing: self-healing is the active runtime recovery primitive — it diagnoses, patches, verifies, and files HEAL- entries to .learnings/HEALS.md when something breaks mid-task. Self-improvement (this skill) is the passive accumulation and promotion layer — it logs corrections, knowledge gaps, and feature requests, and promotes recurring heal handoffs to permanent memory. They share .learnings/ but write to different files; verify discipline lives in self-healing, promotion logic lives here.