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.
npx skills add https://github.com/pskoett/pskoett-ai-skills --skill self-improvement