agentic-behavior

Correct a behavior mistake I made and update rules to prevent recurrence

Git-backed memory and prompt tracking with self-checking reminders. Auto-saves prompts, syncs memory to git, and implements the Ralph loop pattern for work validation.

Use this skill when the user says you did something wrong, made a mistake, or wants to correct your behavior. Trigger phrases include "don't do that", "that's wrong", "stop doing X", "you should have done Y", "correct yourself", "fix your behavior", "remember to always/never", or any feedback about incorrect AI actions that should be prevented in the future.

Use this skill when the user says "make an issue", "create an issue", "file a bug", "this is a bug", "let's follow up later", "track this", "open a ticket", "create a ticket", "log this for later", "we need to fix this", "add to backlog", "make a task for", "file an enhancement", "create a feature request", or any phrase indicating that something should be tracked, logged, or followed up on in a ticketing system.

Detect time-referencing language in user prompts and investigate history before answering. Auto-recall when users say "now", "still", "yet", "changed", "has X", "did Y", etc.

4 hooks across 3 events