What problem does it solve? Agent sessions often repeat the same mistakes or miss required checks, and manually reminding the agent every time is unreliable. This Skill turns concerns expressed in conversation into persistent hook files that block actions, inject context, or automate behavior at lifecycle events. ## Core Features & Use Cases - Policy Enforcement: Create hooks that block or gate specific tool actions, such as preventing dangerous commands before they run. - Context Injection: Automatically inject relevant context at events like SessionStart or PreToolUse so the agent always has the right information. - Lifecycle Automation: Automate tasks at session start, session end, or tool use with optional companion scripts. - Use Case: After telling the agent multiple times to never run a destructive command, use this Skill to generalize that concern into a PreToolUse hook saved in .github/hooks/ that blocks it permanently. ## Quick Start Ask the agent to create a hook that blocks a specific command or injects context at session start, and it will draft the JSON hook file in .github/hooks/ for your review.