What problem does it solve? Agent sessions often need consistent guardrails—blocking risky commands, injecting context at the right moment, or automating setup at session start. This Skill turns those recurring concerns into concrete hook definitions stored in .github/hooks/, so policies are enforced automatically instead of repeated in every prompt. ## Core Features & Use Cases - Policy Enforcement: Draft hook JSON that blocks, warns on, or gates specific tool actions such as dangerous commands. - Lifecycle Automation: Configure hooks for events like PreToolUse, SessionStart, or Stop to inject context or run companion scripts. - Conversation-Driven Extraction: Generalize concerns expressed during the conversation (e.g., "always check before doing X") into reusable hook rules. - Use Case: A user repeatedly tells the agent not to run destructive git commands. The Skill extracts that concern, drafts a PreToolUse hook in .github/hooks/ that blocks the command, and suggests how to test it. ## Quick Start Ask the agent to create a hook that blocks force-pushing to the main branch before any git push command runs.
