Workflow hook metadata for agent-playbook skills. This skill documents trigger intent between skills - DO NOT use directly, and do not assume hooks execute unless the host runtime explicitly supports them.

Auto Trigger Hooks This skill defines trigger intent between skills. When a skill completes its workflow, a host runtime or agent may read this metadata, record a pending follow up, and execute the next skill only when that action is supported and safe for the current session. Hook Definitions PRD Creation Chain Implementation Chain Session Management Hook Format in Skills To add auto trigger capability to a skill, add to its front matter: Implementation Guide When a skill completes its workflow: 1. Check hooks in its own front matter ( before start , after complete , on error , on progress ) 2. For each hook: If mode: auto , record or run a low risk follow up only when the host runtime supports it If mode: background , record a non blocking follow up; do not mutate durable files silently If mode: ask first , ask user before triggering If condition: exists, check it first 3. Pass context to the triggered skill Example Integration prd planner should add self improving agent uses explicit validation and application gates Its Claude failure hook is installed by the CLI adapter, not declared as portable skill metadata. The hooks examples in this skill are declarative intent only unless a host adapter explicitly implements them. Other hosts should use documented adapters or manual capture. create pr should add Chain Visualization Error Correction Chain Important Rules 1. Don't create infinite loops Ensure chains terminate 2. Ask before major actions Use mode: ask first for PRs, deployments, and durable file changes 3. Background tasks Use mode: background for non blocking analysis or proposal artifacts 4. Pass context Always include relevant context to triggered skills

auto-trigger