What problem does it solve? After running trellis init, teams often need to adapt the generated Trellis setup to their own workflow, but it is unclear which local files control phases, hooks, agents, skills, or specs. This Skill teaches an AI assistant the local Trellis architecture so it can safely modify the right files inside the user project instead of guessing or editing upstream source. ## Core Features & Use Cases - Architecture Orientation: Explains the three-layer local Trellis model (workflow, persistence, platform integration) and which files are editable versus managed runtime state. - Platform File Mapping: Maps directories like .claude/, .codex/, .cursor/, and .agents/skills/ to their hooks, agents, skills, and commands across many AI tools. - Customization Playbooks: Provides step-by-step references for changing workflow phases, task lifecycle hooks, context injection, agent behavior, spec structure, and project-local conventions. - Use Case: A user says "the implement agent never reads our backend spec." The Skill directs the AI to inspect the task's implement.jsonl, the platform agent file, and the inject-subagent-context hook, then fix the correct layer. ## Quick Start Ask the AI to use the trellis-meta skill to change how the check agent runs project-specific commands in this project.