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 files are safe to edit and how the pieces connect. This Skill explains the local Trellis architecture and directs AI agents to the correct customization entry points inside a user project. ## Core Features & Use Cases - Architecture Reference: Documents the three-layer local Trellis model covering .trellis/workflow.md, tasks, specs, workspace memory, and context injection. - Platform File Map: Maps hooks, settings, agents, skills, and commands across platforms such as Claude Code, Cursor, Codex, OpenCode, Kiro, and Gemini CLI. - Customization Guides: Provides step-by-step references for changing workflow phases, task lifecycle hooks, context loading, agents, skills, and spec structure. - Use Case: A user asks to make the check agent run project-specific lint commands; the Skill directs the AI to edit the platform's trellis-check agent file and update .trellis/spec/ rather than upstream Trellis source. ## Quick Start Ask the AI to customize your project's Trellis setup, for example: change the workflow so tasks can be skipped for one-reply questions, and it will read the local .trellis/ files and edit the right ones.