From trabuco
Propose what to add next to an existing Trabuco project based on its current state and what the user wants to achieve. Different from /trabuco:add-module — that adds a specific module; this one ADVISES on what to add. Use when the user has a project and asks "what's next?" or "how would you extend this?"
How this skill is triggered — by the user, by Claude, or both
Slash command
/trabuco:extendThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
1. **Load context**:
Load context:
mcp__trabuco__get_project_info for the current projectmcp__trabuco__scan_project for a deeper structural readtrabuco://modules resource to know the full catalogLoad expertise: request the extend_project MCP prompt (argument: project path). This loads Trabuco's extension philosophy — the reasoning framework the advice should follow.
Understand the goal: if the user's argument is vague, ask specifically what they want to enable. "Make it faster" is too vague; "handle 10k concurrent requests" is actionable.
Match against patterns: call mcp__trabuco__suggest_architecture with the extended requirements (current + goal). Compare the recommended config against what's currently installed. The delta is the extension proposal.
Present as a plan, not a wall of text: for each proposed addition, say:
Offer to execute: if the user approves, delegate to /trabuco:add-module for each addition. If the proposal involves creating new entities/endpoints/events, mention that the project's own .claude/skills/ already has /add-entity, /add-endpoint, etc. for the implementation work.
FooRepository.findAll()" is a valid answer.trabuco://limitations before proposing something Trabuco can't help with (e.g., adding GraphQL, adding a React frontend).npx claudepluginhub arianlopezc/trabuco --plugin trabucoGuides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.