onboard

Onboard developers to AI-assisted Trellis workflows and project-specific guidelines.

Updated Apr 13, 2026
One-click install
npx skills add https://github.com/MaplumeX/deepresearch --skill onboard-maplumex
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: onboard
Source: https://github.com/MaplumeX/deepresearch/tree/main/.agents/skills/onboard
Command: npx skills add https://github.com/MaplumeX/deepresearch --skill onboard-maplumex

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This onboarding Skill solves the problem of bringing new developers up to speed on an AI-assisted Trellis workflow by explaining project-specific conventions, session memory, and safeguards so AI can be used effectively and safely within the team.

Core Features & Use Cases

  • Three-part interactive onboarding: Teaches core philosophy, system structure, and a deep dive into workflow skills ($start, $before-dev, $check, $finish-work, $record-session) so developers understand why each step exists and what it achieves.
  • Real-world workflow walkthroughs: Detailed, step-by-step examples for bug fixes, planning, code review fixes, large refactors, and debugging that explain the principle, what happens, and the consequences of skipping steps.
  • Guidelines customization assistance: Detects whether .trellis/spec guideline templates are empty and guides the developer through analyzing the codebase and filling project-specific conventions to ensure future AI actions align with team standards.

Quick Start

Start an interactive onboarding session that explains Trellis core concepts, walks through the five real-world workflow examples step by step, and helps you inspect and customize the .trellis/spec guideline files for your project.

Frequently Asked Questions about onboard

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I onboard new developers to an AI-assisted workflow with project-specific guidelines?

Developer onboarding to an AI-assisted workflow involves teaching project-specific conventions, session memory, and safeguards through interactive walkthroughs covering bug fixes, planning, and code reviews to ensure AI is used safely within the team.

What is the Trellis workflow process for bug fixes and code refactoring?

The Trellis workflow process for bug fixes and refactoring follows five sequential steps: $start, $before-dev, $check, $finish-work, and $record-session, each requiring human review before commits to maintain code quality and project alignment.

How do I customize empty .trellis spec guideline templates for my repository?

To customize empty .trellis spec guideline templates, analyze your codebase to identify project-specific conventions, then fill the spec files so future AI actions and session recordings align with established team standards and code quality requirements.

Do I need a .trellis workspace directory to use AI-assisted developer onboarding?

Yes, a .trellis workspace directory is required for AI-assisted developer onboarding, as the process needs access to run or simulate the $start, $before-dev, $check, $finish-work, and $record-session commands within repositories using spec conventions.

Why does the AI workflow require human review before commits during session recording?

Human review before commits is required during session recording because the AI workflow generates code suggestions and executes workflow steps that must be validated against project-specific guidelines to prevent quality issues and ensure safe AI integration.

What happens if I skip the $before-dev or $check steps in the Trellis workflow?

Skipping the $before-dev or $check steps in the Trellis workflow breaks the safeguard chain, risking misaligned AI actions, undetected code quality issues, and non-compliant commits that bypass the project-specific spec conventions established during onboarding.