/onboard

name: onboard
description: "Developer onboarding guide that composes architecture mapping, tooling review, and agentic setup review with setup, troubleshooting, and next-steps agents to produce a comprehensive guide at .turbo/onboarding.md and .turbo/onboarding.html. Use when the user asks to \"onboard me\", \"onboard to this project\", \"generate onboarding guide\", \"new developer guide\", \"how do I get started\", or \"help me ramp up\"."

Onboard

Developer onboarding pipeline. Composes `/map-codebase`, `/review-tooling`, and `/review-agentic-setup` with inline agents, then synthesizes everything into `.turbo/onboarding.md` and `.turbo/onboarding.html`. Analysis-only.

Task Tracking

At the start, use `TaskCreate` to create a task for each phase:

1. Launch all agents 2. Synthesize and generate markdown report 3. Generate HTML report

Step 1: Launch All Agents

Emit all 6 Agent tool calls below in one assistant message. Each Agent call uses `model: "opus"` and no `name`. Wait for every agent to report before continuing. Do not begin the next step on a partial set, and do not relaunch an agent that has not yet reported. Each Composed Skills agent invokes its assigned skill via the Skill tool; each Inline Agent follows its exploration brief directly. Every agent's prompt must direct it to treat the shared working tree and its git index as read-only and to explore by reading and reasoning, except that each Composed Skills agent writes the report files its own skill defines. HEAD stays where it is: read other refs with `git show <ref>:<path>` rather than `git checkout` or `git switch`.

Composed Skills

Launch one Agent tool call per row. Each agent's prompt instructs it to invoke its assigned skill via the Skill tool.

| Skill | Onboarding role | |---|---| | `/map-codebase` | Architecture understanding: structure, tech stack, entry points, patterns, data flow, dependencies, testing | | `/review-tooling` | Development workflow: linters, formatters, pre-commit hooks, test runners, CI/CD | | `/review-agentic-setup` | Agentic coding: CLAUDE.md, AGENTS.md, skills, MCP servers, hooks, cross-tool compatibility |

Inline Agents

Launch one Agent tool call each with the exploration brief below.

| Agent | Exploration Brief | |---|---| | Prerequisites and Setup | Read README.md, CONTRIBUTING.md, and package manager configs (package.json, Gemfile, Cargo.toml, go.mod, pyproject.toml, Package.swift, etc.). Extract: required language runtimes and versions, system dependencies, environment variables, database or service requirements, first-time setup steps (install, build, run, seed), and any bootstrap or setup scripts. | | Troubleshooting | Search for troubleshooting content in README.md, TROUBLESHOOTING.md, docs/ directory, FAQ files, and GitHub Discussions/Wiki if accessible. Extract common errors, known quirks, platform-specific gotchas, and debugging tips. If no troubleshooting docs exist, report that. | | Next Steps | Run `gh issue list --state open --json number,title,url,reactionGroups,comments,labels --limit 50`. Identify: (1) issues labeled `good-first-issue` or `good first issue`, (2) top 5 issues by engagement score (sum of reactions weighted 2x for thumbs-up, plus comment count). If `gh` is not available or not in a GitHub repo, skip and note that. |

Each agent writes its findings as structured markdown.

Step 2: Synthesize and Generate Markdown Report

After all agents complete:

1. Read all agent reports. Check if `.turbo/threat-model.md` exists; if so, read it for the Security Considerations section. Collect each surface's cited paths from **Entry points and sinks** and **Hot files**, ignoring any `:line` suffix. Treat the threat model as superseded when a surface has no cited path that still resolves. In place of a superseded threat model's content, name its path and state that it predates the current code. 2. Reframe review skill outputs as documentation. `/review-tooling` findings become "Development Workflow" (what tools are used and how to run them). `/review-agentic-setup` findings become "AI-Assisted Development" (what's set up and how to use it). Focus on what exists, not what's missing. Strip severity labels, findings numbering, and gap framing from review skill outputs. Present detected tools and configurations as project conventions the new developer should know. 3. Write a brief welcome summary (3-5 sentences) capturing what the project is, who it's for, and the fastest path to a first contribution. 4. Write `.turbo/onboarding.md` using the report template. Output the welcome summary as text before writing the file.

Report Template

# Onboarding Guide

**Date:** <date>
**Project:** <project name>

## Welcome

<3-5 sentences: what this project is, who it's for, fastest path to a first contribution>

## Prerequisites and Setup

<from Prerequisites and Setup agent: language runtimes, dependencies, first-time setup steps, build/run commands>

## Architecture Overview

<from /map-codebase: condensed executive summary and key structural insights — not the full report, which lives at .turbo/codebase-map.md>

## Development Workflow

<from /review-tooling: reframed as "how to develop" — what linters/formatters to run, how to test, pre-commit hooks, CI/CD pipeline>

## AI-Assisted Development

<from /review-agentic-setup: reframed as "how to use AI coding tools" — what CLAUDE.md/AGENTS.md cover, installed skills, MCP servers, cross-tool compatibility>

## Security Considerations

<from .turbo/threat-model.md if present: key trust boundaries, security-sensitive areas, and what to be careful with, or, when it is superseded, its path and a note that it predates the current code. Omit this section when no threat model exists>

## Troubleshooting

<from Troubleshooting agent: common errors, known quirks, debugging tips, or "no troubleshooting docs found">

## Next Steps

<from Next Steps agent: good-first-issue issues, top-engaged issues, or "