skills.rest
autopus-ai
autopus-aiOFFICIAL
Explore all skills by this author →
GitHub

auto-setup

Analyzes a codebase and generates persistent project context documents including ARCHITECTURE.md.

111|73|Updated Mar 20, 2026
Search Tags:#architecture#documentation#onboarding#ai agent#codebase analysis#project context#autopus
One-click install
npx skills add https://github.com/autopus-ai/autopus-adk --skill auto-setup-autopus-ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: auto-setup
Source: https://github.com/autopus-ai/autopus-adk/tree/main/.omp/skills/auto-setup
Command: npx skills add https://github.com/autopus-ai/autopus-adk --skill auto-setup-autopus-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? New sessions with an AI coding agent start with zero knowledge of your project, forcing you to re-explain the architecture, tech stack, and conventions every time. This Skill analyzes the codebase once and generates persistent context documents that are automatically loaded in future sessions. ## Core Features & Use Cases - Codebase Analysis via Subagent: Dispatches an explorer subagent to map directory structure, tech stack, entry points, architecture patterns, and domain boundaries. - Context Document Generation: Creates or updates ARCHITECTURE.md plus .autopus/project files covering product purpose, structure, tech stack, workspace boundaries, E2E scenarios, and canary health checks. - Use Case: When returning to a long-dormant repository or onboarding a new monorepo, run the setup command so the agent documents the workspace layout, nested repo boundaries, and health-check targets before you start planning features. ## Quick Start Ask the agent to run /auto setup to analyze this repository and generate the project context documents.

Frequently Asked Questions about auto-setup

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

FAQPage Schema
How do I generate project context documentation for an AI coding agent?▼

Run /auto setup in an OMP-compatible agent session. The skill dispatches an explorer subagent to analyze the codebase, then writes ARCHITECTURE.md and a set of .autopus/project documents that future sessions load automatically.

What files does auto setup create in a repository?▼

It creates or updates ARCHITECTURE.md at the repo root plus six files under .autopus/project: product.md, structure.md, tech.md, workspace.md, scenarios.md, and canary.md. Each covers a distinct aspect of the project context.

Does auto setup work with monorepos and nested git repositories?▼

Yes. The explorer step identifies the root repository role, nested git repo boundaries, and generated versus source-of-truth paths. For meta workspaces it documents keep and drop targets instead of treating generated runtime artifacts as canonical docs.

When should I rerun auto setup on an existing project?▼

Rerun it when re-entering a stale project, after major structural changes, or before /auto plan and /auto sync when context may be outdated. Existing documents are updated to reflect the current codebase state rather than skipped.

Why does auto setup require a subagent instead of analyzing directly?▼

The OMP execution model mandates that full codebase analysis runs in an explorer subagent first, keeping the main session focused on reviewing results and finalizing documents. If the runtime restricts subagent dispatch, the skill asks the user before proceeding in a single session.

Related Skills

Explore More Software Engineering Skills→
RCSnyderRCSnyder

init

Scaffold the Lights Out SWE harness into a target Git repository.

Community
Basic
shiftreposhiftrepo

subagent-driven-development

Dispatch fresh subagents per task with two-stage reviews.

Official
Advanced
arsen-ask-lxarsen-ask-lx

fsd-architecture

Enforce FSD layer rules and HR isolation via static import analysis.

Community
Advanced
shin0720shin0720

auto-setup

Generate ARCHITECTURE.md and .autopus/project documentation from codebase analysis.

Community
Intermediate