dev-team

Automate build, test, review, and fix loops for plan items.

Updated Jul 2, 2026
One-click install
npx skills add https://github.com/nseluga/os --skill dev-team-nseluga
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: dev-team
Source: https://github.com/nseluga/os/tree/main/skills/dev-team
Command: npx skills add https://github.com/nseluga/os --skill dev-team-nseluga

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires python, claude-code, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill coordinates the development team's workflow, driving a convergence loop to ensure that plan items are built, tested, reviewed, and fixed efficiently until they meet specified criteria.

Core Features & Use Cases

  • Convergence Loop: Automates the process of building, testing, reviewing, and fixing plan items through a structured loop.
  • Role-Based Execution: Spawns agents like Engineer, QA, Reviewer, and Fixer, each with specific tasks and responsibilities.
  • Design Exploration: Offers design exploration for complex/critical items before implementation.
  • Efficiency and Scalability: Implements best practices for efficiency, reliability, scalability, and safety.
  • Logging and Reporting: Provides detailed logs and reports for every step of the process.

Quick Start

Run the dev-team skill with the task description: dev-team --task "Build the new feature"

Frequently Asked Questions about dev-team

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

FAQPage Schema
How do I automate code review and testing in my development workflow?

You can automate code review and testing by running a convergence loop with role-based agents for building, testing, reviewing, and fixing plan items. This ensures development processes meet specified quality criteria efficiently.

What is a convergence loop in software development?

A convergence loop is an automated development workflow process that repeatedly builds, tests, reviews, and fixes plan items until they meet specified criteria. It uses role-based execution to ensure quality and efficiency.

Do I need Python and Claude Code to orchestrate role-based development agents?

Yes, you need Python and Claude Code to orchestrate the structured development workflow. These dependencies are required to spawn agents like Engineer, QA, Reviewer, and Fixer and run the convergence loop.

Can I explore design options for critical plan items before implementation?

Yes, you can explore design options for complex or critical plan items before implementation. The workflow supports design exploration to ensure best practices for efficiency, reliability, scalability, and safety.

How do I track quality assurance steps during automated development workflows?

You can track quality assurance steps through detailed logs and reports generated for every step of the process. The workflow provides logging and reporting to monitor the building, testing, and fixing phases.

What's the best way to spawn specialized agents for fixing code issues?

The best way to spawn specialized agents for fixing code is using role-based execution within a convergence loop. It assigns specific tasks to Engineer, QA, Reviewer, and Fixer agents to resolve items until criteria are met.