ai-team-orchestration for GitHub Copilot

Q: How do I install ai-team-orchestration in GitHub Copilot?

Run `copilot plugin install ai-team-orchestration@awesome-copilot`.

What ai-team-orchestration does

ai-team-orchestration runs a role-separated group of agents. Producer scopes the work, plans it, coordinates tasks, handles triage, and prepares the merge. Dev Team adapts the implementation to the project stack, runs tests, reviews its own diff, and prepares a pull request. QA can be added for independent behavioral testing and fix verification.

The /ai-team-orchestration skill includes a concise project brief template, a proportional work-plan template, brainstorming guidance with distinct perspectives, and practical anti-patterns for multi-agent work. The agents inherit the developer's enabled built-in, MCP, and extension tools, along with the developer-selected model. Their frontmatter intentionally omits tools and model.

Install it when you want clear boundaries between planning, coding, and QA. Small changes can skip the full process because the workflow is meant to match the size and risk of the work.

What it helps with

separate planning from application coding
prepare a pull request without merging it
test a pull request against acceptance criteria
scale the process to the size of a change

Example prompts for the agent

@ai-team-producer Help me define the next useful outcome for this project. Use /ai-team-orchestration and keep planning proportional to the work.
@ai-team-dev Read the repository instructions and active plan or issue. Implement the requested outcome, run relevant checks, self-review the diff, and prepare the pull request. Do not merge.
@ai-team-qa Test the pull request against its acceptance criteria. Focus on important behavior and regressions.

How to install ai-team-orchestration

Command from the source

copilot plugin install ai-team-orchestration@awesome-copilot

From the same set554

The whole set →

git-commit official github This skill reviews Git changes, stages related files, and creates Conventional Commits. Use it when you want an agent to make one commit or split work into separate commits. GitHub Copilot 47,165installs excalidraw-diagram-generator official github Turn a plain-language description into an Excalidraw diagram. Useful for mapping processes, system structure, and relationships between entities. GitHub Copilot 31,639installs multi-stage-dockerfile official github This skill guides GitHub Copilot in writing multi-stage Dockerfiles for different languages and frameworks. Use it when the final runtime image should contain fewer build dependencies. GitHub Copilot 29,688installs documentation-writer official github Skill that turns the agent into a technical writer following the Diátaxis framework: tutorials, how-to guides, reference, and explanation. Proposes structure before writing. GitHub Copilot 27,757installs prd official github Turns a feature idea into a structured PRD with user stories, technical requirements, and risks. Use it when planning a software feature or an AI-powered one. GitHub Copilot 24,035installs refactor official github This skill reshapes existing code without changing its external behavior. Use it for gradual cleanup of large functions, duplication, weak types, and code smells. GitHub Copilot 22,321installs java-springboot official github Gives GitHub Copilot Spring Boot development practices, from project layout to tests and security. Use it when writing or reviewing Java application code. GitHub Copilot 21,272installs create-readme official github This skill reviews a project and creates a structured README.md. Use it when the repository needs clear documentation based on its actual files and code. GitHub Copilot 19,081installs

Questions about ai-team-orchestration

How do I install ai-team-orchestration in GitHub Copilot?

Run copilot plugin install ai-team-orchestration@awesome-copilot.

What does ai-team-orchestration do?

It assigns work to Producer, Dev Team, and optional QA agents. The default flow covers planning, implementation, testing, review or QA, merge, and project-state updates.

Which tools and model do the agents use?

They inherit the developer's enabled built-in, MCP, and extension tools and use the developer-selected model. Normal permission and approval controls still apply.

Source text

ai-team-orchestration · MIT

# AI Team Orchestration

Run a lightweight, role-separated AI development team with flexible tools, developer-selected models, proportionate planning, and optional QA.

## What's Included

### Agents

| Agent | Mention | Role |
|---|---|---|
| **Producer** (Remy) | `@ai-team-producer` | Scope, planning, coordination, triage, and merge |
| **Dev Team** (Nova, Sage, Milo) | `@ai-team-dev` | Stack-adaptive implementation, tests, self-review, and pull requests |
| **QA** (Ivy) | `@ai-team-qa` | Optional independent behavioral testing and fix verification |

The agents intentionally omit `tools` and `model` frontmatter. They inherit the developer's enabled built-in, MCP, and extension tools and use the developer-selected model. Role boundaries remain in the instructions and normal permission and approval controls.

### Skill

`/ai-team-orchestration` provides:

- a concise project brief template;
- a proportional work-plan template;
- brainstorm guidance with distinct perspectives;
- practical anti-patterns for multi-agent work.

## Default Workflow

```text
Plan -> Implement -> Test -> optional review or QA -> Merge -> update project state
```

Use the lightest process that fits the work. Small changes can proceed directly; substantial or risky changes benefit from a short plan, independent review, or dedicated QA.

## Quick Start

### Plan

```text
@ai-team-producer Help me define the next useful outcome for this project.
Use /ai-team-orchestration and keep planning proportional to the work.
```

### Implement

```text
@ai-team-dev Read the repository instructions and active plan or issue.
Implement the requested outcome, run relevant checks, self-review the diff,
and prepare the pull request. Do not merge.
```

### Optional QA

```text
@ai-team-qa Test the pull request against its acceptance criteria.
Focus on important behavior and regressions. Report Ready, Ready with minor
follow-ups, or Blocked with reproducible findings.
```

## Principles

- Producer coordinates but never implements application code.
- Dev implements and verifies but never merges or claims independent approval.
- QA is optional and independently verifies behavior without fixing application source.
- Repository contribution policy and platform protections define Git and merge behavior.
- Important context and bugs live in durable project files or issue trackers, not only chat.

## Origin

The plugin grew from [Arcade After Dark](https://github.com/denis-a-evdokimov/guess-and-get), a multi-agent project built with distinct planning, implementation, design, and QA perspectives.

ai-team-orchestration — GitHub Copilot plugin