Bootstrap and run a lightweight multi-agent development team to plan, implement, and test software projects.
- GitHub stars
- 41,038
- Files
- 5
- Last commit
- Nov 11, 2026
- License
- MIT
- Allowed tools
- —
What does the ai-team-orchestration skill do?
ai-team-orchestration is an agent skill. Bootstrap and run a lightweight multi-agent development team to plan, implement, and test software projects.
Summary generated from the skill's SKILL.md.
About the ai-team-orchestration skill
Bootstrapping a lightweight multi-agent development team to plan, implement, and test software projects is the primary function of this skill. It provides three specialized agents: a producer to clarify scope and coordinate, a developer to implement and prepare pull requests, and a QA agent for independent behavioral verification. Developers use this when starting new projects, adopting existing codebases, or coordinating complex multi-step work that requires distinct perspectives.
The workflow follows a sequence of planning, implementation, testing, and merging. It relies on repository documentation and can generate files like PROJECT_BRIEF.md or sprint plans to maintain context across different sessions. Unlike rigid frameworks, this system inherits your existing MCP tools and model selections, allowing you to maintain control over your specific environment and permissions. It prioritizes working software and repository-specific Git policies over heavy process artifacts.
What an agent can do with it
- 1Onboard to a new codebaseAnalyze an existing repository to discover its architecture, stack, and deployment model.
- 2Execute complex software changesCoordinate a multi-step implementation by creating a concise plan and managing the development lifecycle.
- 3Conduct architectural brainstormingEvaluate product or architecture decisions using competing perspectives from different agents.
- 4Recover session contextResume work after an interruption by reading the project brief and active progress notes.
Written from the skill's SKILL.md. Every use case is checked against a quote from it.
How to install the ai-team-orchestration skill
Each command copies the skill folder into the client's skills directory. Restart the client or start a new session to load it.Install the ai-team-orchestration skill in Claude Code
~/.claude/skills/ai-team-orchestration/SKILL.md
$ npx degit github/awesome-copilot/skills/ai-team-orchestration ~/.claude/skills/ai-team-orchestrationInstall the ai-team-orchestration skill in Claude Code (project)
.claude/skills/ai-team-orchestration/SKILL.md
$ npx degit github/awesome-copilot/skills/ai-team-orchestration .claude/skills/ai-team-orchestrationInstall the ai-team-orchestration skill in Codex
~/.agents/skills/ai-team-orchestration/SKILL.md
$ npx degit github/awesome-copilot/skills/ai-team-orchestration ~/.agents/skills/ai-team-orchestrationInstall the ai-team-orchestration skill in Gemini CLI
~/.gemini/skills/ai-team-orchestration/SKILL.md
$ npx degit github/awesome-copilot/skills/ai-team-orchestration ~/.gemini/skills/ai-team-orchestrationInstall the ai-team-orchestration skill in Claude.ai
npx degit github/awesome-copilot/skills/ai-team-orchestration ai-team-orchestration && zip -r ai-team-orchestration.zip ai-team-orchestration # claude.ai → Customize → Skills → + → Create skill → Upload a skill → ai-team-orchestration.zip
Automated checks
Ran Nov 15, 2026Full report →Passed our automated checks. That is not a security audit: read the scripts before you let an agent run them. How checks work
- Source repository linked and reachablegithub/awesome-copilot/skills/ai-team-orchestration is public and reachablegithub.com/github/awesome-copilot/tree/HEAD/skills/ai-team-o ↗Pass
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit 2026-11-11github.com/github/awesome-copilot/commits ↗Pass
- No download-and-run or credential theft in scriptsNo scripts in the skill folderPass
- No hidden instructions in SKILL.mdNo override phrases, safeguard switches, credential requests or hidden charactersgithub.com/github/awesome-copilot/blob/HEAD/skills/ai-team-o ↗Pass
- Pre-approved tools are scopedNo pre-approved tools; the agent asks before using onegithub.com/github/awesome-copilot/blob/HEAD/skills/ai-team-o ↗Pass
- SKILL.md follows the Agent Skills formatValid name and description; says when to use it; 93 linesgithub.com/github/awesome-copilot/blob/HEAD/skills/ai-team-o ↗Pass
SKILL.md
View on GitHubAI Team Orchestration
Use three stable agents:
| Agent | Purpose |
|---|---|
@ai-team-producer |
Clarify scope, plan proportionately, coordinate, and merge |
@ai-team-dev |
Implement, test, self-review, and prepare the pull request |
@ai-team-qa |
Independently test behavior when dedicated QA is useful |
Nova, Sage, and Milo are perspectives inside the Dev agent, not mandatory project layers.
Default Workflow
Plan -> Implement -> Test -> optional review or QA -> Merge -> update project state
Keep the workflow proportional:
- Skip formal planning for small, obvious changes.
- Use a short plan for multi-step or cross-cutting work.
- Add independent review or QA when risk, uncertainty, or repository policy justifies it.
- Let branch protection, required checks, permissions, and merge queues enforce repository merge policy.
Start or Adopt a Project
- Read existing repository instructions and documentation.
- Discover the actual stack, architecture, commands, deployment model, and risks.
- Create or update
PROJECT_BRIEF.mdonly when durable cross-session context is useful. Start from the project brief template and omit irrelevant sections. - For substantial work, create a concise plan from the sprint plan template.
- Use a separate branch or clone when parallel sessions could conflict, following the repository's own Git policy.
Execute
Producer
- Define the outcome, constraints, acceptance criteria, and explicit exclusions.
- Choose review and QA based on risk rather than ceremony.
- Keep durable project state concise and current.
Dev
- Follow repository conventions and implement the smallest complete solution.
- Run relevant checks and inspect the final diff.
- Open or update the pull request with summary, verification, and limitations.
QA
- Use only when dedicated behavioral verification adds value.
- Test the requested change and important regressions.
- Report reproducible findings and verify fixes.
Brainstorms
Use the brainstorm format for product or architecture decisions that benefit from competing perspectives. For ordinary implementation choices, let Dev decide using repository conventions.
Context Recovery
Before ending a long or interrupted session:
- Update the active plan or progress note if one exists.
- Record material decisions, blockers, and the next action in repository context.
- Use a cold-start prompt such as:
Read the repository instructions, then read whichever sources exist for this
work: the active issue or request, PROJECT_BRIEF.md, and the active plan or
progress note.
Continue from the recorded next action.
Tool and Model Inheritance
The bundled agents intentionally omit tools and model frontmatter:
- available built-in, MCP, and extension tools remain usable;
- developers keep control of model selection;
- role boundaries are defined by instructions and normal trust, permission, authentication, and approval controls.
If the environment exposes too many tools, deselect irrelevant tools or MCP servers, or use VS Code virtual-tool management. Do not add a machine-specific plugin allowlist.
Principles
- Prefer working software and clear handoffs over process artifacts.
- Follow repository policy instead of embedding universal Git commands.
- Preserve unknown work and ask before destructive or privileged actions.
- Keep bugs and important decisions in durable project systems, not only chat.
- See anti-patterns for concise lessons.
Files in this skill
5ai-team-orchestration skill questions
How do I install the ai-team-orchestration skill in Claude Code?
Run npx degit github/awesome-copilot/skills/ai-team-orchestration ~/.claude/skills/ai-team-orchestration. Claude Code loads skills from ~/.claude/skills (all projects) or .claude/skills (one project) and uses a skill when its description matches the task.
Which clients can use the ai-team-orchestration skill?
Any client that reads the Agent Skills format: Claude Code, Codex, Gemini CLI and claude.ai (upload as a ZIP). Scripts in the skill run only where the client allows code execution.
How should I handle context recovery after an interrupted session?
Update the active plan or progress note, record decisions and blockers in the repository context, and use a cold-start prompt to read existing instructions and project briefs.
Do I need to specify tools and models for the agents?
No, the agents are designed to inherit available built-in, MCP, and extension tools while allowing developers to maintain control over model selection.