Index of every page on this site: llms.txt
All skills
github avatar

/ai-team-orchestration

@f10fdb8 official
by githubgithub/awesome-copilot41k stars
5,399
Run it yourself

Bootstrap and run a lightweight multi-agent development team. Use when starting or adopting a project, planning work, coordinating implementation and optional QA, brainstorming with distinct perspectives, or preserving context across sessions.

Use this Skill: https://skilld.dev/gh/github/awesome-copilot/ai-team-orchestration

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈67 tokens for metadata: the name and description. ≈917 when used: this file. ≈2.7k more on demand in 4 files.

Description uses 3.3% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈267 characters, or 3.3%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

AI 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

  1. Read existing repository instructions and documentation.
  2. Discover the actual stack, architecture, commands, deployment model, and risks.
  3. Create or update PROJECT_BRIEF.md only when durable cross-session context is useful. Start from the project brief template and omit irrelevant sections.
  4. For substantial work, create a concise plan from the sprint plan template.
  5. 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:

  1. Update the active plan or progress note if one exists.
  2. Record material decisions, blockers, and the next action in repository context.
  3. 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.

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

1 warning15d3 checks · Risk SAFE
  • Gen Agent Trust Hub15d

    This skill provides a structured framework and set of templates for a multi-agent development workflow. It focuses on role-based orchestration (Producer, Developer, QA) and includes templates for project planning and brainstorming. The analysis found no malicious behavior or security risks, and the skill follows good security practices such as advising the use of environment-controlled secrets and repository-specific policies.

  • Socket26d

    No alerts

  • Snyk26d

    Risk: MEDIUM · 1 issue

Signed by skilld at f10fdb8. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 4 months ago
  • Testing
  • multi-agent
  • orchestration
  • sprint-planning
  • team-coordination
  • github
  • project-management
  • ai-workflow

README badge

README badge for github/awesome-copilot/ai-team-orchestration

Orchestrates parallel AI agent teams (dev, QA, DevOps, design) across separate VS Code clones to execute multi-sprint software projects from brainstorm through deployment. Uses a human coordinator role, shared PROJECT_BRIEF.md for context continuity, and GitHub Issues for cross-chat handoffs to prevent context collapse.

Generated from the current SKILL.md.

Does this skill work with Claude or other AI models?
The skill is model-agnostic and designed for any AI coding agent. It uses role-based prompts and chat architecture that work across Claude, other LLMs, or mixed-model teams.
Can I use fewer than seven agent roles?
Yes. The skill explicitly states 'Not every project needs all roles.' Customize names and roles based on your project's actual needs.
How does context survive between separate AI chats?
Through three documents kept in version control: PROJECT_BRIEF.md (single source of truth), docs/sprint-N/progress.md (live tracker), and docs/sprint-N/done.md (handoff doc). Each chat reads these before continuing.
Do I need separate git clones for each team?
Yes. The skill prescribes separate VS Code windows with separate clones (project-dev, project-qa, project-devops) so teams work in parallel without merge conflicts during execution.
What happens when a chat exceeds context limits?
Save progress to docs/sprint-N/progress.md and PROJECT_BRIEF.md, then start a fresh chat. The cold-start prompt reads these files to resume work without losing state.

Generated from the current SKILL.md. These answers refresh after source changes.