$npx -y skills add github/awesome-copilot --skill ai-team-orchestrationBootstrap and run a multi-agent AI development team. Use when: starting a new software project with AI agents, setting up parallel dev/QA teams, creating sprint plans, writing brainstorm prompts with distinct agent voices, recovering a project workflow, or planning sprints.
| 1 | # AI Team Orchestration |
| 2 | |
| 3 | ## When to Use |
| 4 | - Starting a new project that needs planning, development, testing, and deployment |
| 5 | - Setting up parallel AI agent teams (dev, QA, DevOps) |
| 6 | - Writing brainstorm prompts that produce real debate (not generic output) |
| 7 | - Creating sprint plans with cross-chat context survival |
| 8 | - Recovering from context overflow mid-sprint |
| 9 | |
| 10 | ## Team Roles |
| 11 | |
| 12 | | Agent | Name | Role | Focus | |
| 13 | |-------|------|------|-------| |
| 14 | | Producer | **Remy** | Sprint planning, coordination, merging PRs | Scope control, handoffs, issue triage | |
| 15 | | Product Designer | **Kira** | UX, mechanics, user experience | Fun factor, user flows, feature design | |
| 16 | | Visual/Art Director | **Milo** | CSS, animations, visual identity | Design system, polish, accessibility | |
| 17 | | Frontend Engineer | **Nova** | UI framework, state management, components | React/Vue/Svelte, client-side logic | |
| 18 | | Backend Engineer | **Sage** | API, database, auth, security | Server-side logic, infrastructure | |
| 19 | | DevOps Engineer | **Dash** | CI/CD, cloud deployment, pipelines | GitHub Actions, Azure/AWS/GCP | |
| 20 | | QA Engineer | **Ivy** | E2E tests, automation, playtesting | Playwright/Cypress, bug filing, sign-off | |
| 21 | |
| 22 | Customize names and roles for your project. Not every project needs all roles. |
| 23 | |
| 24 | ## Chat Architecture |
| 25 | |
| 26 | The human (CEO) is the message bus between parallel chats: |
| 27 | |
| 28 | ``` |
| 29 | ┌────────────────────────────────────────┐ |
| 30 | │ @ai-team-producer — Plans, merges │ |
| 31 | │ NEVER writes code │ |
| 32 | └────────────────┬───────────────────────┘ |
| 33 | │ Human carries messages |
| 34 | ┌──────────┼──────────┐ |
| 35 | ▼ ▼ ▼ |
| 36 | ┌──────────┐ ┌────────┐ ┌────────┐ |
| 37 | │@ai-team │ │@ai-team│ │DevOps │ |
| 38 | │-dev │ │-qa │ │(on │ |
| 39 | │ │ │ │ │demand) │ |
| 40 | │ Nova │ │ Ivy │ │ │ |
| 41 | │ Sage │ │ │ │ │ |
| 42 | │ Milo │ │ │ │ │ |
| 43 | │ │ │feature/│ │feature/│ |
| 44 | │ feature/ │ │qa-N │ │devops-N│ |
| 45 | │ sprint-N │ └────────┘ └────────┘ |
| 46 | └──────────┘ |
| 47 | ``` |
| 48 | |
| 49 | Each team works in a **separate VS Code window** with its own clone: |
| 50 | ```bash |
| 51 | git clone <repo> project-dev # Dev team |
| 52 | git clone <repo> project-qa # QA |
| 53 | git clone <repo> project-devops # DevOps (only when needed) |
| 54 | ``` |
| 55 | |
| 56 | ## Project Bootstrap |
| 57 | |
| 58 | ### 1. Create PROJECT_BRIEF.md |
| 59 | |
| 60 | The single source of truth across all chats. See the [project brief template](./references/project-brief-template.md). |
| 61 | |
| 62 | **Required sections (do not abbreviate):** |
| 63 | 1. Project Overview |
| 64 | 2. Concept / Product Description |
| 65 | 3. Tech Stack |
| 66 | 4. Architecture (ASCII diagram) |
| 67 | 5. Key Files Map |
| 68 | 6. Team Roles |
| 69 | 7. Sprint Status (updated every sprint) |
| 70 | 8. Current State (rewritten every sprint) |
| 71 | 9. Security Rules |
| 72 | 10. How to Run Locally |
| 73 | 11. How to Deploy |
| 74 | 12. **Cross-Chat Handoff Protocol** — how context survives between chats |
| 75 | 13. **Bug & Fix Tracking** — GitHub Issues as single source of truth |
| 76 | 14. **Multi-Repo Setup** — separate clones, branch strategy, merge rules |
| 77 | |
| 78 | ### 2. Run a Brainstorm |
| 79 | |
| 80 | See the [brainstorm format](./references/brainstorm-format.md). Key: name each agent explicitly with distinct personality and perspective. Require at least 2 genuine disagreements to prevent groupthink. |
| 81 | |
| 82 | ### 3. Create Sprint Plans |
| 83 | |
| 84 | See the [sprint plan template](./references/sprint-plan-template.md). Every sprint gets: |
| 85 | - `docs/sprint-N/plan.md` — prioritized tasks, success criteria |
| 86 | - `docs/sprint-N/progress.md` — live tracker, enables recovery |
| 87 | - `docs/sprint-N/done.md` — handoff doc written at sprint end |
| 88 | |
| 89 | ### 4. Execute Sprints |
| 90 | |
| 91 | ``` |
| 92 | Read PROJECT_BRIEF.md, then read docs/sprint-N/plan.md. Execute Sprint N. |
| 93 | |
| 94 | First: git pull origin main && git checkout -b feature/sprint-N |
| 95 | |
| 96 | Close GitHub Issues in commits: "fix: description (Fixes #NN)" |
| 97 | Update docs/sprint-N/progress.md after each phase. |
| 98 | When done, push and create PR: git push origin feature/sprint-N |
| 99 | Follow Sections 12-14 of PROJECT_BRIEF.md. |
| 100 | ``` |
| 101 | |
| 102 | ### 5. QA Sign-off |
| 103 | |
| 104 | After dev merges, QA does a full playthrough: |
| 105 | ``` |
| 106 | Read PROJECT_BRIEF.md. You are Ivy (QA). |
| 107 | Sprint N is merged to main. Do full playthrough. |
| 108 | File bugs as GitHub Issues. Write docs/qa/sprint-N-signoff.md. |
| 109 | ``` |
| 110 | |
| 111 | ## Context Recovery |
| 112 | |
| 113 | When a chat gets long (>100 messages), save state and start fresh: |
| 114 | |
| 115 | **Before closing:** |
| 116 | 1. Update `docs/sprint-N/progress.md` with current status |
| 117 | 2. Update `PROJECT_BRIEF.md` sections 7+8 |
| 118 | 3. Write `docs/sprint-N/done.md` |
| 119 | |
| 120 | **Cold start prompt:** |
| 121 | ``` |
| 122 | Read PROJECT_BRIEF.md and docs/sprint-N/progress.md. |
| 123 | Continue from where it left off. |
| 124 | ``` |
| 125 | |
| 126 | ## Anti-Patterns |
| 127 | |
| 128 | See [anti-patterns reference](./references/anti-patterns.md) for the full list. Top 5: |
| 129 | |
| 130 | | Don't | Do Instead | |
| 131 | |-------|------------| |
| 132 | | Rebase feature branches | Merge (rebase loses commits) | |
| 133 | | Producer writes code | P |