| name | team-uidesign |
| description | Unified team skill for UI design team. Research -> design tokens -> audit -> implementation. Uses team-worker agent architecture with roles/ for domain logic. Coordinator orchestrates dual-track pipeline with GC loops and sync points. Triggers on "team ui design", "ui design team". |
| allowed-tools | ["AskUserQuestion","Bash","Edit","Glob","Grep","Read","SendMessage","Write","mcp__maestro__edit_file","mcp__maestro__read_file","mcp__maestro__team_msg","mcp__maestro__write_file","teammate","todo"] |
| session-mode | run |
<required_reading>
@~/.maestro/workflows/run-mode-lite.md
</required_reading>
Team UI Design
Systematic UI design pipeline: research -> design tokens -> review -> implementation. Built on team-worker agent architecture — all worker roles share a single agent definition with role-specific Phase 2-4 loaded from roles/<role>/role.md.
Architecture
Skill(skill="team-uidesign", args="task description")
|
SKILL.md (this file) = Router
|
+--------------+--------------+
| |
no --role flag --role <name>
| |
Coordinator Worker
roles/coordinator/role.md roles/<name>/role.md
|
+-- analyze → dispatch → spawn workers → STOP
|
+-------+-------+-------+-------+
v v v v
[team-worker agents, each loads roles/<role>/role.md]
researcher designer reviewer implementer
Role Registry
Pre-load (coordinator, before dispatch)
- Codebase docs: If
.workflow/codebase/ARCHITECTURE.md exists, read for module boundaries
- Specs (ui):
maestro load --type spec --category ui — load ui constraints as shared context
- Wiki knowledge:
maestro search "UI design tokens audit" --json — top 5 entries as prior context
- All optional — proceed without if unavailable
Role Router
Parse $ARGUMENTS:
- Has
--role <name> → Read roles/<name>/role.md, execute Phase 2-4
- No
--role → @roles/coordinator/role.md, execute entry router
Shared Constants
- Session prefix:
UDS
- Session path:
{run_dir}/work/team/
- CLI tools:
maestro delegate --mode analysis (read-only), maestro delegate --mode write (modifications)
- Message bus:
mcp__maestro__team_msg(session_id=<run-id>, ...)
- Max GC rounds: 2
Worker Spawn Template
Coordinator spawns workers using this template:
teammate({ agent: "team-worker", name: "<role>", description: "Spawn <role> worker for <task-id>", context: "fresh" })
User Commands
| Command | Action |
|---|
check / status | View execution status graph |
resume / continue | Advance to next step |
Specs Reference
Session Directory
{run_dir}/work/team/
├── .msg/
│ ├── messages.jsonl # Team message bus
│ └── meta.json # Pipeline config + GC state
├── {run_dir}/outputs/research/ # Researcher output
│ ├── design-system-analysis.json
│ ├── component-inventory.json
│ ├── accessibility-audit.json
│ ├── design-intelligence.json
│ └── visual-quality-baseline.json
├── {run_dir}/outputs/design/ # Designer output
│ ├── design-tokens.json
│ ├── component-specs/
│ └── layout-specs/
├── {run_dir}/outputs/audit/ # Reviewer output
│ └── audit-*.md
├── {run_dir}/outputs/build/ # Implementer output
│ ├── token-files/
│ └── component-files/
└── wisdom/ # Cross-task knowledge
Error Handling
| Scenario | Resolution |
|---|
| Unknown command | Error with available command list |
| Role not found | Error with role registry |
| Session corruption | Attempt recovery, fallback to manual |
| Fast-advance conflict | Coordinator reconciles on next callback |
| Completion action fails | Default to Keep Active |
| GC loop stuck > 2 rounds | Escalate to user: accept / retry / terminate |