Team UX Improve

Systematic UX improvement pipeline: scan -> diagnose -> design -> implement -> test. 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-ux-improve", args="<project-path> [--framework react|vue]")
                    |
         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       v
           [team-worker agents, each loads roles/<role>/role.md]
          scanner  diagnoser  designer  implementer  tester

Role Registry

Utility Member Registry

Coordinator-only: Utility members can only be spawned by Coordinator. Workers CANNOT call spawn_agent() to spawn utility members.

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

Delegation Lock

Coordinator is a PURE ORCHESTRATOR. It coordinates, it does NOT do.

Before calling ANY tool, apply this check:

If a tool call is BLOCKED: STOP. Create a task, spawn a worker.

No exceptions for "simple" tasks. Even a single-file read-and-report MUST go through spawn_agent.

Shared Constants

• Session prefix: ux-improve
• Session path: .workflow/.team/ux-improve-<timestamp>/
• CLI tools: ccw cli --mode analysis (read-only), ccw cli --mode write (modifications)
• Message bus: mcp__ccw-tools__team_msg(session_id=<session-id>, ...)
• Max test iterations: 5

Worker Spawn Template

Coordinator spawns workers using this template:

spawn_agent({
  agent_type: "team_worker",
  task_name: "<task-id>",
  fork_turns: "none",
  message: `## Role Assignment
role: <role>
role_spec: <skill_root>/roles/<role>/role.md
session: <session-folder>
session_id: <session-id>
requirement: <task-description>
inner_loop: <true|false>

Read role_spec file (<skill_root>/roles/<role>/role.md) to load Phase 2-4 domain instructions.

## Task Context
task_id: <task-id>
title: <task-title>
description: <task-description>
pipeline_phase: <pipeline-phase>

## Upstream Context
<prev_context>`
})

After spawning, use wait_agent({ timeout_ms: 1800000 }) to collect results. If result.timed_out, send STATUS_CHECK via followup_task (wait 3 min), then FINALIZE with interrupt (wait 3 min), then mark timed_out and close agents. Use close_agent({ target }) each worker.

Model Selection Guide

UX improvement has an explorer utility member and a scan-diagnose-design-implement-test pipeline.

User Commands

Specs Reference

• specs/pipelines.md — Pipeline definitions and task registry

Session Directory

.workflow/.team/ux-improve-<timestamp>/
├── .msg/
│   ├── messages.jsonl      # Team message bus
│   └── meta.json           # Pipeline config + role state snapshot
├── artifacts/              # Role deliverables
│   ├── scan-report.md      # Scanner output
│   ├── diagnosis.md        # Diagnoser output
│   ├── design-guide.md     # Designer output
│   ├── fixes/              # Implementer output
│   └── test-report.md      # Tester output
├── explorations/           # Explorer cache
│   └── cache-index.json
└── wisdom/                 # Session knowledge base
    ├── contributions/      # Worker contributions (write-only for workers)
    ├── principles/
    ├── patterns/
    └── anti-patterns/

v4 Agent Coordination

Message Semantics

Agent Health Check

Use list_agents({}) in handleResume and handleComplete:

// Reconcile session state with actual running agents
const running = list_agents({})
// Compare with meta.json active tasks
// Reset orphaned tasks (in_progress but agent gone) to pending

Named Agent Targeting

Workers are spawned with task_name: "<task-id>" enabling direct addressing:

• send_message({ target: "SCAN-001", message: "..." }) -- send explorer findings to scanner
• followup_task({ target: "IMPL-001", message: "..." }) -- assign UX fix from designer output
• close_agent({ target: "TEST-001" }) -- cleanup after UX testing

Explorer-Assisted Scanning

Coordinator spawns explorer (utility member) early to gather codebase context, then sends findings to scanner via upstream context:

// Explorer results inform scanner's scope
send_message({
  target: "SCAN-001",
  message: `## Explorer Findings
component_patterns: <explorer's component inventory>
framework: <detected framework>
ui_library: <detected UI library>`
})

Error Handling