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
| Role |
Path |
Prefix |
Inner Loop |
| coordinator |
roles/coordinator/role.md |
— |
— |
| scanner |
roles/scanner/role.md |
SCAN-* |
false |
| diagnoser |
roles/diagnoser/role.md |
DIAG-* |
false |
| designer |
roles/designer/role.md |
DESIGN-* |
false |
| implementer |
roles/implementer/role.md |
IMPL-* |
true |
| tester |
roles/tester/role.md |
TEST-* |
false |
Utility Member Registry
Coordinator-only: Utility members can only be spawned by Coordinator. Workers CANNOT call Agent() to spawn utility members.
| Utility Member |
Path |
Callable By |
Purpose |
| explorer |
roles/explorer/role.md |
Coordinator only |
Explore codebase for UI component patterns and framework-specific patterns |
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:
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:
Agent({
subagent_type: "team-worker",
description: "Spawn <role> worker for <task-id>",
team_name: "ux-improve",
name: "<role>",
run_in_background: true,
prompt: `## Role Assignment
role: <role>
role_spec: <skill_root>/roles/<role>/role.md
session: <session-folder>
session_id: <session-id>
team_name: ux-improve
requirement: <task-description>
inner_loop: <true|false>
## Progress Milestones
session_id: <session-id>
Report progress via team_msg at natural phase boundaries (context loaded -> core work done -> verification).
Report blockers immediately via team_msg type="blocker".
Report completion via team_msg type="task_complete" after final SendMessage.
Read role_spec file (@<skill_root>/roles/<role>/role.md) to load Phase 2-4 domain instructions.
Execute built-in Phase 1 (task discovery) -> role Phase 2-4 -> built-in Phase 5 (report).`
})
User Commands
| Command |
Action |
check / status |
View execution status graph |
resume / continue |
Advance to next step |
Specs Reference
- specs/pipelines.md — Pipeline definitions and task registry
- specs/design-standards.md — Impeccable visual design standards
- specs/anti-patterns.md — AI slop detection catalog (20 items)
- specs/heuristics.md — Nielsen's 10 usability heuristics evaluation framework
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/
Error Handling
| Scenario |
Resolution |
| Unknown command |
Error with available command list |
| Role not found |
Error with role registry |
| Project path invalid |
Re-prompt user for valid path |
| Framework detection fails |
AskUserQuestion for framework selection |
| Session corruption |
Attempt recovery, fallback to manual |
| Fast-advance conflict |
Coordinator reconciles on next callback |
| No UI issues found |
Complete with empty fix list, generate clean bill report |
| Test iterations exceeded |
Accept current state, continue to completion |
1---2name: team-ux-improve-23description: Unified team skill for UX improvement. Systematically discovers and fixes UI/UX interaction issues including unresponsive buttons, missing feedback, and state refresh problems. Uses team-worker agent architecture with roles/ for domain logic. Coordinator orchestrates pipeline, workers are team-worker agents. Triggers on "team ux improve".4allowed-tools: Agent, AskUserQuestion, Read, Write, Edit, Bash, Glob, Grep, TaskList, TaskGet, TaskUpdate, TaskCreate, TeamCreate, TeamDelete, SendMessage, mcp__ace-tool__search_context, mcp__ccw-tools__read_file, mcp__ccw-tools__write_file, mcp__ccw-tools__edit_file, mcp__ccw-tools__team_msg5metadata:6 source: https://skillmd.com/skills/catlog22/team-ux-improve-27---89# Team UX Improve1011Systematic 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`.1213## Architecture1415```16Skill(skill="team-ux-improve", args="<project-path> [--framework react|vue]")17 |18 SKILL.md (this file) = Router19 |20 +--------------+--------------+21 | |22 no --role flag --role <name>23 | |24 Coordinator Worker25 roles/coordinator/role.md roles/<name>/role.md26 |27 +-- analyze → dispatch → spawn workers → STOP28 |29 +-------+-------+-------+-------+30 v v v v v31 [team-worker agents, each loads roles/<role>/role.md]32 scanner diagnoser designer implementer tester33```3435## Role Registry3637| Role | Path | Prefix | Inner Loop |38|------|------|--------|------------|39| coordinator | [roles/coordinator/role.md](roles/coordinator/role.md) | — | — |40| scanner | [roles/scanner/role.md](roles/scanner/role.md) | SCAN-* | false |41| diagnoser | [roles/diagnoser/role.md](roles/diagnoser/role.md) | DIAG-* | false |42| designer | [roles/designer/role.md](roles/designer/role.md) | DESIGN-* | false |43| implementer | [roles/implementer/role.md](roles/implementer/role.md) | IMPL-* | true |44| tester | [roles/tester/role.md](roles/tester/role.md) | TEST-* | false |4546## Utility Member Registry4748**Coordinator-only**: Utility members can only be spawned by Coordinator. Workers CANNOT call Agent() to spawn utility members.4950| Utility Member | Path | Callable By | Purpose |51|----------------|------|-------------|---------|52| explorer | [roles/explorer/role.md](roles/explorer/role.md) | Coordinator only | Explore codebase for UI component patterns and framework-specific patterns |5354## Role Router5556Parse `$ARGUMENTS`:57- Has `--role <name>` → Read `roles/<name>/role.md`, execute Phase 2-458- No `--role` → `@roles/coordinator/role.md`, execute entry router5960## Shared Constants6162- **Session prefix**: `ux-improve`63- **Session path**: `.workflow/.team/ux-improve-<timestamp>/`64- **CLI tools**: `ccw cli --mode analysis` (read-only), `ccw cli --mode write` (modifications)65- **Message bus**: `mcp__ccw-tools__team_msg(session_id=<session-id>, ...)`66- **Max test iterations**: 56768## Worker Spawn Template6970Coordinator spawns workers using this template:7172```73Agent({74 subagent_type: "team-worker",75 description: "Spawn <role> worker for <task-id>",76 team_name: "ux-improve",77 name: "<role>",78 run_in_background: true,79 prompt: `## Role Assignment80role: <role>81role_spec: <skill_root>/roles/<role>/role.md82session: <session-folder>83session_id: <session-id>84team_name: ux-improve85requirement: <task-description>86inner_loop: <true|false>8788## Progress Milestones89session_id: <session-id>90Report progress via team_msg at natural phase boundaries (context loaded -> core work done -> verification).91Report blockers immediately via team_msg type="blocker".92Report completion via team_msg type="task_complete" after final SendMessage.9394Read role_spec file (@<skill_root>/roles/<role>/role.md) to load Phase 2-4 domain instructions.95Execute built-in Phase 1 (task discovery) -> role Phase 2-4 -> built-in Phase 5 (report).`96})97```9899## User Commands100101| Command | Action |102|---------|--------|103| `check` / `status` | View execution status graph |104| `resume` / `continue` | Advance to next step |105106## Specs Reference107108- [specs/pipelines.md](specs/pipelines.md) — Pipeline definitions and task registry109- [specs/design-standards.md](specs/design-standards.md) — Impeccable visual design standards110- [specs/anti-patterns.md](specs/anti-patterns.md) — AI slop detection catalog (20 items)111- [specs/heuristics.md](specs/heuristics.md) — Nielsen's 10 usability heuristics evaluation framework112113## Session Directory114115```116.workflow/.team/ux-improve-<timestamp>/117├── .msg/118│ ├── messages.jsonl # Team message bus119│ └── meta.json # Pipeline config + role state snapshot120├── artifacts/ # Role deliverables121│ ├── scan-report.md # Scanner output122│ ├── diagnosis.md # Diagnoser output123│ ├── design-guide.md # Designer output124│ ├── fixes/ # Implementer output125│ └── test-report.md # Tester output126├── explorations/ # Explorer cache127│ └── cache-index.json128└── wisdom/ # Session knowledge base129 ├── contributions/ # Worker contributions (write-only for workers)130 ├── principles/131 ├── patterns/132 └── anti-patterns/133```134135## Error Handling136137| Scenario | Resolution |138|----------|------------|139| Unknown command | Error with available command list |140| Role not found | Error with role registry |141| Project path invalid | Re-prompt user for valid path |142| Framework detection fails | AskUserQuestion for framework selection |143| Session corruption | Attempt recovery, fallback to manual |144| Fast-advance conflict | Coordinator reconciles on next callback |145| No UI issues found | Complete with empty fix list, generate clean bill report |146| Test iterations exceeded | Accept current state, continue to completion |