team-ux-improve

GitHub

系统化发现并修复UI/UX交互问题(如按钮无响应、状态刷新失败)的技能。基于team-worker架构,协调扫描、诊断、设计、实现和测试流程,自动优化前端用户体验。

.claude/skills/team-ux-improve/SKILL.md catlog22/Claude-Code-Workflow

Trigger Scenarios

发现界面交互缺陷或体验不佳 需要系统性审查和优化现有UI组件 用户反馈存在状态不同步或缺失反馈

Install

npx skills add catlog22/Claude-Code-Workflow --skill team-ux-improve -g -y
More Options

Non-standard path

npx skills add https://github.com/catlog22/Claude-Code-Workflow/tree/main/.claude/skills/team-ux-improve -g -y

Use without installing

npx skills use catlog22/Claude-Code-Workflow@team-ux-improve

指定 Agent (Claude Code)

npx skills add catlog22/Claude-Code-Workflow --skill team-ux-improve -a claude-code -g -y

安装 repo 全部 skill

npx skills add catlog22/Claude-Code-Workflow --all -g -y

预览 repo 内 skill

npx skills add catlog22/Claude-Code-Workflow --list

SKILL.md

Frontmatter
{
    "name": "team-ux-improve",
    "description": "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\".",
    "allowed-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_msg"
}

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

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

Version History

  • 07491b0 Current 2026-07-25 09:32

Same Skill Collection

.claude/skills/brainstorm/SKILL.md
.claude/skills/ccw-chain/SKILL.md
.claude/skills/ccw-help/SKILL.md
.claude/skills/delegation-check/SKILL.md
.claude/skills/investigate/SKILL.md
.claude/skills/issue-manage/SKILL.md
.claude/skills/memory-capture/SKILL.md
.claude/skills/memory-manage/SKILL.md
.claude/skills/prompt-generator/SKILL.md
.claude/skills/review-code/SKILL.md
.claude/skills/review-cycle/SKILL.md
.claude/skills/security-audit/SKILL.md
.claude/skills/ship/SKILL.md
.claude/skills/skill-generator/SKILL.md
.claude/skills/skill-iter-tune/SKILL.md
.claude/skills/skill-simplify/SKILL.md
.claude/skills/skill-tuning/SKILL.md
.claude/skills/spec-generator/SKILL.md
.claude/skills/team-arch-opt/SKILL.md
.claude/skills/team-brainstorm/SKILL.md
.claude/skills/team-coordinate/SKILL.md
.claude/skills/team-designer/SKILL.md
.claude/skills/team-executor/SKILL.md
.claude/skills/team-frontend-debug/SKILL.md
.claude/skills/team-frontend/SKILL.md
.claude/skills/team-interactive-craft/SKILL.md
.claude/skills/team-issue/SKILL.md
.claude/skills/team-lifecycle-v4/SKILL.md
.claude/skills/team-motion-design/SKILL.md
.claude/skills/team-perf-opt/SKILL.md
.claude/skills/team-planex/SKILL.md
.claude/skills/team-quality-assurance/SKILL.md
.claude/skills/team-review/SKILL.md
.claude/skills/team-roadmap-dev/SKILL.md
.claude/skills/team-tech-debt/SKILL.md
.claude/skills/team-testing/SKILL.md
.claude/skills/team-ui-polish/SKILL.md
.claude/skills/team-uidesign/SKILL.md
.claude/skills/team-ultra-analyze/SKILL.md
.claude/skills/team-visual-a11y/SKILL.md
.claude/skills/wf-composer/SKILL.md
.claude/skills/wf-player/SKILL.md
.claude/skills/workflow-execute/SKILL.md
.claude/skills/workflow-lite-execute/SKILL.md
.claude/skills/workflow-lite-plan/SKILL.md
.claude/skills/workflow-lite-test-review/SKILL.md
.claude/skills/workflow-multi-cli-plan/SKILL.md
.claude/skills/workflow-plan/SKILL.md
.claude/skills/workflow-skill-designer/SKILL.md

Metadata

Files
0
Version
07491b0
Hash
984855ce
Indexed
2026-07-25 09:32

- 위키
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-08-21 05:16
浙ICP备14020137号-1 $방문자$