重要前提
安装AI Skills的关键前提是:必须科学上网,且开启TUN模式,这一点至关重要,直接决定安装能否顺利完成,在此郑重提醒三遍:科学上网,科学上网,科学上网。查看完整安装教程 →
team-quality-assurance by catlog22/claude-code-workflow
npx skills add https://github.com/catlog22/claude-code-workflow --skill team-quality-assurance编排多智能体质量保证流程:侦察员 -> 策略师 -> 生成器 -> 执行器 -> 分析师。支持发现、测试和完整的闭环模式,具备并行生成与垃圾回收循环。
Skill(skill="team-quality-assurance", 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 v
[scout] [strat] [gen] [exec] [analyst]
team-worker agents, each loads roles/<role>/role.md
| 角色 | 路径 | 前缀 | 内部循环 |
|---|---|---|---|
| coordinator | roles/coordinator/role.md |
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
| — |
| — |
| scout | roles/scout/role.md | SCOUT-* | false |
| strategist | roles/strategist/role.md | QASTRAT-* | false |
| generator | roles/generator/role.md | QAGEN-* | false |
| executor | roles/executor/role.md | QARUN-* | true |
| analyst | roles/analyst/role.md | QAANA-* | false |
解析 $ARGUMENTS:
--role <name> -> 读取 roles/<name>/role.md,执行阶段 2-4--role -> 读取 roles/coordinator/role.md,执行入口路由器QA.workflow/.team/QA-<slug>-<date>/quality-assuranceccw cli --mode analysis(只读),ccw cli --mode write(修改)mcp__ccw-tools__team_msg(session_id=<session-id>, ...)协调器使用此模板生成工作进程:
Agent({
subagent_type: "team-worker",
description: "Spawn <role> worker",
team_name: "quality-assurance",
name: "<role>",
run_in_background: true,
prompt: `## Role Assignment
role: <role>
role_spec: ~ or <project>/.claude/skills/team-quality-assurance/roles/<role>/role.md
session: <session-folder>
session_id: <session-id>
team_name: quality-assurance
requirement: <task-description>
inner_loop: <true|false>
Read role_spec file to load Phase 2-4 domain instructions.
Execute built-in Phase 1 (task discovery) -> role Phase 2-4 -> built-in Phase 5 (report).`
})
| 命令 | 操作 |
|---|---|
check / status | 查看流水线状态图 |
resume / continue | 推进到下一步 |
--mode=discovery | 强制发现模式 |
--mode=testing | 强制测试模式 |
--mode=full | 强制完整质量保证模式 |
当流水线完成时,协调器呈现:
AskUserQuestion({
questions: [{
question: "质量保证流水线已完成。您希望做什么?",
header: "完成",
multiSelect: false,
options: [
{ label: "归档与清理(推荐)", description: "归档会话,清理团队" },
{ label: "保持活动", description: "保留会话以供后续工作" },
{ label: "导出结果", description: "将交付物导出到目标目录" }
]
}]
})
.workflow/.team/QA-<slug>-<date>/
├── .msg/messages.jsonl # 团队消息总线
├── .msg/meta.json # 会话状态 + 共享内存
├── wisdom/ # 跨任务知识
├── scan/ # 侦察员输出
├── strategy/ # 策略师输出
├── tests/ # 生成器输出 (L1/, L2/, L3/)
├── results/ # 执行器输出
└── analysis/ # 分析师输出
| 场景 | 解决方案 |
|---|---|
| 未知的 --role 值 | 显示可用角色列表的错误 |
| 角色未找到 | 显示预期路径的错误 (roles//role.md) |
| CLI 工具失败 | 工作进程回退到直接实现 |
| 侦察员未发现问题 | 报告干净的扫描结果,跳转到测试模式 |
| 垃圾回收循环超限 | 接受当前覆盖率并发出警告 |
| 快速推进冲突 | 协调器在下一次回调时协调 |
| 完成操作失败 | 默认保持活动状态 |
每周安装
40
仓库
GitHub 星标
1.5K
首次出现
2026年2月17日
安全审计
安装于
cline39
github-copilot39
codex39
kimi-cli39
gemini-cli39
cursor39
Orchestrate multi-agent QA: scout -> strategist -> generator -> executor -> analyst. Supports discovery, testing, and full closed-loop modes with parallel generation and GC loops.
Skill(skill="team-quality-assurance", 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 v
[scout] [strat] [gen] [exec] [analyst]
team-worker agents, each loads roles/<role>/role.md
| Role | Path | Prefix | Inner Loop |
|---|---|---|---|
| coordinator | roles/coordinator/role.md | — | — |
| scout | roles/scout/role.md | SCOUT-* | false |
| strategist | roles/strategist/role.md | QASTRAT-* | false |
| generator | roles/generator/role.md | QAGEN-* | false |
| executor | roles/executor/role.md | QARUN-* | true |
| analyst | roles/analyst/role.md | QAANA-* | false |
Parse $ARGUMENTS:
--role <name> -> Read roles/<name>/role.md, execute Phase 2-4--role -> Read roles/coordinator/role.md, execute entry routerQA.workflow/.team/QA-<slug>-<date>/quality-assuranceccw cli --mode analysis (read-only), ccw cli --mode write (modifications)mcp__ccw-tools__team_msg(session_id=<session-id>, ...)Coordinator spawns workers using this template:
Agent({
subagent_type: "team-worker",
description: "Spawn <role> worker",
team_name: "quality-assurance",
name: "<role>",
run_in_background: true,
prompt: `## Role Assignment
role: <role>
role_spec: ~ or <project>/.claude/skills/team-quality-assurance/roles/<role>/role.md
session: <session-folder>
session_id: <session-id>
team_name: quality-assurance
requirement: <task-description>
inner_loop: <true|false>
Read role_spec file to load Phase 2-4 domain instructions.
Execute built-in Phase 1 (task discovery) -> role Phase 2-4 -> built-in Phase 5 (report).`
})
| Command | Action |
|---|---|
check / status | View pipeline status graph |
resume / continue | Advance to next step |
--mode=discovery | Force discovery mode |
--mode=testing | Force testing mode |
--mode=full | Force full QA mode |
When pipeline completes, coordinator presents:
AskUserQuestion({
questions: [{
question: "Quality Assurance pipeline complete. What would you like to do?",
header: "Completion",
multiSelect: false,
options: [
{ label: "Archive & Clean (Recommended)", description: "Archive session, clean up team" },
{ label: "Keep Active", description: "Keep session for follow-up work" },
{ label: "Export Results", description: "Export deliverables to target directory" }
]
}]
})
.workflow/.team/QA-<slug>-<date>/
├── .msg/messages.jsonl # Team message bus
├── .msg/meta.json # Session state + shared memory
├── wisdom/ # Cross-task knowledge
├── scan/ # Scout output
├── strategy/ # Strategist output
├── tests/ # Generator output (L1/, L2/, L3/)
├── results/ # Executor output
└── analysis/ # Analyst output
| Scenario | Resolution |
|---|---|
| Unknown --role value | Error with available role list |
| Role not found | Error with expected path (roles//role.md) |
| CLI tool fails | Worker fallback to direct implementation |
| Scout finds no issues | Report clean scan, skip to testing mode |
| GC loop exceeded | Accept current coverage with warning |
| Fast-advance conflict | Coordinator reconciles on next callback |
| Completion action fails | Default to Keep Active |
Weekly Installs
40
Repository
GitHub Stars
1.5K
First Seen
Feb 17, 2026
Security Audits
Gen Agent Trust HubWarnSocketFailSnykPass
Installed on
cline39
github-copilot39
codex39
kimi-cli39
gemini-cli39
cursor39
GitHub Actions 官方文档查询助手 - 精准解答 CI/CD 工作流问题
53,800 周安装