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-issue by catlog22/claude-code-workflow
npx skills add https://github.com/catlog22/claude-code-workflow --skill team-issue编排问题解决流程:探索上下文 -> 规划解决方案 -> 审核(可选)-> 编排队列 -> 实施。支持快速、完整和批量流程,包含审核-修复循环。
Skill(skill="team-issue", args="<issue-ids> [--mode=<mode>]")
|
SKILL.md (this file) = Router
|
+--------------+--------------+
| |
no --role flag --role <name>
| |
Coordinator Worker
roles/coordinator/role.md roles/<name>/role.md
|
+-- clarify -> dispatch -> spawn workers -> STOP
|
+-------+-------+-------+-------+
v v v v v
[explor] [plann] [review] [integ] [imple]
| 角色 | 路径 | 前缀 | 内部循环 |
|---|---|---|---|
| 协调者 | 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
| — |
| 探索者 | roles/explorer/role.md | EXPLORE-* | false |
| 规划者 | roles/planner/role.md | SOLVE-* | false |
| 审核者 | roles/reviewer/role.md | AUDIT-* | false |
| 集成者 | roles/integrator/role.md | MARSHAL-* | false |
| 实施者 | roles/implementer/role.md | BUILD-* | 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TISL.workflow/.team/TISL-<slug>-<date>/issueccw cli --mode analysis(只读),ccw cli --mode write(修改)mcp__ccw-tools__team_msg(session_id=<session-id>, ...)协调者使用此模板生成工作进程:
Agent({
subagent_type: "team-worker",
description: "生成 <role> 工作进程",
team_name: "issue",
name: "<role>",
run_in_background: true,
prompt: `## 角色分配
role: <role>
role_spec: ~ 或 <project>/.claude/skills/team-issue/roles/<role>/role.md
session: <session-folder>
session_id: <session-id>
team_name: issue
requirement: <task-description>
inner_loop: false
读取 role_spec 文件以加载阶段 2-4 的领域指令。
执行内置阶段 1(任务发现)-> 角色阶段 2-4 -> 内置阶段 5(报告)。`
})
并行生成(批量模式,N 个探索者或 M 个实施者实例):
Agent({
subagent_type: "team-worker",
name: "<role>-<N>",
team_name: "issue",
run_in_background: true,
prompt: `## 角色分配
role: <role>
role_spec: ~ 或 <project>/.claude/skills/team-issue/roles/<role>/role.md
session: <session-folder>
session_id: <session-id>
team_name: issue
requirement: <task-description>
agent_name: <role>-<N>
inner_loop: false
读取 role_spec 文件以加载阶段 2-4 的领域指令。
执行内置阶段 1(任务发现,owner=<role>-<N>)-> 角色阶段 2-4 -> 内置阶段 5(报告)。`
})
| 命令 | 操作 |
|---|---|
check / status | 查看执行状态图,不推进流程 |
resume / continue | 检查工作进程状态,推进到下一步 |
.workflow/.team/TISL-<slug>-<date>/
├── session.json # 会话元数据 + 流程 + fix_cycles
├── task-analysis.json # 协调者分析输出
├── .msg/
│ ├── messages.jsonl # 消息总线日志
│ └── meta.json # 会话状态 + 跨角色状态
├── wisdom/ # 跨任务知识库
│ ├── learnings.md
│ ├── decisions.md
│ ├── conventions.md
│ └── issues.md
├── explorations/ # 探索者输出
│ └── context-<issueId>.json
├── solutions/ # 规划者输出
│ └── solution-<issueId>.json
├── audits/ # 审核者输出
│ └── audit-report.json
├── queue/ # 集成者输出(也位于 .workflow/issues/queue/)
└── builds/ # 实施者输出
| 场景 | 解决方案 |
|---|---|
| 未知命令 | 报错并显示可用命令列表 |
| 角色未找到 | 报错并显示角色注册表 |
| CLI 工具失败 | 工作进程回退到直接实现 |
| 快速推进冲突 | 协调者在下次回调时协调 |
| 完成操作失败 | 默认为保持活动状态 |
| 审核拒绝超过 2 轮 | 强制收敛到集成者 |
| 未找到给定 ID 的问题 | 协调者向用户报告错误 |
| 延迟的 BUILD 数量未知 | 延迟到 MARSHAL 回调处理 |
每周安装次数
41
代码仓库
GitHub 星标数
1.5K
首次出现
2026年2月17日
安全审计
安装于
codex40
gemini-cli39
github-copilot39
kimi-cli39
amp39
cline39
Orchestrate issue resolution pipeline: explore context -> plan solution -> review (optional) -> marshal queue -> implement. Supports Quick, Full, and Batch pipelines with review-fix cycle.
Skill(skill="team-issue", args="<issue-ids> [--mode=<mode>]")
|
SKILL.md (this file) = Router
|
+--------------+--------------+
| |
no --role flag --role <name>
| |
Coordinator Worker
roles/coordinator/role.md roles/<name>/role.md
|
+-- clarify -> dispatch -> spawn workers -> STOP
|
+-------+-------+-------+-------+
v v v v v
[explor] [plann] [review] [integ] [imple]
| Role | Path | Prefix | Inner Loop |
|---|---|---|---|
| coordinator | roles/coordinator/role.md | — | — |
| explorer | roles/explorer/role.md | EXPLORE-* | false |
| planner | roles/planner/role.md | SOLVE-* | false |
| reviewer | roles/reviewer/role.md | AUDIT-* | false |
| integrator | roles/integrator/role.md | MARSHAL-* | false |
| implementer | roles/implementer/role.md | BUILD-* | false |
Parse $ARGUMENTS:
--role <name> → Read roles/<name>/role.md, execute Phase 2-4--role → Read roles/coordinator/role.md, execute entry routerTISL.workflow/.team/TISL-<slug>-<date>/issueccw 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: "issue",
name: "<role>",
run_in_background: true,
prompt: `## Role Assignment
role: <role>
role_spec: ~ or <project>/.claude/skills/team-issue/roles/<role>/role.md
session: <session-folder>
session_id: <session-id>
team_name: issue
requirement: <task-description>
inner_loop: 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).`
})
Parallel spawn (Batch mode, N explorer or M implementer instances):
Agent({
subagent_type: "team-worker",
name: "<role>-<N>",
team_name: "issue",
run_in_background: true,
prompt: `## Role Assignment
role: <role>
role_spec: ~ or <project>/.claude/skills/team-issue/roles/<role>/role.md
session: <session-folder>
session_id: <session-id>
team_name: issue
requirement: <task-description>
agent_name: <role>-<N>
inner_loop: false
Read role_spec file to load Phase 2-4 domain instructions.
Execute built-in Phase 1 (task discovery, owner=<role>-<N>) -> role Phase 2-4 -> built-in Phase 5 (report).`
})
| Command | Action |
|---|---|
check / status | View execution status graph, no advancement |
resume / continue | Check worker states, advance next step |
.workflow/.team/TISL-<slug>-<date>/
├── session.json # Session metadata + pipeline + fix_cycles
├── task-analysis.json # Coordinator analyze output
├── .msg/
│ ├── messages.jsonl # Message bus log
│ └── meta.json # Session state + cross-role state
├── wisdom/ # Cross-task knowledge
│ ├── learnings.md
│ ├── decisions.md
│ ├── conventions.md
│ └── issues.md
├── explorations/ # Explorer output
│ └── context-<issueId>.json
├── solutions/ # Planner output
│ └── solution-<issueId>.json
├── audits/ # Reviewer output
│ └── audit-report.json
├── queue/ # Integrator output (also .workflow/issues/queue/)
└── builds/ # Implementer output
| Scenario | Resolution |
|---|---|
| Unknown command | Error with available command list |
| Role not found | Error with role registry |
| CLI tool fails | Worker fallback to direct implementation |
| Fast-advance conflict | Coordinator reconciles on next callback |
| Completion action fails | Default to Keep Active |
| Review rejection exceeds 2 rounds | Force convergence to integrator |
| No issues found for given IDs | Coordinator reports error to user |
| Deferred BUILD count unknown | Defer to MARSHAL callback |
Weekly Installs
41
Repository
GitHub Stars
1.5K
First Seen
Feb 17, 2026
Security Audits
Gen Agent Trust HubPassSocketFailSnykWarn
Installed on
codex40
gemini-cli39
github-copilot39
kimi-cli39
amp39
cline39
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