work
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseWork
工作内容
Orchestrate end-to-end task implementation: understand the task, assess complexity, implement directly or distribute across a team, then polish the result.
编排端到端任务实现:理解任务、评估复杂度,直接实现或分配给团队完成,之后打磨结果。
Pre-flight
前置检查
Verify prerequisites before starting any work.
- Check availability: Confirm the
code-polishskill exists. If missing, stop immediately with: "Thecode-polishskill is required but not installed."code-polish - Verify repository context: Run . If not inside a git worktree, stop with a clear error.
git rev-parse --is-inside-work-tree
开始任何工作前先验证先决条件。
- 检查技能可用性:确认
code-polish技能已存在。若缺失,立即停止并提示:“code-polish技能为必需项,但未安装。”code-polish - 验证仓库上下文:执行命令。若不在git工作目录内,立即停止并给出明确错误提示。
git rev-parse --is-inside-work-tree
Workflow
工作流程
1) Parse Task
1) 解析任务
Read the task description from .
$ARGUMENTS- If is empty, ask the user for a task description and stop.
$ARGUMENTS - Extract key signals: scope (files, modules, components mentioned), action type (new feature, bug fix, refactor, migration), and any constraints.
- Note any referenced issues, PRs, or URLs for later context gathering.
从中读取任务描述。
$ARGUMENTS- 若为空,询问用户获取任务描述并停止操作。
$ARGUMENTS - 提取关键信息:范围(提及的文件、模块、组件)、操作类型(新功能开发、Bug修复、重构、迁移)及任何约束条件。
- 记录任何关联的Issue、PR或URL,用于后续上下文收集。
2) Assess Complexity
2) 评估复杂度
Classify the task as simple or complex using these heuristics:
| Signal | Simple | Complex |
|---|---|---|
| File count | 1-3 files | 4+ files |
| Module span | Single module or package | Cross-module or cross-package |
| Dependency chain | No new dependencies | New packages or service integrations |
| Risk surface | Low (UI, docs, config) | High (auth, payments, data, infra) |
| Parallelism | Sequential steps only | Independent subtasks benefit from concurrency |
A task is complex when 3 or more signals fall in the complex column. When in doubt, prefer the simple path — team overhead is only justified when parallelism provides a real speedup.
- Simple — proceed to Step 3.
- Complex — proceed to Step 4.
使用以下规则将任务划分为简单或复杂:
| 信号指标 | 简单任务 | 复杂任务 |
|---|---|---|
| 文件数量 | 1-3个文件 | 4个及以上文件 |
| 模块范围 | 单个模块或包 | 跨模块或跨包 |
| 依赖链 | 无新增依赖 | 新增包或服务集成 |
| 风险面 | 低风险(UI、文档、配置) | 高风险(认证、支付、数据、基础设施) |
| 并行性 | 仅支持顺序步骤 | 独立子任务可从并行执行中获益 |
当3项及以上信号符合复杂任务特征时,判定为复杂任务。若存在疑问,优先按简单任务处理——仅当并行执行能切实提升效率时,才值得引入团队协作的额外开销。
- 简单任务 —— 进入步骤3。
- 复杂任务 —— 进入步骤4。
3) Implement (Simple Path)
3) 任务实现(简单路径)
Execute the task directly without spawning subagents.
- Gather context: Read all relevant files. Understand existing code, tests, and conventions.
- Implement: Make the changes. Follow project conventions inferred from existing code, linters, and formatters.
- Verify: Run the narrowest useful checks:
- Formatter/linter on touched files.
- Targeted tests for touched modules.
- Type check when relevant.
- If fast checks pass, run broader checks only when risk warrants it.
- Proceed to Step 5 (Polish).
无需生成子Agent,直接完成任务。
- 收集上下文:读取所有相关文件,理解现有代码、测试及约定。
- 实现开发:进行代码修改,遵循从现有代码、代码检查工具及格式化工具中推断出的项目约定。
- 验证检查:执行最必要的验证操作:
- 对修改的文件运行格式化工具/代码检查工具。
- 针对修改的模块执行定向测试。
- 若相关,执行类型检查。
- 若快速检查通过,仅当风险较高时才执行更全面的检查。
- 进入步骤5(代码打磨)。
4) Implement (Complex Path)
4) 任务实现(复杂路径)
Distribute work across a team of subagents.
将工作分配给子Agent团队完成。
4a) Decompose
4a) 任务拆分
Break the task into independent subtasks. Each subtask should:
- Target a distinct set of files with minimal overlap.
- Be completable without waiting on other subtasks (no circular dependencies).
- Include clear acceptance criteria.
Avoid over-decomposition. If subtasks cannot run in parallel, prefer the simple path.
将任务拆分为独立的子任务。每个子任务需满足:
- 针对一组明确区分的文件,重叠最小化。
- 无需等待其他子任务即可完成(无循环依赖)。
- 包含清晰的验收标准。
避免过度拆分。若子任务无法并行执行,优先选择简单路径。
4b) Create Team and Assign
4b) 创建团队并分配任务
Create a team with a name derived from the task (e.g., "add-auth", "refactor-api"). Create a task for each subtask. Set up dependencies when ordering matters.
Spawn implementation agents as teammates. Assign each agent one or more tasks.
Recommended team sizing:
- 1 agent per module when modules are independent.
- Separate agent for shared utilities when consumers depend on them (utility blocks consumers).
- Dedicated agent for tests if test volume is high.
根据任务名称创建团队(例如“add-auth”、“refactor-api”)。为每个子任务创建独立任务项,若有顺序要求则设置依赖关系。
生成实现型Agent作为团队成员,为每个Agent分配一个或多个任务。
推荐团队规模:
- 若模块相互独立,每个模块分配1个Agent。
- 当多个消费者依赖共享工具库时,为共享工具库分配独立Agent(工具库的开发会阻塞消费者)。
- 若测试量较大,分配专门的测试Agent。
4c) Coordinate
4c) 协调管理
Monitor progress. As agents complete tasks:
- Review output for integration issues.
- Resolve cross-agent conflicts (merge overlaps, API mismatches).
- Assign follow-up tasks if gaps emerge.
After all tasks complete:
- Run integration verification: full test suite, type check, lint.
- Fix any integration issues directly — do not re-spawn agents for small fixes.
- Shut down teammates.
- Proceed to Step 5 (Polish).
监控任务进度。当Agent完成任务后:
- 检查输出是否存在集成问题。
- 解决跨Agent冲突(合并重叠代码、修复API不匹配问题)。
- 若发现遗漏,分配后续补充任务。
所有任务完成后:
- 执行集成验证:完整测试套件、类型检查、代码检查。
- 直接修复任何集成问题——小问题无需重新生成Agent。
- 终止团队成员Agent。
- 进入步骤5(代码打磨)。
5) Polish
5) 代码打磨
Invoke to simplify and review all session-modified files.
/code-polishWait for completion. If it reports residual risks or stop conditions, relay them to the user.
This step is mandatory — always run it, even if the implementation seems clean.
调用对本次会话中修改的所有文件进行简化和审查。
/code-polish等待操作完成。若工具报告残留风险或停止条件,将相关信息反馈给用户。
此步骤为强制性操作——即使实现看起来无问题,也必须执行。
Error Handling
错误处理
| Error | Response |
|---|---|
Empty | Ask for a task description and stop |
| Stop immediately with installation instructions |
| Not in a git repository | Stop with clear error |
| Verification failures after impl | Attempt to fix; if unfixable, report to user before polishing |
| Team agent fails or times out | Reclaim the task and complete it directly |
| Relay to user with context |
| 错误类型 | 响应方式 |
|---|---|
| 询问用户获取任务描述并停止操作 |
| 立即停止并提供安装指引 |
| 不在git仓库内 | 停止操作并给出明确错误提示 |
| 实现后验证失败 | 尝试修复;若无法修复,在打磨前向用户报告问题 |
| 团队Agent执行失败或超时 | 收回任务并直接完成 |
| 结合上下文将信息反馈给用户 |
Stop Conditions
停止条件
Stop and ask for direction when:
- The task description is ambiguous and multiple interpretations exist.
- Implementation requires changing public APIs or breaking contracts not mentioned in the task.
- The task scope grows beyond the original description during implementation.
- External dependencies (APIs, services, packages) are unavailable or broken.
- A CRITICAL security concern is discovered in existing code adjacent to the task.
出现以下情况时,停止操作并向用户请求指导:
- 任务描述模糊,存在多种解读方式。
- 实现需要修改任务描述中未提及的公共API或破坏现有契约。
- 实现过程中任务范围超出原始描述。
- 外部依赖(API、服务、包)不可用或已损坏。
- 在任务相关的现有代码中发现严重安全问题。",