task
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
Chinese/task - Task Planning Agent
/task - 任务规划Agent
Model: opus (complex planning requires advanced reasoning)
模型: opus(复杂规划需要高级推理能力)
Command Flags
命令参数
| Flag | Short | Description |
|---|---|---|
| | Show available commands and options |
| | Show workflow skills version |
| Enable automated pipeline (implement → test → document → ship) |
| 完整参数 | 缩写 | 说明 |
|---|---|---|
| | 展示可用命令和选项 |
| | 展示工作流技能版本 |
| 启用自动化流水线(实现 → 测试 → 文档 → 发布) |
Flag Handling
参数处理
On or :
-h--help/task - Task Planning Agent
Usage:
/task Create a new task (manual mode)
/task auto Create task with auto-pipeline enabled
/task -h, --help Show this help message
/task -v, --version Show version
Options:
auto After task approval, automatically chain through:
implement → test → document → ship
Examples:
/task # Interactive task creation
/task auto # Task with full automation
Next: /implement {ID}On or :
Display:
-v--versionWorkflow Skills v1.4.1
https://github.com/eljun/claude-skills触发 或 时:
-h--help/task - Task Planning Agent
Usage:
/task Create a new task (manual mode)
/task auto Create task with auto-pipeline enabled
/task -h, --help Show this help message
/task -v, --version Show version
Options:
auto After task approval, automatically chain through:
implement → test → document → ship
Examples:
/task # Interactive task creation
/task auto # Task with full automation
Next: /implement {ID}触发 或 时:
展示:
-v--versionWorkflow Skills v1.4.1
https://github.com/eljun/claude-skillsWhen to Use
使用场景
Invoke when:
/task- Starting a new feature or enhancement
- Planning a bug fix that requires multiple changes
- User says "I want to add...", "Let's implement...", "Can we build..."
- Discussing requirements before coding
- Creating implementation specs for future work
出现以下情况时调用 :
/task- 启动新功能或功能增强开发
- 规划需要多处修改的缺陷修复
- 用户表示「我想要添加...」、「我们来实现...」、「我们能不能做...」
- 编码前讨论需求
- 为后续工作创建实现规范
Invocation Options
调用选项
| Command | Mode | Behavior |
|---|---|---|
| Manual | You control each step: implement → test → document → ship |
| Automated | After task approval, all steps run autonomously |
| 命令 | 模式 | 行为 |
|---|---|---|
| 手动 | 你可以控制每一步:实现 → 测试 → 文档 → 发布 |
| 自动 | 任务通过审核后,所有步骤自动执行 |
Auto Mode Workflow
自动模式工作流
/task auto → User approves task
↓
/implement
↓
/test (Playwright E2E)
│
PASS → /document
FAIL → /implement (with test report)
│
▼
/ship → PR + notifyAuto mode notes:
- Full automation: Runs through implement → test → document → ship
- Test failures: Auto-retries by sending test report back to implement agent
- Unexpected errors: Stops and notifies you
/task auto → User approves task
↓
/implement
↓
/test (Playwright E2E)
│
PASS → /document
FAIL → /implement (with test report)
│
▼
/ship → PR + notify自动模式说明:
- 全自动化: 完整执行实现 → 测试 → 文档 → 发布流程
- 测试失败: 会将测试报告回传给实现Agent自动重试
- 意外错误: 停止流程并通知用户
Workflow
工作流
User Request
↓
1. Discuss & clarify requirements
2. Research codebase for context
3. Generate Task ID (next available number)
4. Create docs/task/{ID}-{task-name}.md
5. Add to TASKS.md under "## Planned" with ID
6. User can /clear and start fresh
↓
Ready for /implement {ID}User Request
↓
1. Discuss & clarify requirements
2. Research codebase for context
3. Generate Task ID (next available number)
4. Create docs/task/{ID}-{task-name}.md
5. Add to TASKS.md under "## Planned" with ID
6. User can /clear and start fresh
↓
Ready for /implement {ID}What This Skill Does
该技能的功能
1. Requirements Gathering
1. 需求收集
Ask clarifying questions:
- What is the expected behavior?
- Any UI/UX preferences?
- Priority level?
询问澄清问题:
- 预期行为是什么?
- 有没有UI/UX偏好?
- 优先级是多少?
Version Impact Guidelines
版本影响指南
Set the field based on the type of change:
Version Impact| Type | Default Impact | When to Use |
|---|---|---|
| | New functionality, backwards compatible |
| | Bug fixes, no new features |
| | Improvements to existing features |
| | Doc updates only |
| | Maintenance, refactoring |
Override to when:
major- Breaking API changes
- Database schema changes requiring migration
- Removing deprecated features
- Changes that require user action
根据变更类型设置字段:
Version Impact| 类型 | 默认影响 | 适用场景 |
|---|---|---|
| | 新功能,向后兼容 |
| | 缺陷修复,无新功能 |
| | 对现有功能的优化 |
| | 仅文档更新 |
| | 维护、重构工作 |
升级为的场景:
major- 破坏性API变更
- 需要迁移的数据库schema变更
- 移除已废弃功能
- 需要用户采取行动的变更
2. Codebase Research
2. 代码库调研
Before creating the task document:
- Check existing similar implementations
- Identify files to modify
- Find reusable components/hooks
- Note potential pitfalls
Note: Specialized skills (vercel-react-best-practices, supabase-postgres-best-practices) are invoked during, not during task planning. This keeps planning focused on requirements and architecture./implement
创建任务文档前:
- 检查现有类似实现
- 确认需要修改的文件
- 查找可复用的组件/hooks
- 标注潜在的问题
注意: 专用技能(vercel-react-best-practices、supabase-postgres-best-practices)会在阶段调用,不会在任务规划阶段调用,确保规划阶段聚焦于需求和架构。/implement
3. Generate Task ID
3. 生成任务ID
Before creating the task document, generate the next available Task ID:
- Read TASKS.md to find all existing task IDs
- Find the highest ID number across all sections (Planned, In Progress, Testing, etc.)
- Assign next ID = highest + 1
- If no tasks exist, start with ID = 1
ID Format: Simple integers (1, 2, 3, ...)
bash
undefined创建任务文档前,生成下一个可用的任务ID:
- 读取TASKS.md查找所有现有任务ID
- 找到所有分区(规划中、进行中、测试中等)的最大ID
- 下一个ID = 最大ID + 1
- 如果没有现有任务,ID从1开始
ID格式: 纯整数(1, 2, 3, ...)
bash
undefinedExample: If TASKS.md has tasks with IDs 1, 2, 5
Example: If TASKS.md has tasks with IDs 1, 2, 5
Next ID = 6 (highest + 1)
Next ID = 6 (highest + 1)
undefinedundefined4. Create Task Document
4. 创建任务文档
Location:
docs/task/{ID}-{task-name}.mdNaming: Zero-padded ID prefix + kebab-case descriptive name:
001-user-dashboard-redesign.md002-lead-auto-tagging.md003-booking-calendar-view.md
ID Padding: Use 3 digits (001, 002, ... 999) for consistent sorting.
存储位置:
docs/task/{ID}-{task-name}.md命名规则: 补零前缀的ID + 短横线分隔的描述性名称:
001-user-dashboard-redesign.md002-lead-auto-tagging.md003-booking-calendar-view.md
ID补零: 使用3位数字(001, 002, ... 999)保证排序一致。
5. Update TASKS.md
5. 更新TASKS.md
Add the task to the "## Planned" section with ID and link to task document.
If TASKS.md doesn't exist, create it first with this structure:
markdown
undefined将任务添加到「## Planned」分区,附带ID和任务文档链接。
如果TASKS.md不存在,先按照以下结构创建:
markdown
undefinedTasks
Tasks
Task tracking for the development workflow.
Task tracking for the development workflow.
Planned
Planned
Tasks ready for .
/implement {ID}| ID | Task | Priority | Task Doc | Created |
|---|
Tasks ready for .
/implement {ID}| ID | Task | Priority | Task Doc | Created |
|---|
In Progress
In Progress
| ID | Task | Started | Task Doc | Status |
|---|
| ID | Task | Started | Task Doc | Status |
|---|
Testing
Testing
Tasks being tested via .
/test| ID | Task | Task Doc | Test Report | Status |
|---|
Tasks being tested via .
/test| ID | Task | Task Doc | Test Report | Status |
|---|
Approved
Approved
Tested and approved. Ready for then .
/document/ship| ID | Task | Task Doc | Feature Doc | Test Report | Approved |
|---|
Tested and approved. Ready for then .
/document/ship| ID | Task | Task Doc | Feature Doc | Test Report | Approved |
|---|
Ready to Ship
Ready to Ship
PRs created via . Items stay here until is run (even after merge).
/ship/release| ID | Task | Branch | PR | Merged | Task Doc |
|---|
PRs created via . Items stay here until is run (even after merge).
/ship/release| ID | Task | Branch | PR | Merged | Task Doc |
|---|
Shipped
Shipped
Released items. Only moves items here with version number.
/release| ID | Task | PR | Release | Shipped |
|---|
---Released items. Only moves items here with version number.
/release| ID | Task | PR | Release | Shipped |
|---|
---Task Document Template
任务文档模板
Create this structure in :
docs/task/{ID}-{task-name}.mdmarkdown
undefined在中使用以下结构:
docs/task/{ID}-{task-name}.mdmarkdown
undefined{Task Title}
{Task Title}
ID: {number} Status: PLANNED Priority: HIGH | MEDIUM | LOW Type: feature | bugfix | enhancement | documentation | chore Version Impact: minor | patch | major Created: {Date} Platform: Web Automation: manual | auto
ID: {number} Status: PLANNED Priority: HIGH | MEDIUM | LOW Type: feature | bugfix | enhancement | documentation | chore Version Impact: minor | patch | major Created: {Date} Platform: Web Automation: manual | auto
Overview
Overview
{2-3 sentence description of what we're building and why}
{2-3 sentence description of what we're building and why}
Requirements
Requirements
Must Have
Must Have
- Requirement 1
- Requirement 2
- Requirement 1
- Requirement 2
Nice to Have
Nice to Have
- Optional requirement
- Optional requirement
Current State
Current State
{Description of how things work now, if applicable}
Current Files:
| File | Purpose |
|---|---|
| Description |
{Description of how things work now, if applicable}
Current Files:
| File | Purpose |
|---|---|
| Description |
Proposed Solution
Proposed Solution
{Description of the implementation approach}
{Description of the implementation approach}
Architecture
Architecture
{High-level design decisions}
{High-level design decisions}
File Changes
File Changes
| Action | File | Description |
|---|---|---|
| CREATE | | New component for X |
| MODIFY | | Add Y functionality |
| DELETE | | No longer needed |
| Action | File | Description |
|---|---|---|
| CREATE | | New component for X |
| MODIFY | | Add Y functionality |
| DELETE | | No longer needed |
Implementation Steps
Implementation Steps
Step 1: {Title}
Step 1: {Title}
{Detailed instructions with code snippets if needed}
{Detailed instructions with code snippets if needed}
Step 2: {Title}
Step 2: {Title}
{Detailed instructions}
{Detailed instructions}
Code Examples
Code Examples
{Include specific code changes when helpful}
typescript
// Example of key implementation{Include specific code changes when helpful}
typescript
// Example of key implementationTesting Checklist
Testing Checklist
- Test case 1
- Test case 2
- Edge case handling
- Test case 1
- Test case 2
- Edge case handling
Dependencies
Dependencies
- Required packages: {list any new deps}
- Required APIs: {list endpoints needed}
- Blocked by: {any dependencies on other tasks}
- Required packages: {list any new deps}
- Required APIs: {list endpoints needed}
- Blocked by: {any dependencies on other tasks}
Notes for Implementation Agent
Notes for Implementation Agent
{Any important context the /implement agent needs to know}
{Any important context the /implement agent needs to know}
Related
Related
- Similar feature: [link to docs]
- Design reference: [link if applicable]
---- Similar feature: [link to docs]
- Design reference: [link if applicable]
---TASKS.md Integration
TASKS.md 集成
After creating the task document, add an entry with the ID:
markdown
undefined创建完任务文档后,添加ID对应的条目:
markdown
undefinedPlanned
Planned
| ID | Task | Priority | Task Doc | Created |
|---|---|---|---|---|
| 1 | Dashboard Redesign | HIGH | 001-dashboard-redesign.md | Jan 25 |
| 2 | Fix Login Bug | MEDIUM | 002-fix-login-bug.md | Jan 26 |
---| ID | Task | Priority | Task Doc | Created |
|---|---|---|---|---|
| 1 | Dashboard Redesign | HIGH | 001-dashboard-redesign.md | Jan 25 |
| 2 | Fix Login Bug | MEDIUM | 002-fix-login-bug.md | Jan 26 |
---Output Checklist
输出检查清单
Before completing :
/task- Task document created in
docs/task/ - Document has all required sections filled
- Implementation steps are clear and actionable
- File paths verified to exist (for modifications)
- Added to TASKS.md "## Planned" section
- User understands the task and approves
完成操作前检查:
/task- 任务文档已创建在路径下
docs/task/ - 文档已填写所有必填部分
- 实现步骤清晰可执行
- (修改操作的)文件路径已验证存在
- 已添加到TASKS.md的「## Planned」分区
- 用户理解任务内容并已审核通过
Handoff to /implement
移交到/implement
When planning is complete, inform the user:
规划完成后,通知用户:
Manual Mode
手动模式
Task created: #{ID} - {Task Title}
Document: docs/task/{ID}-{task-name}.md
Added to TASKS.md under "Planned"
Next Steps:
/implement {ID} # e.g., /implement 1
/implement {ID}-{task-name} # e.g., /implement 001-auth-jwt
(Optional: /clear first to start fresh session)Task created: #{ID} - {Task Title}
Document: docs/task/{ID}-{task-name}.md
Added to TASKS.md under "Planned"
Next Steps:
/implement {ID} # e.g., /implement 1
/implement {ID}-{task-name} # e.g., /implement 001-auth-jwt
(Optional: /clear first to start fresh session)Auto Mode
自动模式
When was invoked and user approves the task:
/task auto- Set in the task document
Automation: auto - Use Task tool to spawn with model: opus
/implement {ID} - The implement skill will chain to subsequent skills automatically
Task approved! Starting automated pipeline...
Task: #{ID} - {Task Title}
Spawning /implement {ID} with opus model...IMPORTANT: In auto mode, after user approves the task:
- Do NOT wait for user to invoke /implement
- Use Task tool to spawn implement agent with model: opus
- Example:
Task({ subagent_type: "general-purpose", model: "opus", prompt: "/implement {ID}" }) - The automation flag in the task doc controls subsequent chaining
当调用且用户审核通过任务后:
/task auto- 在任务文档中设置
Automation: auto - 使用任务工具调用,指定model: opus
/implement {ID} - 实现技能会自动链式调用后续技能
Task approved! Starting automated pipeline...
Task: #{ID} - {Task Title}
Spawning /implement {ID} with opus model...重要提示: 自动模式下,用户审核通过任务后:
- 不要等待用户调用/implement
- 使用任务工具调用实现Agent,指定模型为opus
- 示例:
Task({ subagent_type: "general-purpose", model: "opus", prompt: "/implement {ID}" }) - 任务文档中的自动化标记会控制后续的链式调用
Related Skills
相关技能
| Skill | When to Use |
|---|---|
| After task is approved, to start coding |
| After implementation, to verify the feature |
| After tests pass, to create documentation |
| After documentation, to create PR |
| After multiple items shipped, to create release |
Note: Specialized skills (vercel-react-best-practices, supabase-postgres-best-practices) are invoked during , not during . Install them separately from their respective repos.
/implement/task| 技能 | 使用场景 |
|---|---|
| 任务审核通过后,开始编码 |
| 实现完成后,验证功能 |
| 测试通过后,创建文档 |
| 文档完成后,创建PR |
| 多个功能发布后,创建版本 |
注意: 专用技能(vercel-react-best-practices、supabase-postgres-best-practices)会在阶段调用,不会在阶段调用,可从对应仓库单独安装。
/implement/task