Back to Details

to-issues

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

To Issues

转化为任务

Convert plans and specs into independently-actionable vertical slice issues.
将计划和规格转化为可独立执行的垂直切片任务。

When to use this skill

何时使用此Skill

  • Breaking down a plan or PRD into implementation tickets
  • Decomposing a feature into parallel work items
  • Preparing work for AI agents (AFK) or human developers (HITL)
  • 将计划或PRD拆解为可执行的任务工单
  • 将功能分解为可并行处理的工作项
  • 为AI Agent（AFK）或人类开发者（HITL）准备工作内容

When not to use this skill

何时不使用此Skill

  • Creating a PRD from scratch → use 
    to-prd
  • Evaluating/categorizing existing issues → use 
    triage
  • Planning without implementation tickets → use 
    task-planning
  • 从零开始创建PRD → 使用
    to-prd
  • 评估/分类现有任务 → 使用
    triage
  • 仅做规划不生成任务工单 → 使用
    task-planning

Core principle: vertical slices

核心原则：垂直切片

Each slice is a narrow but COMPLETE path through every layer: schema, API, UI, tests. Completed slices are independently demoable.
❌ Horizontal: "Add all database tables" → "Add all API endpoints" → "Add all UI components" ✅ Vertical: "User can create a task" (schema + API + UI + tests, end-to-end)
每个切片都是贯穿所有层级的精简但完整的路径：schema、API、UI、测试。完成的切片可独立进行演示。
❌ 横向拆分：“添加所有数据库表” → “添加所有API端点” → “添加所有UI组件” ✅ 垂直拆分：“用户可创建任务”（包含schema + API + UI + 测试的端到端流程）

Issue types

任务类型

  • HITL — requires human interaction: architectural decisions, design review, external access, manual testing
  • AFK — implementable and mergeable without human input (preferred when possible)
  • HITL — 需要人工参与：架构决策、设计评审、外部权限申请、手动测试
  • AFK — 无需人工输入即可实现并合并（尽可能优先选择此类）

Process

流程

1. Gather context

1. 收集上下文

Read the plan from the conversation or fetch referenced issues. Understand the full scope before decomposing.
阅读对话中的计划内容或获取关联任务信息。在拆解前先理解完整范围。

2. Explore the codebase

2. 探索代码库

Use the project's domain glossary (CONTEXT.md) and vocabulary when naming issues. Understand current state to avoid redundant work.
命名任务时使用项目的领域术语表（CONTEXT.md）和词汇。了解当前状态以避免重复工作。

3. Draft vertical slices

3. 草拟垂直切片

  • Each slice = one independently-completable unit of user-facing value
  • Each slice cuts through all relevant layers
  • Order by dependency (what must exist before what)
  • Label HITL or AFK
  • 每个切片 = 一个可独立完成的用户价值单元
  • 每个切片覆盖所有相关层级
  • 按依赖关系排序（确定执行顺序）
  • 标记为HITL或AFK类型

4. Quiz the user

4. 与用户确认

Before publishing, confirm:
  • Are the slices the right granularity? (Too big = hard to estimate; too small = churn)
  • Are dependencies correctly ordered?
  • Any slices that should be merged or split?
  • Any HITL/AFK classifications to change?
发布前确认：
  • 切片的粒度是否合适？（太大=难以估算；太小=频繁切换）
  • 依赖顺序是否正确？
  • 是否有需要合并或拆分的切片？
  • 是否需要调整HITL/AFK的分类？

5. Publish to tracker

5. 发布到任务跟踪系统

Publish in dependency order. Use the standard issue template:
markdown
undefined
按依赖顺序发布。使用标准任务模板：
markdown
undefined

Context

Context

[Brief description of what this slice delivers and why it matters]
[Brief description of what this slice delivers and why it matters]

Acceptance Criteria

Acceptance Criteria

  • [Specific, testable criterion]
  • [Specific, testable criterion]
  • [Specific, testable criterion]
  • [Specific, testable criterion]

Implementation Notes

Implementation Notes

[Key decisions, constraints, or approach hints if known]
[Key decisions, constraints, or approach hints if known]

Type

Type

HITL | AFK

Add appropriate labels: category (`bug`/`enhancement`) + state (`needs-triage` or `ready-for-agent`/`ready-for-human`).
HITL | AFK

添加合适的标签：类别（`bug`/`enhancement`）+ 状态（`needs-triage` 或 `ready-for-agent`/`ready-for-human`）。

Instructions

操作说明

  1. Identify the task trigger and expected output.
  2. Follow the workflow steps in this skill from top to bottom.
  3. Validate outputs before moving to the next step.
  4. Capture blockers and fallback path if any step fails.
  1. 识别任务触发条件和预期输出。
  2. 从上到下遵循此Skill中的工作流步骤。
  3. 进入下一步前验证输出内容。
  4. 记录阻塞点及任何步骤失败时的回退方案。

Examples

示例

  • Example: Apply this skill to a small scope first, then scale to full scope after validation passes.
  • 示例：先在小范围内应用此Skill，验证通过后再扩展到完整范围。

Best practices

最佳实践

  • Keep outputs deterministic and auditable.
  • Prefer small reversible changes over broad risky edits.
  • Record assumptions explicitly.
  • 保持输出可确定且可审计。
  • 优先选择小型可逆变更，而非大范围高风险修改。
  • 明确记录假设条件。

References

参考资料

  • Project standards: 
    .agent-skills/skill-standardization/SKILL.md
  • Validator script: 
    .agent-skills/skill-standardization/scripts/validate_skill.sh
  • 项目标准：
    .agent-skills/skill-standardization/SKILL.md
  • 验证脚本：
    .agent-skills/skill-standardization/scripts/validate_skill.sh