groove-work-spec

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

groove-work-spec

groove-work-spec

Use $ARGUMENTS as the spec topic if provided.
如果提供了$ARGUMENTS,则将其用作规范主题。

Outcome

产出

A complete outcome spec that defines what to build and how to verify it — the agent determines the procedure.
一份完整的产出规范,定义需要构建的内容以及验证方式——具体流程由Agent决定。

Acceptance Criteria

验收标准

Spec file contains:
  • Overview: What to build and why
  • Decisions: Key technical choices with rationale
  • Implementation Steps: Concrete, ordered steps
  • Edge Cases: Error handling, boundary conditions
规范文件包含:
  • 概述:需要构建的内容及背景原因
  • 决策:核心技术选型及依据
  • 实现步骤:具体的、有序的执行步骤
  • 边界情况:错误处理、边界条件

Constraints

约束

  • Sanitize topic for use as filename — strip path separators, special characters, and traversal patterns (
    ../
    )
  • Read
    memory:
    from
    .groove/index.md
    for base path; save spec to
    <memory>/specs/
  • Ensure
    <memory>/specs/
    exists (create if missing)
  • Research codebase first (use Explore agent)
  • Interview user for decisions, edge cases, testing approach, scope
  • Assess scope: if the work has natural seams (independent components, sequential phases, separable concerns), recommend splitting into a parent spec with child specs
    • Parent spec: Overview of the full feature, links to child specs, execution order if sequential
    • Child specs: Each self-contained with its own Overview, Decisions, Steps, Edge Cases
    • Naming:
      <topic>.md
      for single specs,
      <topic>/index.md
      +
      <topic>/01-<part>.md
      for split specs
    • User decides: Present the split recommendation with rationale, user confirms or overrides
  • Write spec in isolated context (use general-purpose agent)
  • Verify all required sections exist before completing
  • Reference actual codebase patterns, not generic advice
  • 清理用作文件名的主题——移除路径分隔符、特殊字符和路径遍历模式(
    ../
  • .groove/index.md
    中读取
    memory:
    作为基础路径;将规范保存到
    <memory>/specs/
    路径下
  • 确保
    <memory>/specs/
    路径存在(若缺失则创建)
  • 首先调研代码库(使用Explore Agent)
  • 向用户询问确认决策、边界情况、测试方案、项目范围
  • 评估范围:如果工作存在天然拆分点(独立组件、连续阶段、可分离关注点),建议拆分为父规范和多个子规范
    • 父规范:完整功能概述、子规范链接,若为顺序执行还需包含执行顺序
    • 子规范:每个子规范独立完备,包含自身的概述、决策、步骤、边界情况
    • 命名规则:单个规范使用
      <topic>.md
      命名,拆分后的规范使用
      <topic>/index.md
      +
      <topic>/01-<part>.md
      命名
    • 用户决策:展示拆分建议及依据,由用户确认或调整
  • 在隔离上下文下编写规范(使用General-purpose Agent)
  • 完成前确认所有必填章节均已存在
  • 引用实际代码库模式,而非通用建议

Quality Signals

质量信号

  • Decisions reference real code patterns
  • Steps include actual file paths and function names
  • Edge cases reflect discovered constraints
  • 决策参考实际代码模式
  • 步骤包含实际文件路径和函数名
  • 边界情况反映已发现的约束