groove-utilities-onboard

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

groove-utilities-onboard

groove-utilities-onboard

Generate a
GROOVE.md
file at the project root — a concise onboarding guide for contributors joining a project that uses groove. Also optionally appends a groove section to
CONTRIBUTING.md
if it exists.
在项目根目录生成
GROOVE.md
文件——这是为加入使用groove的项目的贡献者准备的简洁上手指南。如果项目存在
CONTRIBUTING.md
,还可以选择在该文件中追加groove相关章节。

Outcome

效果

New contributors understand how groove works in this project: which commands to run, where logs live, and what the compound loop expects of them.
新贡献者能够理解groove在本项目中的工作方式:需要运行哪些命令、日志存储位置,以及复合循环对他们的要求。

Acceptance Criteria

验收标准

  • GROOVE.md
    exists at the project root with project-specific config values substituted
  • If
    CONTRIBUTING.md
    exists, it contains a "## Using groove" section linking to
    GROOVE.md
  • Content reflects actual configured values (memory path, task backend, specs path)
  • GROOVE.md
    存在于项目根目录,且已替换为项目特定的配置值
  • 如果存在
    CONTRIBUTING.md
    ,其中需包含「## Using groove」章节,且指向
    GROOVE.md
    链接
  • 内容需与实际配置值(内存路径、任务后端、规范路径)一致

Steps

步骤

  1. Read
    tasks:
    ,
    memory:
    ,
    specs:
    ,
    git.*
    from
    .groove/index.md
  2. Ask: "Any project-specific context to include? (e.g. which tasks to pick up, team conventions) — enter to skip"
  3. Write
    GROOVE.md
    from the template below, substituting live config values
  4. If
    CONTRIBUTING.md
    exists and does not already contain
    <!-- groove:onboard -->
    :
    • Append the following section:
      markdown
      <!-- groove:onboard -->
      ## Using groove
      This project uses [groove](https://github.com/andreadellacorte/groove) for AI-assisted engineering workflow. See [GROOVE.md](./GROOVE.md) for setup and commands.
      <!-- groove:onboard:end -->
  5. Report: "GROOVE.md written" and whether CONTRIBUTING.md was updated
  1. .groove/index.md
    中读取
    tasks:
    memory:
    specs:
    git.*
    配置项
  2. 询问:「是否需要加入项目专属上下文?例如可承接的任务类型、团队约定等,按回车跳过」
  3. 基于下方模板生成
    GROOVE.md
    ,替换为实际的配置值
  4. 如果
    CONTRIBUTING.md
    存在且未包含
    <!-- groove:onboard -->
    标记:
    • 追加以下章节:
      markdown
      <!-- groove:onboard -->
      ## Using groove
      This project uses [groove](https://github.com/andreadellacorte/groove) for AI-assisted engineering workflow. See [GROOVE.md](./GROOVE.md) for setup and commands.
      <!-- groove:onboard:end -->
  5. 反馈:「GROOVE.md已写入」以及是否更新了CONTRIBUTING.md

GROOVE.md template

GROOVE.md模板

markdown
undefined
markdown
undefined

Groove Workflow

Groove Workflow

This project uses groove — an AI-assisted engineering workflow companion.
本项目使用groove——一款AI辅助工程工作流助手。

Quick start

快速上手

bash
npx skills add andreadellacorte/groove
/groove-admin-install
Then start every session with:
/groove-utilities-prime
bash
npx skills add andreadellacorte/groove
/groove-admin-install
之后每次开启工作会话时运行:
/groove-utilities-prime

Daily workflow

日常工作流

/groove-daily-start     — review yesterday, load tasks, set agenda
/groove-daily-end       — write memory, commit logs
/groove-daily-start     —— 回顾昨日工作,加载任务,制定日程
/groove-daily-end       —— 写入记忆内容,提交日志

Compound loop (for any feature or fix)

复合循环(适用于所有功能开发或问题修复场景)

/groove-work-brainstorm — clarify scope
/groove-work-plan       — research and plan
/groove-work-exec       — implement
/groove-work-review     — evaluate output
/groove-work-compound   — capture lessons
/groove-work-brainstorm —— 明确范围
/groove-work-plan       —— 调研与规划
/groove-work-exec       —— 代码实现
/groove-work-review     —— 产出评估
/groove-work-compound   —— 沉淀经验

Config

配置

KeyValue
Task backend
<tasks>
Memory path
<memory>
Specs path
<specs or (default: <memory>/specs/)>
Git strategy (memory)
<git.memory>
任务后端
<tasks>
内存路径
<memory>
规范路径
<specs or (default: <memory>/specs/)>
Git策略(记忆)
<git.memory>

Conventions

约定

  • Stage tasks are named
    YYYY-MM-DD, <Stage>
    — no numbers
  • Task completion requires a "Summary of Changes" in the task body before marking done
  • Archive is always user-triggered — never automatic
  • 阶段任务命名格式为
    YYYY-MM-DD, <Stage>
    ——无需加数字
  • 任务完成前需在任务正文中填写「变更总结」,再标记为完成
  • 归档操作始终由用户触发——永不自动执行

Where things live

文件存储位置

  • Config:
    .groove/index.md
  • Daily logs:
    <memory>daily/
  • Learned insights:
    <memory>learned/
  • Specs:
    <specs or (default: <memory>/specs/)>
  • Hooks:
    .groove/hooks/
    (start.md, end.md)
<custom-context> </custom-context> ```
  • 配置
    .groove/index.md
  • 每日日志
    <memory>daily/
  • 经验沉淀
    <memory>learned/
  • 规范文档
    <specs or (default: <memory>/specs/)>
  • 钩子
    .groove/hooks/
    (start.md、end.md)
<custom-context> </custom-context> ```

Constraints

约束条件

  • Read
    .groove/index.md
    and substitute all
    <placeholder>
    values before writing
  • If
    GROOVE.md
    already exists: ask "GROOVE.md exists — overwrite, update, or skip?" before touching it
  • The
    <custom-context>
    block is replaced with user-provided context or removed if none
  • Do not create
    CONTRIBUTING.md
    if it doesn't exist — only append to existing files
  • GROOVE.md
    should be short enough to read in 2 minutes
  • 写入前需读取
    .groove/index.md
    ,替换所有
    <placeholder>
    占位符
  • 如果
    GROOVE.md
    已存在:操作前先询问「GROOVE.md已存在——覆盖、更新还是跳过?」
  • <custom-context>
    区块会替换为用户提供的上下文,若无用户输入则移除该区块
  • CONTRIBUTING.md
    不存在则不要创建,仅对已有文件进行追加操作
  • GROOVE.md
    的内容长度应控制在2分钟可读完的范围内