backlog

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Backlog

Backlog 待办项

Create a comprehensive backlog item for work we've explored but decided not to implement now.

为我们已探索但决定暂不实施的工作创建完整的Backlog待办项。

Instructions

操作步骤

Step 1: Gather Context

步骤1：收集上下文

Ask these questions to understand what we're deferring:

What feature/enhancement are we deferring? (brief name)
Why did we explore it? (what problem does it solve)
Why are we deferring? (out of scope, lower priority, needs more info, etc.)
What did we learn? (key findings from exploration)

通过以下问题明确我们要推迟的工作：

我们推迟的是哪项功能/功能增强？（简短名称）
我们为何探索该内容？（它能解决什么问题）
我们为何推迟实施？（超出范围、优先级较低、需要更多信息等）
我们有哪些收获？（探索过程中的关键发现）

Step 2: Determine Category

步骤2：确定分类

Based on the work, select the appropriate category per

backlog/AGENTS.md

plan: Comprehensive design for new features (most common for /backlog)
followup: Post-merge improvements and tech debt
task-list: Collection of related items
ideas: Ideas to explore, not yet developed into actionable plans

根据工作内容，参考

backlog/AGENTS.md

选择合适的分类：

plan（计划）：新功能的完整设计（/backlog目录中最常用的分类）
followup（后续跟进）：合并后的改进工作与技术债务
task-list（任务列表）：相关任务的集合
ideas（创意）：待探索的创意，尚未转化为可执行计划

Step 3: Create Backlog File

步骤3：创建Backlog文件

Create a file at

backlog/{feature}-{category}.md

with this structure:

markdown

---
status: pending
category: {plan|followup|task-list|ideas}
pr: null
branch: null
score: null
retro_summary: null
completed: null
---

在

backlog/{feature}-{category}.md

路径下创建文件，结构如下：

markdown

---
status: pending
category: {plan|followup|task-list|ideas}
pr: null
branch: null
score: null
retro_summary: null
completed: null
---

{Feature Name}

{功能名称}

Problem Statement

问题说明

{1-2 paragraphs explaining why this work matters and what problem it solves}

{1-2个段落，说明这项工作的重要性以及它能解决的问题}

Key Decisions

关键决策

Decision	Choice	Rationale
{decision point}	{what we'd choose}	{why}

决策点	选择方案	理由
{决策点}	{我们的选择}	{理由}

Architecture

架构设计

{ASCII diagram if helpful}

{如有需要可添加ASCII示意图}

Implementation Phases

实施阶段

Phase 1: {Name}

阶段1：{名称}

Files to modify:

```
path/to/file.ts
```
- {what changes}

Files to create:

```
path/to/new-file.ts
```
- {purpose}

Acceptance criteria:

{testable outcome}
{testable outcome}

需修改的文件：

```
path/to/file.ts
```
- {修改内容}

需创建的文件：

```
path/to/new-file.ts
```
- {文件用途}

验收标准：

{可测试的结果}
{可测试的结果}

Phase 2: {Name}

阶段2：{名称}

...

Verification Commands

验证命令

bash

undefined

bash

undefined

Commands to verify the implementation works

用于验证实施效果的命令

undefined

undefined

Rollback Plan

回滚计划

{How to undo if things go wrong}

{如果出现问题，如何撤销实施}

References

参考资料

{Related files, PRs, docs, or external resources}

undefined

{相关文件、PR、文档或外部资源}

undefined

Step 4: Include Research Artifacts

步骤4：纳入探索成果

Incorporate what we learned during exploration:

Code snippets we prototyped or found
Configuration examples
API patterns from existing code
External documentation links

将我们在探索过程中学到的内容纳入文件：

我们原型开发或找到的代码片段
配置示例
现有代码中的API模式
外部文档链接

Step 5: Commit

步骤5：提交代码

Commit the backlog file with message:

chore: add {feature} to backlog

{One sentence on what this enables}

使用以下提交信息提交Backlog文件：

chore: add {feature} to backlog

{一句话说明该待办项的作用}

Quality Checklist

质量检查清单

Before finishing, verify the backlog file:

Has enough context that a fresh session can understand without the original conversation
Includes specific file paths (with line numbers when relevant)
Has verification commands or acceptance criteria
References related code patterns in the codebase
Follows the frontmatter schema from
```
backlog/AGENTS.md
```

完成前，请验证Backlog文件是否满足以下要求：

包含足够的上下文，即使不了解原始对话也能理解内容
包含具体的文件路径（相关时需标注行号）
包含验证命令或验收标准
引用代码库中的相关代码模式
遵循
```
backlog/AGENTS.md
```
中的前置元数据规范

List Backlog Items

查看所有Backlog待办项

To see all backlog items, run:

bash

~/.claude/skills/backlog/scripts/status.sh

要查看所有Backlog待办项，执行以下命令：

bash

~/.claude/skills/backlog/scripts/status.sh

Grooming

Backlog梳理

Detect stale or likely-completed backlog items that were never moved to

done/

bash

~/.claude/skills/backlog/scripts/groom.sh [path/to/backlog]

The script cross-references pending items against git history (PR numbers, branch names, keyword matches) and the filesystem (files that were supposed to be created). It flags items that look done so you can review and close them.

See

references/grooming.md

for the full grooming workflow and checklist.

检测已过时或可能已完成但从未移至

done/

目录的Backlog待办项。

bash

~/.claude/skills/backlog/scripts/groom.sh [path/to/backlog]

该脚本会将待处理项与Git历史记录（PR编号、分支名称、关键词匹配）和文件系统（应创建的文件）进行交叉比对，标记出看起来已完成的项，方便你审核并关闭它们。

完整的梳理工作流和检查清单请查看

references/grooming.md

。

Example Usage

使用示例

User: /backlog
Claude: I'll help capture the work we explored for future implementation.

What feature/enhancement are we deferring?
> R2 storage for docs assets

Why did we explore it?
> Docs screenshots are gitignored, wanted persistent storage without git bloat

Why are we deferring?
> Works fine locally for now, R2 adds complexity we don't need yet

What did we learn?
> R2 bindings in wrangler.jsonc, Worker route pattern, wrangler CLI for uploads

[Creates backlog/docs-r2-storage-plan.md with full implementation plan]

User: /backlog
Claude: 我将帮你记录我们已探索的工作，以便未来实施。

我们推迟的是哪项功能/功能增强？
> R2 storage for docs assets

我们为何探索该内容？
> 文档截图被git忽略，我们需要无需增加Git仓库体积的持久化存储

我们为何推迟实施？
> 目前本地运行正常，R2会增加我们暂时不需要的复杂度

我们有哪些收获？
> wrangler.jsonc中的R2绑定、Worker路由模式、用于上传的wrangler CLI

[创建包含完整实施计划的backlog/docs-r2-storage-plan.md文件]

Setting Up backlog/ Directory

配置backlog/目录

See

references/agents-schema.md

for the full directory setup and frontmatter schema.

完整的目录配置和前置元数据规范请查看

references/agents-schema.md

。

References

参考资料

```
references/agents-schema.md
```
— Frontmatter schema, categories, lifecycle, directory setup
```
references/grooming.md
```
— Backlog maintenance workflow and checklist
```
references/README.md
```
— Background, design philosophy, and related projects

```
references/agents-schema.md
```
— 前置元数据规范、分类、生命周期、目录配置
```
references/grooming.md
```
— Backlog维护工作流和检查清单
```
references/README.md
```
— 背景信息、设计理念及相关项目