spec-to-backlog
仓库创建 2026年6月21日最近提交 21 天前SkillHot 收录 21 天前
▸ 精选理由
将高层设计自动拆分成可追踪工单,适合产品与开发衔接
▸ 风险提示
需要配置 atl CLI,创建/链接工单会更改 Jira 数据,需权限与确认
这个 Skill 做什么
把 Confluence 规格页拆成 Epic 与可执行的 Jira 子任务并创建
把 Confluence 上的规格或设计文档拆成一个 Epic 加上可执行的子任务,先给出建议的拆分方案、等待你审批,然后用 atl CLI 先建 Epic、再建并关联子票。特点是强调先提案后批准,绝不会在未获同意时随意创建工单,适合把大需求变成可追踪的 backlog。
▸ 展开 SKILL.md 英文原文
Convert a Confluence specification page into a structured Jira backlog — an Epic plus linked implementation tickets — with the atl CLI. USE WHEN the user asks to break a spec, requirements page, RFC, or design doc into tickets, generate a backlog from a Confluence page, or create an epic with child tasks.
0
Stars
0
Forks
30
仓库内 Skill
+0
7 日增星
安装 / 使用
给你的 Agent 一句话(通用)
帮我安装这个 skill:https://raw.githubusercontent.com/isukharev/atl/main/skills-src/spec-to-backlog/SKILL.md或 curl 直取 SKILL.md
curl -fsSL "https://raw.githubusercontent.com/isukharev/atl/main/skills-src/spec-to-backlog/SKILL.md"SKILL.MD 节选查看完整文件 ↗
# Spec → backlog with `atl`
Read the spec → propose a breakdown → **get approval** → create the Epic
**first**, then children linked to it. `link-epic` needs the Epic to already
exist, so create it first and capture its key. Never create anything before
the user approves the breakdown. Command details live in the `jira` and `confluence`
skills.
**Preflight:** `atl` must be installed and configured. If `command -v atl` fails
or a command exits `7` ("not configured"), run `{{atl.setup_cmd}}` and stop.
## Workflow
### 1. Fetch the spec
```sh
atl conf page get --id <id> --format view
```
Long or multi-section specs: mirror instead —
`atl conf pull --id <id> --into <dir>` and read the genervia SKILL·HOT · 数据来自 GitHub 公开信息 · 原文版权归作者所有