Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →tencentblueking/tapd-iteration-runner
TAPD 迭代调度器——批量开发一个迭代中的全部需求。自动完成环境初始化、 需求依赖分析、逐需求调度 pipeline 实现、迭代汇总报告四段编排。
Passed 17 of 22 test cases with the skill, and 6 of 22 without it.
and 11 more in the full report
12 fixed6 passed either way5 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
A story pipeline exits and leaves unformatted open questions in specs/v1.2.0/889900/questions.md. After collecting user answers and writing them to questions.md, what action parameter does the runner issue?
| Checked | Without skill | With skill |
|---|---|---|
| Selects answer as action after recording user answers in questions.md. | Missed | Passed |
The instructions your model reads when the skill loads.
本 skill 负责迭代级编排：建分支、拉需求、依赖排序、依次调度每个需求的 pipeline、迭代收尾。
runner 不知道的事：
这些全部由 tapd-story-pipeline 承担。runner 在自己的主上下文中内联加载并执行
tapd-story-pipeline/SKILL.md，仅根据 meta.yaml 与 questions.md 做决策。
项目根目录下的 project.json 提供默认配置：
{
"workspace_id": "对应的 TAPD 工作空间 ID",
"owner": "开发者 ID"
}
取值优先级（适用于 workspace_id 和 owner）：
project.json 中的配置 → 次优先owner）→ 再次iteration_id 无默认值，必须由用户提供或通过交互获取。
用户在发起迭代时可指定 agent 工具名称（如 agent / claude / cursor），存入
test cases passed, vs 6 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.