Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →tencentblueking/tapd-iteration-analysis
迭代执行流水线需求分析阶段。通过 TAPD MCP stories_get 拉取迭代中所有需求详情， 将 description 字段（完整 Markdown 内容）直接保存为需求文档，基于 parent_id 字段自动识别父子关系和独立需求，从需求文档的"依赖关系"章节提取显式依赖进行 拓扑排序，确定实现顺序，更新迭代状态。
Passed 12 of 20 test cases with the skill, and 4 of 20 without it.
and 7 more in the full report
9 fixed5 passed either way9 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
When saving `iteration-state.json` at the conclusion of story analysis, what exact value should be set for the top-level `status` property?
| Checked | Without skill | With skill |
|---|---|---|
| Sets status field in iteration-state.json to analyzed | Missed | Passed |
The instructions your model reads when the skill loads.
iteration-state.json 已存在且 status 为 initializediteration_id、workspace_id、owner在迭代目录下创建 .tmp/ 用于存放需求原始信息。
Linux / macOS:
mkdir -p "specs/${VERSION}/.tmp"
Windows (PowerShell):
New-Item -ItemType Directory -Force -Path "specs\$VERSION\.tmp" | Out-Null
通过 TAPD MCP stories_get 获取迭代中所有需求并识别层级关系。
调用 stories_get，传入 workspace_id 和 iteration_id，获取本迭代中所有需求详情。
注意设置 limit 为足够大的值（如 200）以确保获取全部需求，必要时翻页处理。
返回结果中每个需求包含以下关键字段：
id：需求长 ID（19 位）name：需求标题description：需求详细描述，是包含完整信息的 Markdown 格式内容parent_id：父需求长 ID（无父需求时为空或 "0"）status、priority、owner 等test cases passed, vs 4 / 20 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.