Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →tencentblueking/tapd-story-plan
迭代执行流水线开发计划阶段。基于 spec.md 调用 /speckit.plan 以测试驱动开发模式构建 开发计划、技术调研与数据模型，并在同一 subagent 内就地做文档级合规自检，产出 plan-report.md。 speckit 命令与报告模板详见 ../references/subagent-prompt-template.md §2.2。
Passed 11 of 17 test cases with the skill, and 5 of 17 without it.
and 5 more in the full report
8 fixed7 passed either way8 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
A downstream skill traced an architectural conflict back to the planning phase for requirement #7731, requesting a re-entry that only impacts the plan itself without changing spec requirements. What `target_phase_to_re_enter` string should be recorded in `attempt-2.md`?
| Checked | Without skill | With skill |
|---|---|---|
| Sets target_phase_to_re_enter to plan | Missed | Passed |
The instructions your model reads when the skill loads.
tech-clarified${WORKDIR}/spec.md 已存在references/context-and-meta-template.md 重写当前阶段的 context.md
（白名单包含：spec.md + 项目宪章 + 架构/安全/编码规范引用文档）${WORKDIR}/meta.yaml（读取 attempts）${WORKDIR}/spec.md${WORKDIR}/context.md${WORKDIR}/iteration-patches/attempt-${N}.md（若为回退重入，必读）pipeline 主编排按 ../references/subagent-prompt-template.md §2.2 Plan 模板渲染
SUBAGENT_PROMPT（含 speckit.plan skill + 就地合规自检 + plan-report.md 产出），
通过 Task(subagent_name="tech-lead", ...) 拉起 subagent。
渲染填充：${ID} / ${VERSION} / ${WORK_DIR} / attempts / round；
若 attempts > 1，附上 iteration-patches/attempt-${attempts}.md 摘要。
subagent 内的两段工作（speckit-plan + 就地合规自检）、合规自检 checklist（3 个维度： 完整度 / research 合规 / 项目宪章）、plan-report.md 统一模板、Verdict 判定规则 均在 subagent-prompt-template.md §2.2 中定义，本子 skill 不重复。
在消费 plan-report.md 的 verdict 前，主编排必须确认 plan 产物具备可实施性：
| 检查项 | 通过标准 |
|---|---|
| 技术上下文 | plan.md 明确技术栈、受影响模块与项目结构；未知项已在 research.md 中消除或显式列出 |
| 架构与契约 | 方案描述模块交互和依赖方向；存在外部接口时，contracts/ 或 plan.md 定义了请求、响应及错误行为 |
| 数据模型 | 涉及数据时 data-model.md 定义实体、字段、校验与关系；不涉及时在 plan.md 显式说明 |
| 需求映射 | spec.md 的每个用户场景、功能需求和验收标准均能映射到实现方案或明确标注不适用原因 |
test cases passed, vs 5 / 17 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.