backend
免费Backend Java — Spring Boot controllers/services, JUnit controller tests, MakeMe. Read this first for any backend work. Use when working on the Java Spring backend.
中文简介正在准备中。当前显示原文说明。
Resplits a large story after slice-plan refinement into smaller stories and mapped slice plans. Use when resplitting is requested, including after a more-than-15-slices recommendation. Leaves the first story and plan refined; later plans await story refinement and backlog priorities are reconsidered.
中文简介正在准备中。当前显示原文说明。
实测评分 未实测
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Replace one large story with smaller stories and partition its refined slice plan to match. A recommendation from slice-plan refinement alone does not authorize this workflow. Do not implement product code.
Require the original story and seed, its refined slice plan, and this project's seed, anchor, plan-location, and lifecycle conventions. Identify completed work, evidence, current decisions, and any existing backlog entry. Resolve backlog context when the original is queued or queueing is requested. If required context or a linked skill is unavailable, name what is missing and stop the affected activity before writing.
Use dough-story-decomposition to decompose the original outcome and order the smaller stories. Supply the original story's established decisions and learning from refinement; reuse answered questions. Keep decomposition's seed non-executable and perform the plan mapping below only after story boundaries and order are resolved.
Split by useful outcomes, not by distributing slices into equal-sized groups. Account for the original scope across the new stories; surface proposed scope removal or changed outcomes for human resolution. Preserve unrelated siblings and stable links. Retain a trace from the original story to its replacements using this project's lifecycle conventions, so it is not left as competing work or recorded as delivered merely because it was split.
Map every original slice and its promises to the story it serves. Preserve completed work, compatible evidence, overrun history, and still-relevant decisions. Split or realign slices spanning story boundaries; do not duplicate implementation work or proof ownership. Record genuine dependencies explicitly.
Partition the original plan into one plan per new story using this project's locations. Reuse the original plan for the first story where the lifecycle allows; otherwise retain a replacement trace and retire the competing plan. Link every plan to its canonical story and account for every original slice.
For the first story in the resolved order:
For every later story, retain the mapped slices as provisional planning input.
Mark its plan explicitly: awaiting story refinement — not ready for slice-plan refinement or execution, using equivalent project status fields where supplied.
Record that resumption requires dough-story-refinement to clarify the mapped
story's goal, scope, and examples, followed by plan realignment before slice-plan
refinement or execution. Old slice readiness does not override this hold.
If the original story is queued, use dough-product-backlog to replace its entry and reassess the selected smaller stories against the whole backlog. The highest-priority replacement may retain the original position when justified. Other replacements do not inherit that position or automatically follow it; apply the backlog skill's ranking rules individually. Leave unselected candidates in their seed and explain placement or deferral. If the original was not queued, do not queue replacements unless requested.
Report the replacement story links, original-to-new slice mapping, first plan's refinement and readiness result, later plans' holds and resumption steps, backlog placement rationale, and unresolved decisions. Resplitting does not authorize execution, commit, or push. End a completed resplit with:
## STORY RESPLIT
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Backend Java — Spring Boot controllers/services, JUnit controller tests, MakeMe. Read this first for any backend work. Use when working on the Java Spring backend.
中文简介正在准备中。当前显示原文说明。
Backend Java production code, Spring Boot controllers/services/repositories, controller return values, imports, schema ERD pointer. Use when editing backend production Java.
中文简介正在准备中。当前显示原文说明。
Backend Java tests, controller-level stable-boundary tests, JUnit, @Nested, MakeMe builders, @Transactional, parameterized tests. Use when writing or changing backend JUnit tests.
中文简介正在准备中。当前显示原文说明。
related to donut CLI. Use when working on donut-cli.
中文简介正在准备中。当前显示原文说明。
Set up and run the Donut dev environment on Cursor Cloud VM (no Nix). Use when working on Cloud VM, running tests on Cloud VM, or encountering command errors related to missing nix. Triggers on: cloud VM, cloud agent, no nix available, /workspace path.
中文简介正在准备中。当前显示原文说明。
Regenerate docs/database-erd.md from MySQL information_schema (Mermaid ERD: foreign keys and key columns). Use after Flyway schema changes, new migrations, or when the diagram is stale. Triggers on: database ERD, database-erd.md, export_database_erd, schema diagram, ER diagram after migration.
中文简介正在准备中。当前显示原文说明。