Challenges and decomposes a broad product problem into ordered Valuable/Visible/Vertical stories with rough effort hypotheses. Use when the parent problem, candidate stories, or learning priority are unresolved. Writes one non-executable seed.
The English summary is being prepared. Showing the original description.
Run score Not tested
See how to installReview the instructions the agent will receive before you install.
Produce one human-reviewed seed containing a clear parent problem and ordered candidate stories. Do not perform technical design or write an executable plan.
Use this skill when the beneficiary, problem, desired effect, or value is unclear; a request prescribes a solution without establishing why; several outcomes or story boundaries must be chosen; or the first increment's value or learning priority is disputed.
For selected-story goal, scope, and examples, use dough-story-refinement. Hand off one understood story to the project's execution-planning workflow only when the user explicitly requests planning. A seed or backlog selection does not authorize execution.
Read the user's instructions and repository guidance to identify:
Resolve project paths from this project, not this skill's location. If context or a linked dependency needed for the current action is unavailable, name it, ask only for the missing information, and stop the affected activity before writing.
Read and follow problem decomposition to establish human-owned framing decisions, challenge alternatives, and select, size, and order stories. Before writing to the seed, establish or reuse the required workspace under preparation workspace; this discussion and decomposition work needs no workspace on its own. Then use seed format to update the supplied seed or create a new seed in that workspace. After a write that leaves a candidate with a recorded identity in its canonical home, apply record preparation facts. Leave the seed there for review by default; this skill commits or publishes it only through that reference's disposition.
Report the seed path, recommended first story, rejected simpler alternative, effort distribution, and open decisions. Apply that reference's keep or discard decision, then close or retain the workspace, when this session ends. After writing the seed, end with:
## STORY DECOMPOSITION WRITTEN
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
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.
The English summary is being prepared. Showing the original description.
Backend Java production code, Spring Boot controllers/services/repositories, controller return values, imports, schema ERD pointer. Use when editing backend production Java.
The English summary is being prepared. Showing the original description.
Backend Java tests, controller-level stable-boundary tests, JUnit, @Nested, MakeMe builders, @Transactional, parameterized tests. Use when writing or changing backend JUnit tests.
The English summary is being prepared. Showing the original description.
related to donut CLI. Use when working on donut-cli.
The English summary is being prepared. Showing the original description.
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.
The English summary is being prepared. Showing the original description.
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.
The English summary is being prepared. Showing the original description.