implement-use-case
Skill0 starsChanged 3 months agoUnlicenseView on GitHub
Implement a use case from the spec/ folder. Use when asked to implement, build, or work on a use case.
In this repository3 other files it gives its agents.
- new-use-caseSkill
- use-case-testsSkill
- visual-verificationSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 29
Follow the use-case-tests workflow and ensure all tests pass before moving on.
- Distinctive: line 32
This step is mandatory: Do not skip it, do not defer it.
- Distinctive: line 34
Follow the visual-verification workflow end-to-end: start the app, navigate every route, take screenshots, and validate the visual …
- Distinctive: line 38
Keep iterating until everything looks and works great.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Use Case Implementation
Implement the use case specified by $ARGUMENTS.
A use case is the unit of work, not a view. A single use case may produce one view, several views, or no UI at all — let the spec drive that, and keep tests grouped per use case as defined by /use-case-tests.
Input
- The use case document itself (in
spec/use-cases/) - Related use cases
- Generic specification files in
spec/ - Any potential images or other resources provided for the use case
Implementation
The following steps are mandatory and sequential. Do not skip or reorder them. Each step must be completed before proceeding to the next.
Step 1: Write the code
- Whenever you are even slightly unsure about Vaadin API usage, component behavior, theme variables, styling, or best practices -- use the Vaadin MCP server to look it up before guessing. Do not rely on memory for Vaadin specifics.
Step 2: Write and run automated tests
- Verify everything that does not depend on visual appearance here first -- main flow, alternative flows, business rules, and services. Use the fast browserless / Vitest /
@SpringBootTestmechanisms; they are far cheaper and faster than driving a browser, so cover as much behaviour as possible this way before touching Playwright. - Follow the use-case-tests workflow and ensure all tests pass before moving on.
Step 3: Visually verify with Playwright MCP
- This step is mandatory. Do not skip it, do not defer it.
- Behaviour is already covered by the automated tests, so use Playwright MCP only to verify what those tests can't: layout, spacing, rendering, and visual appearance.
- Follow the visual-verification workflow end-to-end: start the app, navigate every route, take screenshots, and validate the visual appearance. Don't re-check functional behaviour already covered by Step 2.
- Fix any issues found before moving on.
Step 4: Iterate
- Keep iterating until everything looks and works great. Prefer great results over finishing quickly.
Step 5: Commit
- Once all steps are complete and everything works, create a git commit with the changes.
All steps must be completed before a use case is considered implemented.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

