Back to AI library

Skill

User stories

Turn a feature description into testable user stories with this AI skill. Use it when defining a new feature or enhancement to prepare for estimation and development.

Open this AI skill

About this AI skill

The User stories skill is pre-built for Elle (the AI assistant in Aha! software) and breaks a feature into stories that each deliver usable behavior. Elle reviews the feature description, linked ideas, and existing requirements, using persona records when available to write each story as "As a [persona], I want [action] so that [outcome]." It outputs stories with testable acceptance criteria, explicit dependencies, and a suggested sequence, along with assumptions and open questions for your team to resolve.

The full User stories skill, as Elle uses it:

# User stories

Use when defining a new feature or enhancement, to turn a description into stories engineering can estimate and test.

## Definitions

Use these meanings consistently in every step.

- **Feature:** The feature record being broken down, or the feature whose record link the user pasted into the chat
- **User story:** One unit of value stated as a role, an action, and an outcome, small enough to build and test on its own
- **Persona:** A persona record in the workspace, used as the role in each story
- **Acceptance criteria:** The conditions that make a story complete, written so they can be judged without interpretation
- **Vertical slice:** A story that delivers usable behavior end to end, rather than a layer of the implementation

## Workflow

1. Read the feature, its description, its linked ideas, and any existing requirements. Linked ideas carry the customer language that makes stories concrete.
2. Identify the personas involved. Use persona records when they exist. When none exist, name the role in one line and mark it as an assumption.
3. Break the feature into vertical slices. Each story delivers behavior a person can use, not a layer such as the schema or the endpoint.
4. Write each story as "As a <persona>, I want <action> so that <outcome>." The outcome states the benefit, not a restatement of the action.
5. Write acceptance criteria for each story. Cover the primary path, the boundaries, and the permission levels that apply.
6. Sequence the stories. Name which ones are prerequisites for others.
7. Flag anything the feature does not answer, and mark assumptions rather than resolving them silently

## Rules

- If the feature is missing or too thin to break down, ask short follow-up questions before drafting
- Every story is independently valuable. A story that cannot ship on its own is a task, and should be folded into the story it serves.
- The "so that" clause states a benefit. If it restates the action, the story needs rework.
- Acceptance criteria are testable. Avoid "works well" and "is intuitive."
- Reference the feature and any linked ideas by reference number and name
- Do not create requirement records. Present the stories and let the user apply them.
- Headers use sentence case. No em dashes, en dashes, or curly quotes.

## Output

```
## Stories  
### <story title>  
As a <persona>, I want <action> so that <outcome>.  
  
\*\*Acceptance criteria\*\*  
- <condition>  
  
\*\*Depends on:\*\* <story or none>  
  
## Sequence  
1. <story title, and why it comes first>  
  
## Open questions  
- <what the feature does not answer>
```

## Quality checks

- Every story is a vertical slice that could ship on its own
- No "so that" clause restates its action
- Every acceptance criterion can be judged without interpretation
- Dependencies between stories are stated rather than implied by order

Try this AI skill now

Open the User stories skill in Aha! Roadmaps to break your feature into stories engineering can estimate and test.

Open this AI skill

About Elle

Elle , the AI assistant in Aha! software, helps product teams accelerate product work by creating content, analyzing records, and updating plans using information in their account. The AI prompt library offers pre-built skills and tasks for Elle that are tuned for product development work.