Skill · Business & Consulting

User Story Writer

Eliminate tautological user stories. Generate INVEST-compliant stories with observable acceptance criteria and edge cases. Install in 30 seconds.

Category: Business & Consulting
Deliverable: 1 .skill bundle
Outputs: —
Last updated: 13 Jun 2026

$8.99 One-time · lifetime updates

Get it on Agensi

Works in Claude Pro, Team, and Enterprise
Lifetime access to updates
Refundable for 30 days via the marketplace

Or get a free skill every month. Subscribers get one curated skill, free, every 1st. Pick yours →

StrategistKit Affiliate. Purchase happens on the marketplace, which handles payment, delivery and refunds.

Overview

What User Story Writer does.

User Story Writer takes a feature description and the user types involved, then applies INVEST criteria from the inside out: it sharpens vague personas into role-specific actors, rewrites acceptance criteria as observable outcomes a tester can verify without reading source code, surfaces unhappy paths and edge cases as explicit Given/When/Then scenarios, and flags stories too large to estimate reliably — returning a split suggestion alongside the stories themselves.

A typical input: 'We're adding a document export feature to our SaaS project-management tool. Users are project managers who own the workspace and team members who have read-only access. We need stories for our next sprint refinement.' The skill distinguishes between the two permission levels, writes separate stories for each role where behaviour diverges, and calls out edge cases like exporting an empty project or losing connection mid-export.

Example output excerpt — one story from that session: Story: As a read-only team member, I want to export a filtered view of project tasks so that I can share a snapshot with external stakeholders without granting them tool access. Acceptance criteria: – Given I have applied a status filter, when I trigger export, then the downloaded file contains only tasks matching that filter — not the full project. – Given the export exceeds 500 rows, when I trigger export, then I receive a warning before download begins. – Given I have no tasks visible under my current filter, when I trigger export, then the export button is disabled and a tooltip explains why. Split flag: 'CSV export' and 'PDF export' are independent value seams — split into two stories before pointing estimation.

Who it's for

Product managers and agile delivery leads who run refinement sessions and are tired of stories that bounce back from QA or sit unestimated because the acceptance criteria describe UI decisions rather than verifiable outcomes. Also useful for solo product owners who write their own backlog and want a forcing function against scope creep.

How it works

Three steps. About two minutes.

Install

Add the .skill file to your Claude app. ~10 seconds.

Run it on your work

Invoke the skill and paste in your material.

Apply the output

Review, keep what works, and use it.

In depth

Why a Claude skill beats a prompt template.

A copy-paste prompt runs one static pass and stops. A skill is a bundled program — instructions, examples, and a workflow Claude runs as a unit: it asks for the right input, applies the same pattern every time, and returns the structured outputs above.

FAQ

Common questions.

What do I need to provide for the skill to produce useful stories?

Describe the feature, identify the distinct user types involved, and mention any known constraints such as permission levels, platform, or integration points. The more specific the persona and the trigger for the action, the sharper the output — but the skill will ask clarifying questions if critical context is missing.

Does the skill handle epics, or only individual stories?

It handles both. If you describe an epic-sized piece of work, the skill identifies value seams and returns a set of independently shippable stories with a rationale for each split, rather than one monolithic story that can't be estimated.

What format does the output arrive in?

Each story is returned with its persona statement, goal, and rationale, followed by Given/When/Then acceptance criteria covering the happy path and at least the most likely failure or edge cases. The format is copy-paste ready for tools like Jira or Linear, and the skill adapts structure if you specify a different target format.

Will it work for non-software products — for example, internal process flows or service design?

Yes. The INVEST framework and Given/When/Then structure apply to any context where a specific actor needs to accomplish a goal with a verifiable outcome. Describe your actor and the process step; the skill does not assume a software interface unless you specify one.

How does it handle stories where multiple roles have different permissions for the same feature?

It writes distinct stories per role when behaviour diverges, rather than a single story that tries to cover all cases with conditional language. This keeps each story independently testable and prevents acceptance criteria from becoming branching logic.