Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →lifinance/creating-user-stories
Use when drafting, maintaining, refining, or auditing a structured user-stories catalogue from a product spec + design-review notes + open-questions list. Outputs persona-grouped stories with explicit linkage to unresolved open questions, in a readable format suited for product, engineering, and audit review alike. Trigger on "write user stories for", "draft stories from this spec", "expand the user stories", "add a story for X", "audit the catalogue", "clean up the open questions", "refine the
Passed 21 of 22 test cases with the skill, and 7 of 22 without it.
and 23 more in the full report
15 fixed6 passed either way0 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 15 test cases the skill fixed. Same model, same prompt, with and without the skill.
Organize three user capabilities for our online store platform into persona sections: 1. Admin configures tax rules, 2. Integrator syncs inventory via webhook, 3. Customer views order history. Provide the H2 headings and story lines.
| Checked | Without skill | With skill |
|---|---|---|
| Uses persona H2 headings formatted like ## As an [Org] admin, I want to... | Missed | Passed |
| Prefixes story IDs with persona letters A, I, and U. | Missed | Passed |
The instructions your model reads when the skill loads.
A structured, auditable user-stories catalogue — the kind that feeds a design doc, audit scope, or estimate. Not for one-off tickets or casual feature lists.
Inputs: product spec / PRD, design-review or meeting notes, open-questions list (or create one in parallel), optional comparable-product research.
Output: two pages — a Stories page and a companion Open Questions page. One readable format per page.
❓Q-id. Never invent an answer.*(research-derived)* in the title to distinguish from spec-derived stories.❓Q-id must resolve to a real Q. Phantom Q references erode trust. See "Keeping pages in sync".The catalogue is read by product managers, engineers, auditors, and ops. None of them tolerate dense jargon. Apply these rules to every story body and every open-question body:
Hard rule: whenever a body presents 2+ discrete options (alternative behaviors, alternative mechanisms, alternative scopes), label them (a), (b), (c), … and have the Recommendation explicitly reference the chosen letter.
*What*: **(a)** open to all, **(b)** invite-only, or **(c)** approval-gated.
*Recommendation*: **(a)** — lowest friction for first-time users.
test cases passed, vs 7 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.