user-story-generator
Skill0 starsChanged 4 months agoMITView on GitHub
Converts a PRD or requirement set into epics and INVEST-compliant user stories in As a / I want / So that form, each with testable Given/When/Then acceptance criteria. Groups related stories under epics with stable IDs so they can be tracked and estimated. Use whenever the user needs a backlog, epics, user stories, or acceptance criteria generated from requirements, a PRD, or a feature list.
6 other projects use a version of this.
Adopted by
Most recently taken up by
- imohammadfaraz/claude-skills-for-product-managertheir own version, first seen Nov 1, 2026
- nek1987/auto-agent-harnesstheir own version, first seen Oct 11, 2026
- CreativeActtech/llm-skillstheir own version, first seen Oct 8, 2026
- lenar-amirov/product-pipeline-publictheir own version, first seen Jul 4, 2026
- patonkikh/APEStheir own version, first seen Jul 3, 2026
- vbrevik/claude_code_skillstheir own version, first seen Mar 14, 2026
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- imohammadfaraz/claude-skills-for-product-manager★ 19same name
- lenar-amirov/product-pipeline-public★ 13same name
- nek1987/auto-agent-harness★ 4same name
- patonkikh/APES★ 3same name
- CreativeActtech/llm-skills★ 2same name
- vbrevik/claude_code_skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository6 other files it gives its agents.
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 6 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 36
Every story should be Independent, Negotiable, Valuable, Estimable, Small, and Testable.
“Common” is measured: kept by at least 6 in 10 of the 6 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
User Story Generator
This skill turns functional requirements into a backlog the team can actually pull from: epics that group related work, and user stories small enough to build and test in a sprint, each with acceptance criteria a QA engineer can verify.
Instructions
Step 1: Group requirements into epics
Cluster the PRD's functional requirements into 3–7 epics by capability area (for example: Onboarding, Reordering, Payments, Delivery, Admin). Give each a stable ID (EP-01, EP-02) and a one-line description of the outcome it delivers.
Step 2: Write user stories
For each epic, write stories in this exact form:
As a [persona]
I want [capability]
So that [benefit]Give each story a stable ID (US-01, US-02) and link it to its epic ID. Keep stories small — if a story needs more than a handful of acceptance criteria, split it.
Step 3: Apply INVEST
Every story should be Independent, Negotiable, Valuable, Estimable, Small, and
Testable. See references/story-rules.md for how to check each and how to split
stories that are too big.
Step 4: Write acceptance criteria
For each story, write 2–5 acceptance criteria in Given/When/Then form. These define "done" and become the basis for test cases:
Given [context]
When [action]
Then [observable result]Cover the happy path and the important edge cases (empty state, invalid input, failure of an external dependency).
Step 5: Hand off
Output the structured object below so the estimation stage can consume it.
Output format
Present a readable backlog for humans AND this JSON:
{
"epics": [{"id": "EP-01", "name": "", "description": ""}],
"stories": [
{
"id": "US-01",
"epic_id": "EP-01",
"as_a": "",
"i_want": "",
"so_that": "",
"acceptance_criteria": ["Given ... When ... Then ..."]
}
]
}Example
Epic: EP-02 Reordering — "Let customers reorder a previous prescription."
Story US-04:
As a returning customer
I want to reorder a prescription from my history
So that I do not have to re-enter the detailsAcceptance criteria:
- Given I have a past order, When I open my order history, Then I see a "Reorder" action on each past order.
- Given I tap Reorder, When the item is still available, Then it is added to a new cart with the same quantity.
- Given I tap Reorder, When the item is discontinued, Then I see a clear message and a suggested alternative.
Troubleshooting
- Stories are too big (an "epic in disguise"). Split by workflow step, by
data variation, or by happy-path-then-edge-case. See
references/story-rules.md. - Acceptance criteria restate the story. They must be checkable. If QA cannot pass or fail it by observation, rewrite it.
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.

