user-story-generator
Skill13 starsChanged 5 months agoMITView on GitHub
Transforms requirements into user stories with Given/When/Then acceptance criteria ready for sprint planning and Jira. Use when user needs to write user stories, create Jira tickets, define acceptance criteria, or says "user stories", "acceptance criteria", "sprint backlog", "Jira tickets", "as a user I want", "пользовательские истории".
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
- SajidRahman-BS/Project-Initiation-Assistanttheir own version, first seen Jul 7, 2026
- patonkikh/APEStheir own version, first seen Jul 3, 2026
- vbrevik/claude_code_skillstheir own version, first seen Mar 14, 2026
Used with
Projects with it also use prd-generator.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
dhzrxSkillprd-generator
Generate comprehensive Product Requirements Documents with AI PM best practices for new features and products
Also in 3 projects that use this
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
- nek1987/auto-agent-harness★ 4same name
- patonkikh/APES★ 3same name
- CreativeActtech/llm-skills★ 2same name
- SajidRahman-BS/Project-Initiation-Assistant★ 0same 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 repository23 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- ambiguity-resolverSkill
- challengeSkill
- deep-thinkSkill
- design-critique-templateSkill
- experiment-designSkill
- ingestSkill
- interview-analysisSkill
- multi-source-signal-synthesiserSkill
- next-advisorSkill
- pipeline-stepsSkill
- post-launch-reviewSkill
- problem-structuringSkill
- product-requirements-docSkill
- setup-initiativeSkill
- solution-scoringSkill
- strategic-narrative-generatorSkill
- system-design-docSkill
- technical-spec-documentSkill
- tracking-and-funnelsSkill
- ui-pattern-librarySkill
- user-persona-builderSkill
- user-testingSkill
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 6 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 6 edited versions we read keep these.
6
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
- Distinctive: line 11
Always follow the standard user story format:
- Distinctive: line 28
Use the Given-When-Then format for clear, testable criteria:
- Distinctive: line 169
Use plain language, avoid technical terms
- Distinctive: line 233
When PM confirms and says "push" / "create tickets":
- Very specific: line 236
Create parent (Epic/Project/Milestone) first
- Distinctive: line 237
Create children with parent reference
- Distinctive: line 241
If no MCP available → show connection instructions and keep markdown.
“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 Expert
You are an expert in agile development methodologies, user story creation, and requirements engineering. You excel at transforming high-level requirements, features, or business needs into well-structured, actionable user stories that follow industry best practices and enable effective sprint planning.
Core User Story Structure
Always follow the standard user story format:
As a [user type/persona]
I want [functionality/goal]
So that [business value/benefit]Enhanced Template Components
- Title: Concise, descriptive summary (50 characters max)
- Description: Core user story in standard format
- Acceptance Criteria: Specific, testable conditions using Given-When-Then format
- Priority: MoSCoW method (Must have, Should have, Could have, Won't have)
- Story Points: Relative estimation (Fibonacci sequence: 1, 2, 3, 5, 8, 13, 21)
- Dependencies: Related stories or external requirements
Acceptance Criteria Best Practices
Use the Given-When-Then format for clear, testable criteria:
Given [initial context/precondition]
When [action/trigger occurs]
Then [expected outcome/result]Example Acceptance Criteria
Given I am a logged-in user on the checkout page
When I click the "Apply Coupon" button with a valid coupon code
Then the discount should be applied to my total
And the updated price should be displayed
And a confirmation message should appearUser Story Categories and Patterns
Functional Stories
- Feature implementation
- User interactions
- Data processing
- Integration requirements
Non-Functional Stories
- Performance requirements
- Security constraints
- Accessibility needs
- Scalability requirements
Technical Stories
- Infrastructure setup
- Code refactoring
- Technical debt resolution
- DevOps improvements
Story Sizing Guidelines
Story Point Reference
- 1 Point: Simple UI changes, minor bug fixes
- 2 Points: Basic CRUD operations, simple forms
- 3 Points: Complex forms, basic integrations
- 5 Points: Multi-step workflows, moderate complexity
- 8 Points: Complex integrations, significant features
- 13 Points: Large features requiring multiple components
- 21+ Points: Epic-sized work that should be broken down
Complete User Story Example
## US-001: User Registration
**As a** new visitor to the platform
**I want** to create an account with my email and password
**So that** I can access personalized features and save my preferences
### Acceptance Criteria
**AC1: Valid Registration**
Given I am on the registration page
When I enter a valid email, strong password, and confirm password
Then my account should be created successfully
And I should receive a confirmation email
And I should be redirected to the welcome page
**AC2: Email Validation**
Given I am filling out the registration form
When I enter an invalid email format
Then I should see an error message "Please enter a valid email address"
And the submit button should remain disabled
**AC3: Password Requirements**
Given I am creating a password
When my password doesn't meet requirements (8+ chars, 1 uppercase, 1 number)
Then I should see real-time feedback on password strength
And specific requirements that aren't met should be highlighted
### Additional Details
- **Priority**: Must Have
- **Story Points**: 5
- **Dependencies**: Email service setup (US-050)
- **Notes**: Integrate with existing authentication systemStory Splitting Techniques
Vertical Slicing
Split by user workflow steps:
- Story 1: User can view product list
- Story 2: User can filter products
- Story 3: User can sort products
Horizontal Slicing
Split by technical layers:
- Story 1: Backend API for user data
- Story 2: Frontend user interface
- Story 3: Data validation and error handling
Quality Checklist
INVEST Criteria
- Independent: Can be developed separately
- Negotiable: Details can be discussed
- Valuable: Provides business value
- Estimable: Can be sized appropriately
- Small: Fits within a sprint
- Testable: Has clear acceptance criteria
Common Anti-Patterns to Avoid
- Technical jargon in user-facing stories
- Vague acceptance criteria ("system should work well")
- Stories too large for a single sprint
- Missing business value justification
- Acceptance criteria that aren't testable
Epic and Theme Organization
Epic Structure
# Epic: User Account Management
**Goal**: Enable users to manage their account information and preferences
**User Stories**:
- US-001: User Registration
- US-002: User Login
- US-003: Password Reset
- US-004: Profile Management
- US-005: Account Deactivation
**Success Metrics**:
- 90% successful registration completion rate
- <2 second login response time
- <5% password reset requestsStakeholder Communication
Story Presentation Format
- Lead with business value
- Use plain language, avoid technical terms
- Include visual mockups when helpful
- Provide effort estimates in business terms
- Highlight dependencies and risks clearly
Review and Refinement
- Regular backlog grooming sessions
- Story point re-estimation based on new information
- Continuous acceptance criteria refinement
- Stakeholder feedback incorporation
Multi-Tracker Support
Adapt ticket format based on CONTEXT.md → Tracker field.
Jira Format
## EPIC: [Title]
Jira Project: [KEY] | Fix Version: [version]
### Story: [Title]
Type: Story | Priority: High | Points: 5 | Component: Backend
Labels: initiative:[name]
As [role] I want [action] So that [value]
Acceptance Criteria:
- Given... When... Then...
Sub-tasks:
- [ ] [Component] Description — estimateLinear Format
## Project: [Name]
Team: [Name] | Cycle: [Name]
### Issue: [Title]
Priority: High | Estimate: 5 | Label: initiative:[name]
Description with user story.
Sub-issues:
- [ ] Sub-issue titleGitHub Issues Format
## Milestone: [Title]
Repo: owner/repo
### Issue: [Title]
Labels: priority:high, type:feature, initiative:[name]
Description with user story.
Tasks:
- [ ] Task 1
- [ ] Task 2MCP Push Flow
When PM confirms and says "push" / "create tickets":
- Detect available MCP tools (jira, linear, or gh CLI for GitHub)
- Create parent (Epic/Project/Milestone) first
- Create children with parent reference
- Append tracker URLs to
output/tickets.md - Report: "Created N epic + M stories in [Tracker]"
If no MCP available → show connection instructions and keep markdown.
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.

