writing-user-stories
Skill11 starsChanged 8 days agoMITView on GitHub
Use when asked to write user stories, define requirements, break a feature into stories, or draft product/feature issues - produces stories in "As a [persona], I want [action], so that [benefit]" format with Given-When-Then acceptance criteria and an INVEST quality checklist
In this repository31 other files it gives its agents.
- architecture-diagrammingSkill
- at-risk-detectionSkill
- build-faq-from-issuesSkill
- context-aware-questionsSkill
- daily-planning-ritualSkill
- dependency-mappingSkill
- estimating-change-footprintSkill
- estimating-work-itemsSkill
- idea-to-designSkill
- issue-decompositionSkill
- markdown-formattingSkill
- mermaid-diagramsSkill
- prepare-meeting-agendaSkill
- project-analysisSkill
- project-planningSkill
- repairing-project-setupSkill
- requirement-elicitationSkill
- research-topic-summarizeSkill
- setting-up-a-projectSkill
- sgai-goalSkill
- stakeholder-trackingSkill
- stakeholder-updatesSkill
- summarize-conversation-threadSkill
- supervising-conductor-workspacesSkill
- supervising-paradev-workspacesSkill
- timeline-planningSkill
- triage-new-issuesSkill
- working-on-an-epicSkill
- working-on-an-issueSkill
- writing-product-specsSkill
- writing-verification-plansSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 38
Add clear, testable conditions in Given-When-Then format:
- Distinctive: line 51
Before finalizing a story, verify it is:
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Writing User Stories
Overview
Core principle: User stories are a formulaic way of expressing user requirements. Every story identifies the persona of the actor, what they want to do, and the benefit they hope to gain.
When to Use
- You are asked to write a user story
- You are writing GitHub issues for product work or feature requirements
- You are asked to plan a feature and express its requirements as stories
Not for: full product specifications — use the writing-product-specs skill instead.
Story Format
As a [persona]
I want [action or feature]
So that [benefit or value]Example:
As a non-technical stakeholder
I want to understand what changed in a release without reading code diffs
So that I can communicate updates to customers effectivelyAcceptance Criteria
Add clear, testable conditions in Given-When-Then format:
Given I am viewing the project dashboard
When I click the "Filter" button
Then I see a dropdown with all available labels
And the issue list updates to show only matching issuesStories without acceptance criteria lead to scope creep, unclear completion, and misaligned expectations.
Quality Checklist (INVEST)
Before finalizing a story, verify it is:
- Independent - Can be developed separately from other stories
- Negotiable - Details can be discussed and refined
- Valuable - Delivers clear value to users or business
- Estimable - You can say what done looks like; size it with the
estimating-work-itemsskill - Small - 8 points or less on the powers-of-two scale; anything bigger is an epic to decompose
- Testable - Success criteria are clear and verifiable
Common Pitfalls
Too technical:
- ❌ "Add a REST endpoint at /api/v2/users with authentication"
- ✅ "As an admin, I want to manage user accounts via API, so that I can automate user provisioning"
Too vague:
- ❌ "Make the dashboard better"
- ✅ "As a manager, I want to see project velocity trends, so that I can forecast delivery dates"
Missing the "why":
- ❌ "As a user, I want dark mode"
- ✅ "As a user, I want dark mode, so that I can reduce eye strain during evening work sessions"
Optional Sections
For stories destined to become GitHub issues, add sections as needed: Dependencies (what must complete first), Open Questions (decisions still needed), Technical Notes (implementation guidance), and Design Assets (mockups, wireframes).
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.

