mehdibargach/claude-code-pm-skills/user-stories
Claude Code and agent skill by mehdibargach/claude-code-pm-skills
- community
Checking that the SKILL.md file is still in the repository.
Turn a feature description into well-structured user stories with acceptance criteria, edge cases, and dependencies.
Install
npx vskill@latest install mehdibargach/claude-code-pm-skills/user-storiesSKILL.md
User Story Generator
Turn a feature description into a complete set of user stories ready for sprint planning. Each story is independently deliverable with testable acceptance criteria.
Process
- Read and analyze the feature description.
- Identify the epic and break it into independently deliverable user stories.
- For each story, write acceptance criteria using Given/When/Then format.
- Identify edge cases and unhappy paths for each story.
- Map dependencies between stories and to external systems.
- Define what is explicitly out of scope.
- Save the output to a file in the current working directory as
stories-[feature-name].md.
Output Format
Epic Summary
- Epic name
- Goal (one sentence — what does this epic achieve for the user?)
- Context (why now, what triggered this work)
User Stories
For each story:
Story [number]: [short title]
Story: As a [specific user type], I want [concrete action], so that [measurable or observable benefit].
Priority: Must-have / Should-have / Nice-to-have
Acceptance Criteria:
- Given [precondition], When [action], Then [expected result]
- Given [precondition], When [action], Then [expected result]
Edge Cases:
- What happens when [unusual condition]?
- What happens when [error condition]?
- What happens when [boundary condition]?
Notes: Any implementation hints or context the team needs.
Dependencies
- Between stories (which stories must be done before others)
- External dependencies (APIs, services, teams, approvals)
- Technical prerequisites
Out of Scope
- Features or behaviors explicitly excluded from this epic
- Adjacent work that might come up but belongs to a different epic
Rules
- Each story must be independently deliverable. If a story can't ship without another, either merge them or make the dependency explicit.
- Acceptance criteria must be testable — a QA engineer should be able to verify each one without asking questions.
- Always include unhappy paths: what happens on failure, timeout, invalid input, missing permissions.
- User stories are written from the user's perspective, not the system's. "The system validates the input" is not a user story.
- Be specific about the user type. "As a user" is too vague — "As a workspace admin with billing access" is specific.
- The benefit in "so that" must be real. "So that I can use the feature" is circular. "So that I can onboard new team members without filing a support ticket" is real.
- If the feature description is too vague, list clarifying questions before writing stories.
- Include story sizing hints (S/M/L) only if enough context is available to estimate.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/user-stories/SKILL.md
Popularity
- 7-day trend score
- 5
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/mehdibargach/claude-code-pm-skills/user-stories)