write-stories — Claude Code command: stories and setup
write-stories is a Claude Code command that turns a feature brief or PRD into backlog items with acceptance criteria. Choose user stories, job stories, or WWA.
MIT ★ 28,211 updated 2026-10-16
/plugin marketplace add phuryn/pm-skills
/plugin install pm-execution@pm-skillsWhat write-stories does
Pass in a feature description or PRD and choose a format. The command splits the work into independent backlog items, orders them by priority and dependencies, and adds acceptance criteria. It can also flag items that need design input or technical investigation. The output is Markdown.
User stories are checked against INVEST; job stories focus on situation and motivation; WWA connects strategic context, deliverable, and acceptance criteria. The workflow aims for 5–15 stories, with 3–5 criteria per story. For a larger feature, it suggests grouping work into epics or phases. If you leave out the format, the command asks which one your team uses and recommends user stories when you’re unsure. Vague feature briefs may need clarification before the breakdown is useful.
What it helps with
- split a feature brief into independent backlog items
- write testable acceptance criteria for each story
- choose a story format for the team’s workflow
- order items by priority and dependencies
- flag work that needs design input or a technical spike
Example prompts for the agent
- Break the task-deadline notification system into job stories.
- Turn the PDF and CSV report export feature into user stories.
- Break the mobile app’s dark mode into WWA items.
How to install write-stories
1Plugin marketplace
/plugin marketplace add phuryn/pm-skills/plugin install pm-execution@pm-skills2Manually: put the files in place
.claude/commands/write-stories.mdCall it with /write-stories. For all projects use ~/.claude/commands/
Manually: put the files in place
~/.codex/prompts/write-stories.mdCall it with /prompts:write-stories. Codex marks this format deprecated in favour of skills
Manually: put the files in place
.github/prompts/write-stories.prompt.mdManually: put the files in place
.gemini/commands/write-stories.tomlGemini stores commands as TOML: the prompt text goes into the prompt field
Questions about write-stories
How do I install write-stories in Claude Code?
Run /plugin marketplace add phuryn/pm-skills, then /plugin install pm-execution@pm-skills.
What does write-stories do?
It turns a feature description or PRD into an ordered backlog with acceptance criteria. You can choose user stories, job stories, or WWA.
Which story formats does write-stories support?
User stories center on a user and a capability, job stories on a situation and motivation, and WWA on why the work matters, what to build, and how to assess it.
Source text
write-stories.md · MIT
--- description: Break a feature into backlog items — user stories, job stories, or WWA format with acceptance criteria argument-hint: "[user|job|wwa] <feature description or PRD>" --- # /write-stories -- Backlog Item Generator Break a feature into well-structured backlog items. Choose from three formats based on your team's preference, each with full acceptance criteria. ## Invocation ``` /write-stories user Allow users to export reports as PDF and CSV /write-stories job Notification system for task deadlines /write-stories wwa Dark mode for the mobile app /write-stories [upload a PRD or feature spec] # asks format preference /write-stories # asks for feature and format ``` ## Formats ### User Stories **Format**: "As a [user type], I want [capability], so that [benefit]" Apply the **user-stories** skill: - Follow the 3 C's: Card (brief), Conversation (context), Confirmation (acceptance criteria) - Validate against INVEST: Independent, Negotiable, Valuable, Estimable, Small, Testable - Include design links or mockup references where relevant ### Job Stories **Format**: "When [situation], I want to [motivation], so I can [outcome]" Apply the **job-stories** skill: - Focus on the situation and context, not the user role - Ground in real user scenarios observed in research - Ideal for JTBD-oriented teams ### WWA (Why-What-Acceptance) **Format**: Why [strategic context] → What [deliverable] → Acceptance [criteria] Apply the **wwas** skill: - Includes strategic reasoning (why we're building this) - Produces independent, valuable, testable items - Good for cross-functional teams that need business context ## Workflow ### Step 1: Accept the Feature Accept in any form: PRD, feature description, user research finding, or verbal idea. If a PRD is provided, extract the requirements to decompose. ### Step 2: Determine Format If not specified in the invocation, ask: - "Which format does your team use? **User stories**, **Job stories**, or **WWA**?" - If unsure, recommend user stories as the default ### Step 3: Decompose the Feature - Break the feature into 5-15 independent stories (small enough to complete in one sprint) - Ensure each story is independently valuable (delivers user value on its own) - Order by dependency and priority - Write 3-5 acceptance criteria per story - Flag stories that need design input or technical spikes ### Step 4: Generate Stories ``` ## Backlog: [Feature Name] **Format**: [User Stories / Job Stories / WWA] **Total stories**: [count] **Estimated total effort**: [if possible] ### Stories #### Story 1: [Short title] **[The story in chosen format]** Acceptance Criteria: - [ ] [Criterion 1] - [ ] [Criterion 2] - [ ] [Criterion 3] Priority: [P0/P1/P2] | Effort: [S/M/L] | Dependencies: [none or list] --- [Repeat for each story] ### Story Map [Visual ordering: must-have → should-have → nice-to-have] ### Technical Notes [Cross-cutting concerns: API changes, data migration, infrastructure] ### Open Questions [Things that need answers before implementation can start] ``` Save as markdown. ### Step 5: Offer Next Steps - "Want me to **generate test scenarios** for these stories?" - "Should I **create dummy data** for development and testing?" - "Want me to **estimate sprint capacity** for these stories?" - "Should I **convert to a different format** (user stories ↔ job stories ↔ WWA)?" ## Notes - One story = one deployable unit of value — if it needs another story to be useful, they should be combined - Acceptance criteria should be testable by QA without additional interpretation - Error handling and edge cases deserve their own stories, not bullet points within a happy-path story - If the feature is large (15+ stories), suggest grouping into epics or phases - Flag any story that requires a spike (technical investigation before estimation is possible)
© Paweł Huryn · MIT · phuryn/pm-skills