agentsclimarketplace

Write user stories

Skill alexe-ev/product-plugins/product-planning/skills/write-user-stories

Skill library for AI agents — 15 product domains, 121 skills. Tells the agent what to ask, how to reason, and what to output.

Install
npx -y skills add alexe-ev/product-plugins --skill write-user-stories

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Write well-formed user stories with clear acceptance criteria ready for development. Use this skill when a team needs to break down a feature or initiative into development-ready stories.

SKILL.md

2.6 KB, as published. Nobody here has run it

Write User Stories

Purpose

Help teams produce well-formed, testable user stories that communicate user intent and enable engineering to build the right thing.

Skill type

Conceptual skill

Use this skill when

  • A feature needs to be broken into development-ready increments
  • User stories are too vague or written from a system perspective rather than user perspective
  • Acceptance criteria are missing or untestable
  • A PRD exists but engineers need story-level granularity

Do not use this skill when

  • Requirements at a higher level need to be defined first (use write-requirements-prd)
  • The goal is sprint planning and sequencing (use plan-delivery-collaboration)

Required inputs

  • Feature or initiative description
  • Target user
  • Goal or outcome the feature serves

Optional inputs

  • PRD or requirements document
  • Design files or mockups
  • Technical constraints
  • Existing story drafts

Upstream context

Works best when:

  • PRD or requirements are defined
  • User and problem are clear

If upstream context is missing

Do not write stories without knowing the user and the problem. Write requirements first.

Downstream handoff

Output can feed:

  • plan-delivery-collaboration (stories feed sprint planning)
  • validate-experiment-quality (stories define what was shipped in an experiment)

Instructions

  1. Identify all user-facing interactions in the feature.
  2. Write each story in format: "As a [specific user type], I want to [action] so that [outcome]."
  3. Keep each story to a single, shippable increment of value.
  4. Write acceptance criteria in Given/When/Then or checklist format.
  5. Identify and flag edge cases and error states.
  6. Define what "done" means for each story (including non-functional requirements if relevant).
  7. Group stories into logical epics or themes.

Output

Provide:

  • Story set organized by epic or theme
  • Each story with: user type, action, outcome, acceptance criteria
  • Edge cases and error state handling per story
  • Definition of done
  • Stories flagged as blockers (must be done before others)
  • Estimated story count and rough scope signal

Risks / caveats

  • "As a user, I want to click a button" is a task, not a story — anchor in user outcome
  • Acceptance criteria must be testable — avoid adjectives like "intuitive" or "fast"
  • Too-large stories (epics) create delivery risk — break them down

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.