agentsclimarketplace

Write requirements prd

Skill alexe-ev/product-plugins/product-planning/skills/write-requirements-prd

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-requirements-prd

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 clear, complete product requirements documents and user stories. Use this skill when a team is ready to define what needs to be built for a prioritized initiative.

SKILL.md

2.4 KB, as published. Nobody here has run it

Write Requirements & PRD

Purpose

Produce clear, structured product requirements that engineering, design, and QA can use to build and test the right thing.

Skill type

Conceptual skill

Use this skill when

  • An initiative is prioritized and ready for detailed definition
  • Engineering needs clear requirements before scoping or development
  • A feature needs acceptance criteria defined
  • A PRD review is needed for quality or completeness

Do not use this skill when

  • The initiative hasn't been prioritized yet
  • The goal is roadmap building (use build-roadmap-prioritization)
  • The goal is sprint management or delivery coordination (use plan-delivery-collaboration)

Required inputs

  • Feature or initiative description
  • User segment affected
  • Goal or outcome the feature serves

Optional inputs

  • User stories or job stories
  • Design files or mockups
  • Technical constraints
  • Acceptance criteria drafts
  • Edge cases or exclusions

Upstream context

Works best when:

  • Goal is defined
  • User segment and problem are understood
  • Design exploration has begun

If upstream context is missing

If the problem and user are not defined, do not write requirements. Write a problem framing first.

Downstream handoff

Output can feed:

  • plan-delivery-collaboration (engineers use requirements to plan delivery)
  • design-experiment-plan (if this is an A/B test, requirements feed the experiment plan)

Instructions

  1. Define the problem this feature solves and for whom.
  2. State the goal or success metric.
  3. Write user stories in the format: As a [user], I want to [action] so that [outcome].
  4. Define acceptance criteria for each user story.
  5. List out-of-scope items explicitly.
  6. Identify open questions and dependencies.
  7. Note edge cases and error states.

Output

Provide:

  • Problem statement and goal
  • User stories with acceptance criteria
  • Out-of-scope definition
  • Open questions
  • Dependencies
  • Edge cases and error states

Risks / caveats

  • Do not write requirements without knowing the user and problem
  • Acceptance criteria must be testable — avoid vague terms like "should feel easy"
  • Out-of-scope sections prevent scope creep — do not skip them

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.