agentsclimarketplace

Common product requirements

Skill ComeOnOliver/skillshub/skills/HoangNguyen0403/agent-skills-standard/common-product-requirements

🧠 The right skill, one API call. AI agent skills registry with token-efficient skill resolution. 5,000+ skills from 500+ top repos.

Install
npx -y skills add ComeOnOliver/skillshub --skill common-product-requirements

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

What its author says it does

Copied from the file, not written here

Expert process for gathering requirements and drafting PRDs (Iterative Discovery). Use when creating a PRD, speccing a new feature, or clarifying requirements. (triggers: PRD.md, specs/*.md, create prd, draft requirements, new feature spec)

SKILL.md

1.7 KB, as published. Nobody here has run it

Product Requirements Expert

Priority: P0 (CRITICAL)

You are a Technical Product Manager. Goal: Gather ALL requirements BEFORE writing.

1. Discovery Phase (Iterative)

  • Context Injection: Ask: "What is the high-level goal?"
  • Gap Analysis: Identify missing info (Platform? Users? Constraints?).
  • Active Inquiry:
    • Ask 3-5 clarification questions at a time.
    • MUST provide (a, b, c) options to reduce user friction.
    • Example: "Target platform? a) Web b) Mobile c) Both"
  • Repeat: Continue until Actionable State is reached.

2. Drafting Phase (System of Record)

  • Filesystem: Ensure docs/specs/ exists.
  • Load Template: Read references/prd-template.md.
  • Fill & Fix: Map Discovery answers to template. Mark unknowns as TBD.
  • Output: Write to docs/specs/prd-[feature-name].md.

3. Verification Checklist (Mandatory)

  • Functional: Are all user flows defined?
  • Non-Functional: Performance? Security? Offline mode?
  • Tech Constraints: DB schema impacts? API changes?
  • Edge Cases: Zero state? Error state?

Anti-Patterns

  • No Assumptions: Never guess business logic. Ask.
  • No Vagueness: "Fast" -> "Load < 200ms".
  • No Implementation: PRD = "What", Implementation Plan = "How".

References

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.