agentleFS
Sign inStart free
janelleciprianojanellecipriano/pm-skills/skills/prd-review/SKILL.md

prd-review

Skill1 starsChanged 5 months agoMITView on GitHub

Review a product requirements document (PRD) or spec against a quality checklist and surface gaps, ambiguities, and risks before engineering starts. Use when the user says "review this PRD", "is this spec ready", "critique my requirements", "PRD checklist", or shares a doc and wants it pressure-tested before build.

16 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use design-review and security-review.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • dillonluiSkill

    design-review

    Review a view or flow for UX and UI issues. Provides severity-ranked, actionable findings grounded in established design heuristics. Use when the user asks for design feedback, UX review, or UI critique.

    Also in 3 projects that use this

  • SentrySkill

    security-review

    Finds exploitable application security vulnerabilities in code changes. Use for Warden security scans, appsec review, OWASP-style checks, authentication or authorization bugs, injection, XSS, SSRF, path traversal, secrets, unsafe crypto, webhook verification, open redirects, or sensitive data exposure.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 11 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the PRD fully first.

    line 30

“Common” is measured: kept by at least 6 in 10 of the 11 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

PRD Review

Pressure-test a PRD so problems are caught on the page, not in code. Be a constructive but skeptical reviewer.

When to use

  • A PRD/spec exists and the user wants feedback or a readiness check before build/estimation.

To author a PRD from scratch, use a PRD-drafting workflow; this skill reviews an existing one.

Review checklist

Assess the doc against each dimension. Quote or reference specifics; don't be generic.

  1. Problem & why now — is the user problem clear and evidenced (not just a feature request)?
  2. Audience — are target users/segments and their context defined?
  3. Goals & success metrics — measurable outcomes, baseline → target? Anti-goals stated?
  4. Scope — explicit in/out? MVP vs. later cuts clear?
  5. Requirements — unambiguous, testable, prioritized (must/should/could)? No solution disguised as requirement.
  6. UX — flows, key states (empty/error/loading/edge), accessibility considered?
  7. Edge cases & failure modes — what happens when things go wrong?
  8. Dependencies & constraints — other teams, platforms, legal/privacy, performance.
  9. Risks & open questions — named, with owners.
  10. Measurement — instrumentation/analytics plan to know if it worked.

Process

  1. Read the PRD fully first.
  2. Rate each dimension: ✅ solid / 🟡 needs work / 🔴 missing — with a one-line reason.
  3. List the top gaps to fix before build, most important first.
  4. Pose the open questions the author must answer to be buildable.
  5. End with a verdict: Ready / Ready with fixes / Not ready.

Output format

A checklist table (dimension · rating · note), then Top gaps, Open questions, and the verdict. Be specific and kind; the goal is a better doc, not a teardown.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free