A review of a PRD, or Product Requirements Document: a description of the user problem, proposed product, audience, and expected results. It examines the document from both engineering and product-management viewpoints.

Use it before approving engineering work or during routine PRD reviews to question the problem, expected impact, risks, alternatives, metrics, and missing information.

Teams can spend engineering time on a poorly defined problem or an idea without measurable success criteria. The review finds gaps in feasibility, evidence, dependencies, audience, and decision quality before work is committed.

prd-review — Skill for Claude Code by caiaffa

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add caiaffa/claude-code-ultimate-engineering-system --skill prd-review

Clone the repo

git clone --depth 1 https://github.com/caiaffa/claude-code-ultimate-engineering-system

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/caiaffa/claude-code-ultimate-engineering-system/prd-review/github.svg)](https://agentmods.dev/skills/caiaffa/claude-code-ultimate-engineering-system/prd-review)

Your own site

<a href="https://agentmods.dev/skills/caiaffa/claude-code-ultimate-engineering-system/prd-review"><img src="https://agentmods.dev/badge/skills/caiaffa/claude-code-ultimate-engineering-system/prd-review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/caiaffa/claude-code-ultimate-engineering-system/prd-review"><img src="https://agentmods.dev/badge/skills/caiaffa/claude-code-ultimate-engineering-system/prd-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,197 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00062	$0.01197
Opus 5.5	$0.00025	$0.00479
Sonnet 5.5	$0.00012	$0.00239
Haiku 4.5	$0.00006	$0.00120

Measured 2mo ago against content hash 2bf60589baef, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

prd-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/prd-review/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mission

Ensure the team builds the right thing AND can build it well. Review the PRD the way a staff engineer and a senior PM would in a peer review — critique and ask, never rewrite. The PRD belongs to the PM; this skill produces feedback.

When to use

Reviewing a PRD before engineering commitment.
The daily routine review of PRDs synced from Drive.

Handoff

Receives from: principal-engineer (initial review).
Hands off to: architecture-decisions (if approved) or back to the PM (if not).

Engineering lens

Front 1 - Problem, value & audience

What metric proves this problem exists today? How big is it?
Root cause or symptom?
"Show me the number": baseline, expected gain, mechanism linking solution to gain.
Cost-to-value ratio acceptable for the time horizon?
Which users/personas are affected - and what happens to those who are NOT the target audience? What is the blast radius if it goes wrong?

Front 2 - Metrics & measurement

Is the baseline credible and measured today?
Are success criteria specific and measurable?
Guardrail metrics - what must NOT regress?
How and when is impact observed?

Front 3 - Gaps & hidden engineering work

Sections missing or vague?
Engineering work implied but unstated: migrations, backfill, infra, auth.
Ambiguities that will block implementation.
Quick feasibility check: does this conflict with ~/.claude/engineering/SYSTEM_INVARIANTS.md, or depend on a service/data that does not exist? (Deep design goes to /adr.)

Front 4 - Dependencies & sequencing

Which other teams, systems, or PRDs does this depend on?
What must exist before this can start?
Coupling with work already in flight?
Sequencing or ownership risk ("we found mid-build we needed team X")?

Front 5 - Decision quality & risk

Is the scope disciplined, or a wishlist? Are cuts identified?
Is the decision reversible if the bet is wrong?
Operational cost (run + maintain) considered?
Non-technical risk: legal/compliance, data privacy (LGPD), product-level security (does this expose sensitive data?), reputation. Cross-check ~/.claude/engineering/ENGINEERING_RISKS_FROM_PRD.md.

Read the full file on GitHub · 119 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 119 lines · 62 tokens per session scan A 2bf60589baef

Subscribe to this mod's changes

prd-review is a skill published in the GitHub repository caiaffa/claude-code-ultimate-engineering-system (17 stars, last pushed 2mo ago), licensed MIT. It adds 62 tokens to every session and 1,197 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-15.

Planning Project management

prd-review next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
prd-reviewcaiaffa/claude-code-ultimate-engineering-system	Skill	17	2mo ago	MIT	A	62	Claude Code
imagegenopenai/codex	Skill	135k	today	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	100k	today	Apache-2.0	A	19	Claude Code
browser-automationopenclaw/openclaw	Skill	394k	today	MIT	A	36	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	80k	7d ago	MIT	A	200	Claude Code, Codex
next-cache-components-adoptionvercel/next.js	Skill	144k	today	MIT	A	95	Claude Code
chat-pet-sprite-creationmicrosoft/vscode	Skill	195k	today	MIT	A	53	Claude Code, Codex