Skip to content
Back to skills

Audit Prd

ASecurity

Audit a multi-section PRD with deterministic Hard Output Rules and cross-section consistency checks. Use when reviewing a complete product requirements document, checking FR-to-AC coverage, acceptance-criteria numbering, story-point arithmetic, or test traceability.

  • 4 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added September 29, 2026
ai-agentssecurity

Works with

  • mcp

Security analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned September 29, 2026

npx -y skills add cdeust/ai-architect-mcp-spec --skill audit-prd --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Audit Prd?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Audit Prd
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/cdeust-audit-prd/badge)](https://www.skillsdirectory.com/skills/cdeust-audit-prd)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: audit-prd
description: Audit a multi-section PRD with deterministic Hard Output Rules and cross-section consistency checks. Use when reviewing a complete product requirements document, checking FR-to-AC coverage, acceptance-criteria numbering, story-point arithmetic, or test traceability.
---

# Audit a PRD

Use the `prd-spec-verifier` MCP server to produce an evidence-based structural audit.

## Workflow

1. Read the complete PRD without rewriting it.
2. Split it into sections and map each section to the closest `section_type` accepted by the `validate_prd_document` tool schema. Ask for clarification when a mapping is genuinely ambiguous.
3. Call `validate_prd_document` once with every mapped section, preserving content exactly.
4. Report each violation with its rule identifier, severity, affected section, and the evidence returned by the tool.
5. Group repeated findings and distinguish blocking violations from warnings.
6. State the scope limit: a passing report demonstrates conformance to the implemented structural rules only. It does not establish factual accuracy, product value, implementation feasibility, security, or semantic correctness.

Do not invent a pass for checks the tool did not run. Do not silently repair the PRD unless the user also asks for edits.

Files in this skill

  • SKILL.md1.3 KB
  • agents/openai.yaml296 B

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.