Skip to content
Back to skills

Validate Spec

ASecurity

Validate one PRD or technical-specification section with deterministic Hard Output Rules. Use when checking a single overview, requirement set, user-story section, acceptance-criteria section, API specification, data model, security section, test plan, deployment plan, risk section, timeline, source-code section, or test-code section.

  • 4 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added September 29, 2026
ai-agentsapisecurity

Works with

  • api
  • 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 validate-spec --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Validate Spec?

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

Security grade badge for Validate Spec
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/cdeust-validate-spec/badge)](https://www.skillsdirectory.com/skills/cdeust-validate-spec)

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: validate-spec
description: Validate one PRD or technical-specification section with deterministic Hard Output Rules. Use when checking a single overview, requirement set, user-story section, acceptance-criteria section, API specification, data model, security section, test plan, deployment plan, risk section, timeline, source-code section, or test-code section.
---

# Validate a specification section

Use the `prd-spec-verifier` MCP server for a focused structural check.

## Workflow

1. Read the section without rewriting it.
2. Select the closest `section_type` accepted by the `validate_prd_section` tool schema. Ask for clarification if the section's role is ambiguous.
3. Call `validate_prd_section` with the exact content and selected type.
4. Report rule identifiers, severities, evidence, and the returned score. Separate violations from checks that passed.
5. State the scope limit: the validator checks implemented formatting, traceability, and consistency rules. It does not prove that claims are true, requirements are desirable, code exists, or the design is feasible.

Do not infer semantic correctness from a zero-violation result. Do not edit the section unless the user asks for a revision.

Files in this skill

  • SKILL.md1.2 KB
  • agents/openai.yaml303 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.