gov-policy-validation
Domain: gov · Model class: strong
Description
Section titled “Description”Use this skill when the user wants to work on Validating AI workflows and prompts against organisational, regulatory, and compliance policies. Triggers include “validate against policy”, “compliance validation for AI”, “policy-as-code for AI”. Do NOT use when harden against injection (use gov-prompt-injection-hardening).
Purpose
Section titled “Purpose”Validating AI workflows and prompts against organisational, regulatory, and compliance policies. This skill provides structured guidance, references, and worked examples to help produce high-quality, actionable outputs.
Trigger Phrases
Section titled “Trigger Phrases”- “validate against policy”
- “compliance validation for AI”
- “policy-as-code for AI”
- “governance check”
- “regulatory compliance for AI”
Anti-Triggers
Section titled “Anti-Triggers”- harden against injection (use gov-prompt-injection-hardening)
- validate at the workflow level (use gov-workflow-compliance)
Intake Questions
Section titled “Intake Questions”- What is the user’s goal and current state?
- What constraints (time, team, compliance) apply?
- Are there existing artifacts (specs, code, benchmarks) to reference?
Output Contract
Section titled “Output Contract”- policy or compliance assessment
- risk classification
- required controls
- audit trail or remediation steps
Related Skills
Section titled “Related Skills”gov-model-compatibility · gov-regulated-workflow-design · gov-workflow-compliance