agentsclimarketplace

Regulatory guardrail checker

Skill sisodiabhumca/agent-skills/skills/regulatory-guardrail-checker

Production-Ready Agent Skills : product analytics, growth experiments, CRM, research synthesis, postmortems, data contracts, SaaS spend, compliance, architecture maps, and LLM eval and many more.

Install
npx -y skills add sisodiabhumca/agent-skills --skill regulatory-guardrail-checker

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Use to screen a feature spec or product change for compliance risks across GDPR, CCPA, HIPAA, PCI-DSS, SOC2, and accessibility (WCAG 2.2). Produces a risk register and required-controls checklist before launch.

SKILL.md

1.5 KB, as published. Nobody here has run it

Regulatory Guardrail Checker

When to invoke

  • "Run compliance review on this PRD."
  • "Does this feature touch PHI / PII?"
  • "What guardrails do we need before launching in EU?"

Inputs needed

  1. Spec text — PRD or design doc (file or stdin).
  2. Regimes to check — default: GDPR, CCPA, SOC2; opt-in: HIPAA, PCI, WCAG.
  3. Geographies / industries (optional).

Workflow

  1. Extract signals from the spec: data types, third parties, user controls, retention, automation/AI use.
  2. Map signals to regime obligations (lawful basis, DSR, BAAs, encryption, audit logging).
  3. Score risk — High / Medium / Low per regime.
  4. Output a risk register + required-controls checklist with owners.

Output format

## Risk register
| Regime | Risk | Severity | Required control | Owner |
## Required controls checklist
- [ ] ...
## Open questions for legal/security
- ...

Guardrails

  • Never claim "compliant" — only "controls in place" or "controls missing".
  • Surface all detected sensitive-data signals; do not hide on low confidence.
  • Produce open questions for ambiguous areas.

Reference code

check.py does pattern-based signal extraction and a rules-based mapping. Hooks for an LLM are provided but optional.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.