agentleFS
CreativeActtechCreativeActtech/llm-skills/skills/example-skill/compliance-policy-analyzer/SKILL.md

compliance-policy-auditor

Skill2 starsChanged 7 months agoMITView on GitHub

Audit corporate policies or data-handling descriptions against regulatory frameworks (GDPR, SOC2, HIPAA). Use when users need to identify compliance gaps or risk levels in technical procedures.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    IF user specifies a framework (GDPR/SOC2/HIPAA/ISO27001), prioritize its rules.

    line 23
  2. Distinctive:

    IF the input text is too vague to audit:

    line 59
  3. Distinctive:

    ASK for specific details regarding data storage, user consent, or encryption

    line 61

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Compliance Policy Auditor

Systematically reviews technical or procedural documentation to identify alignment or deviations from major regulatory frameworks.

🎯 When to Use

  • User provides a "Privacy Policy" or "Data Retention Plan" for review.
  • User asks: "Is this process SOC2 compliant?" or "What GDPR risks exist here?"
  • Do NOT use for providing binding legal advice or drafting contracts.
  • Do NOT use for auditing physical security (cams, locks) unless documented.

🧠 Core Workflow

Step 1 — Scope & Framework Selection IF user specifies a framework (GDPR/SOC2/HIPAA/ISO27001), prioritize its rules; ELSE, apply General Data Protection principles.

Step 2 — Data Mapping Identify PII (Personally Identifiable Information), PHI (Protected Health Information), or PCI data mentioned in the text.

Step 3 — Gap Analysis

  1. Data Minimization — Check if only necessary data is collected.
  2. Access Control — Audit description of "Who has access" (RBAC).
  3. Security Measures — Identify encryption, hashing, and log requirements.

Step 4 — Risk Scoring Assign Severity (Critical/Major/Minor) to gaps based on regulatory fine potential.

Step 5 — Return Output Provide a structured JSON audit report.

📋 Output Format

{
  "frameworks_evaluated": ["GDPR", "SOC2"],
  "pii_detected": ["email", "IP address"],
  "findings": [
    {
      "severity": "critical",
      "category": "Data Retention",
      "issue": "Policy states data is kept indefinitely.",
      "remediation": "Define a 7-year purge cycle per Article 5(1)(e)."
    }
  ],
  "risk_summary": "1 Critical Gap detected. High risk of non-compliance."
}

⚠️ Fallback Behavior

IF the input text is too vague to audit:

ASK for specific details regarding data storage, user consent, or encryption

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.