Grc Compliance logo

Grc Compliance

Organization
serac-labs
grc-compliance

Build ServiceNow GRC — sn_compliance_policy lifecycle, sn_compliance_control tests, sn_risk_risk assessment with inherent/residual scoring, audit engagements, and findings remediation.

Overview

Publisherserac-labs
Repositoryserac
Skill namegrc-compliance
Stars
78
Forks
26
Bundled files
Instructions only
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by serac-labs on GitHub. Read the source before you install it.

Installation

Install the Grc Compliance AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/serac-labs/serac.git /tmp/serac
mkdir -p .claude/skills
cp -r /tmp/serac/packages/skills/grc-compliance .claude/skills/grc-compliance
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Grc Compliance in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Grc Compliance on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Grc Compliance is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

GRC & Compliance for ServiceNow

GRC (Governance, Risk, Compliance) manages organizational policies, risks, and regulatory compliance.

GRC Architecture

Policy (sn_compliance_policy)
    └── Policy Statements
        └── Controls (sn_compliance_control)
            └── Control Tests
                └── Test Results

Risk (sn_risk_risk)
    ├── Risk Assessment
    └── Risk Response

Key Tables

TablePurpose
sn_compliance_policyCompliance policies
sn_compliance_controlControls
sn_compliance_control_testControl tests
sn_risk_riskRisk records
sn_audit_engagementAudit engagements

Policies (ES5)

Create Policy

javascript
// Create compliance policy (ES5 ONLY!)
var policy = new GlideRecord("sn_compliance_policy")
policy.initialize()

// Basic info
policy.setValue("name", "Information Security Policy")
policy.setValue("description", "Enterprise information security requirements")
policy.setValue("short_description", "InfoSec Policy")

// Classification
policy.setValue("category", "security")
policy.setValue("type", "corporate")

// Owner
policy.setValue("owner", policyOwnerSysId)
policy.setValue("owning_group", securityTeamSysId)

// Status
policy.setValue("state", "draft")

// Dates
policy.setValue("effective_date", "2024-01-01")
policy.setValue("review_date", "2025-01-01")

policy.insert()

Policy Lifecycle

javascript
// Transition policy state (ES5 ONLY!)
function transitionPolicy(policySysId, newState, notes) {
  var policy = new GlideRecord("sn_compliance_policy")
  if (!policy.get(policySysId)) {
    return { success: false, message: "Policy not found" }
  }

  var validTransitions = {
    draft: ["review", "retired"],
    review: ["approved", "draft"],
    approved: ["published", "draft"],
    published: ["review", "retired"],
    retired: ["draft"],
  }

  var currentState = policy.getValue("state")

  if (!validTransitions[currentState] || validTransitions[currentState].indexOf(newState) === -1) {
    return { success: false, message: "Invalid transition" }
  }

  policy.setValue("state", newState)

  if (newState === "published") {
    policy.setValue("published_date", new GlideDateTime())
  }

  if (notes) {
    policy.work_notes = notes
  }

  policy.update()

  return { success: true, state: newState }
}

Controls (ES5)

Create Control

javascript
// Create compliance control (ES5 ONLY!)
var control = new GlideRecord("sn_compliance_control")
control.initialize()

// Basic info
control.setValue("name", "Access Control Review")
control.setValue("description", "Quarterly review of user access rights")
control.setValue("short_description", "Access Review Control")

// Link to policy
control.setValue("policy", policySysId)

// Classification
control.setValue("type", "detective") // preventive, detective, corrective
control.setValue("category", "access_control")
control.setValue("frequency", "quarterly")

// Owner
control.setValue("owner", controlOwnerSysId)

// Testing
control.setValue("test_frequency", "quarterly")
control.setValue("test_type", "manual")

// Status
control.setValue("state", "draft")

control.insert()

Control Testing

javascript
// Create control test (ES5 ONLY!)
function createControlTest(controlSysId, testData) {
  var test = new GlideRecord("sn_compliance_control_test")
  test.initialize()

  test.setValue("control", controlSysId)
  test.setValue("name", testData.name)
  test.setValue("description", testData.description)

  // Test details
  test.setValue("test_type", testData.type) // design, operating
  test.setValue("planned_start", testData.plannedStart)
  test.setValue("planned_end", testData.plannedEnd)

  // Assignment
  test.setValue("assigned_to", testData.tester)

  // Status
  test.setValue("state", "open")

  return test.insert()
}

// Record test result
function recordTestResult(testSysId, result) {
  var test = new GlideRecord("sn_compliance_control_test")
  if (!test.get(testSysId)) {
    return false
  }

  test.setValue("state", "closed")
  test.setValue("result", result.outcome) // pass, fail, not_tested
  test.setValue("actual_end", new GlideDateTime())
  test.setValue("findings", result.findings)
  test.setValue("evidence", result.evidence)

  // If failed, create issue
  if (result.outcome === "fail") {
    createComplianceIssue(test, result)
  }

  test.update()
  return true
}

Risk Management (ES5)

Create Risk

javascript
// Create risk record (ES5 ONLY!)
var risk = new GlideRecord("sn_risk_risk")
risk.initialize()

// Basic info
risk.setValue("name", "Data Breach Risk")
risk.setValue("description", "Risk of unauthorized access to customer data")
risk.setValue("short_description", "Data Breach")

// Classification
risk.setValue("category", "security")
risk.setValue("subcategory", "data_protection")

// Risk assessment
risk.setValue("inherent_likelihood", 3) // 1-5 scale
risk.setValue("inherent_impact", 5) // 1-5 scale
// Inherent risk = likelihood x impact

// Controls that mitigate this risk
risk.setValue("controls", controlSysIds) // Comma-separated

// Residual risk (after controls)
risk.setValue("residual_likelihood", 2)
risk.setValue("residual_impact", 5)

// Owner
risk.setValue("owner", riskOwnerSysId)

// Status
risk.setValue("state", "assess")

risk.insert()

Risk Assessment

javascript
// Calculate risk score (ES5 ONLY!)
function calculateRiskScore(likelihood, impact) {
  var score = likelihood * impact

  var rating = "low"
  if (score >= 20) {
    rating = "critical"
  } else if (score >= 12) {
    rating = "high"
  } else if (score >= 6) {
    rating = "medium"
  }

  return {
    score: score,
    rating: rating,
  }
}

// Assess risk and update record (ES5 ONLY!)
function assessRisk(riskSysId, assessment) {
  var risk = new GlideRecord("sn_risk_risk")
  if (!risk.get(riskSysId)) {
    return false
  }

  // Update inherent risk
  risk.setValue("inherent_likelihood", assessment.inherentLikelihood)
  risk.setValue("inherent_impact", assessment.inherentImpact)

  var inherentScore = calculateRiskScore(assessment.inherentLikelihood, assessment.inherentImpact)
  risk.setValue("inherent_risk_score", inherentScore.score)
  risk.setValue("inherent_risk_rating", inherentScore.rating)

  // Update residual risk
  risk.setValue("residual_likelihood", assessment.residualLikelihood)
  risk.setValue("residual_impact", assessment.residualImpact)

  var residualScore = calculateRiskScore(assessment.residualLikelihood, assessment.residualImpact)
  risk.setValue("residual_risk_score", residualScore.score)
  risk.setValue("residual_risk_rating", residualScore.rating)

  // Assessment metadata
  risk.setValue("assessed_date", new GlideDateTime())
  risk.setValue("assessed_by", gs.getUserID())
  risk.setValue("state", "monitor")

  risk.update()

  return true
}

Audits (ES5)

Create Audit Engagement

javascript
// Create audit engagement (ES5 ONLY!)
var audit = new GlideRecord("sn_audit_engagement")
audit.initialize()

audit.setValue("name", "Q1 2024 SOX Audit")
audit.setValue("description", "Quarterly SOX compliance audit")
audit.setValue("type", "compliance")

// Dates
audit.setValue("planned_start", "2024-01-15")
audit.setValue("planned_end", "2024-02-15")

// Scope
audit.setValue("scope", "Financial controls, access management")

// Team
audit.setValue("lead_auditor", auditorSysId)
audit.setValue("audit_team", auditTeamSysId)

// Status
audit.setValue("state", "planning")

audit.insert()

Audit Findings

javascript
// Create audit finding (ES5 ONLY!)
function createAuditFinding(auditSysId, findingData) {
  var finding = new GlideRecord("sn_audit_finding")
  finding.initialize()

  finding.setValue("engagement", auditSysId)
  finding.setValue("title", findingData.title)
  finding.setValue("description", findingData.description)

  // Severity
  finding.setValue("severity", findingData.severity) // critical, high, medium, low

  // Related control
  if (findingData.control) {
    finding.setValue("control", findingData.control)
  }

  // Recommendation
  finding.setValue("recommendation", findingData.recommendation)

  // Owner for remediation
  finding.setValue("owner", findingData.owner)

  // Due date for remediation
  finding.setValue("due_date", findingData.dueDate)

  finding.setValue("state", "open")

  return finding.insert()
}

Compliance Reporting (ES5)

Compliance Dashboard Data

javascript
// Get compliance summary (ES5 ONLY!)
function getComplianceSummary() {
  var summary = {
    policies: { total: 0, published: 0, review_needed: 0 },
    controls: { total: 0, effective: 0, failed: 0 },
    risks: { critical: 0, high: 0, medium: 0, low: 0 },
    audits: { open: 0, findings: 0 },
  }

  // Policies
  var ga = new GlideAggregate("sn_compliance_policy")
  ga.addAggregate("COUNT")
  ga.groupBy("state")
  ga.query()

  while (ga.next()) {
    var count = parseInt(ga.getAggregate("COUNT"), 10)
    summary.policies.total += count
    if (ga.getValue("state") === "published") {
      summary.policies.published = count
    }
  }

  // Risks by rating
  ga = new GlideAggregate("sn_risk_risk")
  ga.addQuery("active", true)
  ga.addAggregate("COUNT")
  ga.groupBy("residual_risk_rating")
  ga.query()

  while (ga.next()) {
    var rating = ga.getValue("residual_risk_rating")
    var riskCount = parseInt(ga.getAggregate("COUNT"), 10)
    if (summary.risks.hasOwnProperty(rating)) {
      summary.risks[rating] = riskCount
    }
  }

  return summary
}

MCP Tool Integration

Available Tools

ToolPurpose
snow_query_tableQuery GRC tables
snow_execute_scriptTest GRC scripts
snow_run_compliance_scanRun compliance audits
snow_grc_risk_manage (action='assess')Risk assessment

Example Workflow

javascript
// 1. Query active policies
await snow_query_table({
  table: "sn_compliance_policy",
  query: "state=published",
  fields: "name,category,effective_date,review_date",
})

// 2. Find high risks
await snow_query_table({
  table: "sn_risk_risk",
  query: "residual_risk_rating=high^ORresidual_risk_rating=critical",
  fields: "name,category,residual_risk_score,owner",
})

// 3. Get compliance summary
await snow_execute_script({
  script: `
        var summary = getComplianceSummary();
        gs.info(JSON.stringify(summary));
    `,
})

Best Practices

  1. Clear Ownership - Assign policy/control/risk owners
  2. Regular Reviews - Schedule periodic assessments
  3. Evidence Collection - Document control effectiveness
  4. Risk Quantification - Use consistent scoring
  5. Audit Trail - Track all changes
  6. Automation - Automate testing where possible
  7. Reporting - Regular compliance dashboards
  8. ES5 Only - No modern JavaScript syntax

Frequently asked questions

What does the Grc Compliance AI skill do?

Build ServiceNow GRC — sn_compliance_policy lifecycle, sn_compliance_control tests, sn_risk_risk assessment with inherent/residual scoring, audit engagements, and findings remediation.

Why use Grc Compliance on TypingMind?

Because you install it once and use it with any model. Grc Compliance is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Grc Compliance in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/serac-labs/serac/tree/main/packages/skills/grc-compliance. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Grc Compliance?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Grc Compliance?

As many as you like. As long as a model supports skills, you can use Grc Compliance with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Grc Compliance AI skill free?

Yes. It is published on GitHub by serac-labs under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇