Data Policies logo

Data Policies

Organization
serac-labs
data-policies

Manage ServiceNow dictionary (sys_dictionary), table/field creation, choice lists, dictionary overrides, and sys_data_policy2 rules that enforce mandatory/read-only/visible field behavior on the data layer.

Overview

Publisherserac-labs
Repositoryserac
Skill namedata-policies
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 Data Policies 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/data-policies .claude/skills/data-policies
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Data Policies 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 Data Policies 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 Data Policies 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.

Data Policies & Dictionary for ServiceNow

Data Policies enforce data integrity rules. Dictionary controls schema and field behavior.

Architecture

Dictionary (sys_dictionary)
    ├── Field Definition
    │   ├── Type, Length, Default
    │   └── Dependent Field
    └── Dictionary Overrides (sys_dictionary_override)

Data Policy (sys_data_policy2)
    └── Data Policy Rules (sys_data_policy_rule)
        └── Condition-based field behaviors

Key Tables

TablePurpose
sys_dictionaryField definitions
sys_dictionary_overrideScoped overrides
sys_data_policy2Data policies
sys_data_policy_rulePolicy rules
sys_db_objectTable definitions

Dictionary Management (ES5)

Create Table

javascript
// Create custom table (ES5 ONLY!)
var table = new GlideRecord("sys_db_object")
table.initialize()

table.setValue("name", "u_custom_table")
table.setValue("label", "Custom Table")
table.setValue("super_class", "task") // Extends task
table.setValue("is_extendable", true)
table.setValue("create_access_controls", true)
table.setValue("live_feed_enabled", false)

table.insert()

Create Field

javascript
// Create field on table (ES5 ONLY!)
var field = new GlideRecord("sys_dictionary")
field.initialize()

// Table and element
field.setValue("name", "u_custom_table")
field.setValue("element", "u_customer_name")

// Field properties
field.setValue("column_label", "Customer Name")
field.setValue("internal_type", "string")
field.setValue("max_length", 100)
field.setValue("mandatory", false)
field.setValue("read_only", false)
field.setValue("display", false)
field.setValue("active", true)

// Default value
field.setValue("default_value", "")

// Reference field specific
// field.setValue('reference', 'customer_account');
// field.setValue('reference_qual', 'active=true');

field.insert()

Field Types

javascript
// Common field types
var FIELD_TYPES = {
  STRING: "string",
  INTEGER: "integer",
  DECIMAL: "decimal",
  BOOLEAN: "boolean",
  GLIDE_DATE: "glide_date",
  GLIDE_DATE_TIME: "glide_date_time",
  REFERENCE: "reference",
  CHOICE: "choice",
  JOURNAL: "journal",
  JOURNAL_INPUT: "journal_input",
  HTML: "html",
  URL: "url",
  EMAIL: "email",
  SCRIPT: "script",
  CONDITIONS: "conditions",
}

// Create different field types (ES5 ONLY!)
function createField(tableName, fieldDef) {
  var field = new GlideRecord("sys_dictionary")
  field.initialize()
  field.setValue("name", tableName)
  field.setValue("element", fieldDef.name)
  field.setValue("column_label", fieldDef.label)
  field.setValue("internal_type", fieldDef.type)

  if (fieldDef.maxLength) {
    field.setValue("max_length", fieldDef.maxLength)
  }

  if (fieldDef.reference) {
    field.setValue("reference", fieldDef.reference)
  }

  if (fieldDef.choices) {
    field.setValue("choice", 1) // Has choices
  }

  return field.insert()
}

Create Choices

javascript
// Create choice list values (ES5 ONLY!)
function createChoices(tableName, fieldName, choices) {
  for (var i = 0; i < choices.length; i++) {
    var choice = new GlideRecord("sys_choice")
    choice.initialize()
    choice.setValue("name", tableName)
    choice.setValue("element", fieldName)
    choice.setValue("value", choices[i].value)
    choice.setValue("label", choices[i].label)
    choice.setValue("sequence", (i + 1) * 10)
    choice.setValue("inactive", false)
    choice.insert()
  }
}

// Usage
createChoices("incident", "u_custom_status", [
  { value: "pending", label: "Pending Review" },
  { value: "approved", label: "Approved" },
  { value: "rejected", label: "Rejected" },
])

Dictionary Overrides (ES5)

Create Override

javascript
// Create dictionary override for scoped app (ES5 ONLY!)
var override = new GlideRecord("sys_dictionary_override")
override.initialize()

// Reference the base field
override.setValue("base_table", "task")
override.setValue("base_element", "short_description")

// Target table
override.setValue("name", "u_custom_table")

// Override properties
override.setValue("column_label", "Request Summary")
override.setValue("mandatory", true)
override.setValue("read_only", false)
override.setValue("max_length", 200)

// Default value override
override.setValue("default_value", "")

override.insert()

Data Policies (ES5)

Create Data Policy

javascript
// Create data policy (ES5 ONLY!)
var policy = new GlideRecord("sys_data_policy2")
policy.initialize()

policy.setValue("model_table", "incident")
policy.setValue("short_description", "Resolution Fields Required on Resolve")
policy.setValue("active", true)

// Conditions - when policy applies
policy.setValue("conditions", "state=6") // Resolved state

// Apply to forms
policy.setValue("apply_to_client", true)
policy.setValue("apply_to_import_sets", true)
policy.setValue("apply_to_soap", true)

// Reverse
policy.setValue("reverse_if_false", true)

var policySysId = policy.insert()

// Add policy rules
addDataPolicyRule(policySysId, "resolution_code", true, false, false)
addDataPolicyRule(policySysId, "close_notes", true, false, false)

Add Policy Rules

javascript
// Add data policy rule (ES5 ONLY!)
function addDataPolicyRule(policySysId, fieldName, mandatory, readOnly, hidden) {
  var rule = new GlideRecord("sys_data_policy_rule")
  rule.initialize()
  rule.setValue("sys_data_policy", policySysId)
  rule.setValue("field", fieldName)
  rule.setValue("mandatory", mandatory)
  rule.setValue("read_only", readOnly)
  rule.setValue("visible", !hidden)
  return rule.insert()
}

Complex Data Policy

javascript
// Data policy with scripted condition (ES5 ONLY!)
var policy = new GlideRecord("sys_data_policy2")
policy.initialize()

policy.setValue("model_table", "change_request")
policy.setValue("short_description", "High Risk Change Requirements")
policy.setValue("active", true)

// Use scripted condition for complex logic
policy.setValue("use_as_condition", true)
policy.setValue(
  "script",
  "(function checkCondition(current) {\n" +
    "    // High risk changes require additional fields\n" +
    '    if (current.risk == "high") {\n' +
    "        return true;\n" +
    "    }\n" +
    "    \n" +
    "    // Also apply to changes affecting critical CIs\n" +
    "    if (current.cmdb_ci) {\n" +
    "        var ci = current.cmdb_ci.getRefRecord();\n" +
    '        if (ci.business_criticality == "1 - most critical") {\n' +
    "            return true;\n" +
    "        }\n" +
    "    }\n" +
    "    \n" +
    "    return false;\n" +
    "})(current);",
)

var policySysId = policy.insert()

// Require additional documentation for high risk
addDataPolicyRule(policySysId, "implementation_plan", true, false, false)
addDataPolicyRule(policySysId, "backout_plan", true, false, false)
addDataPolicyRule(policySysId, "test_plan", true, false, false)
addDataPolicyRule(policySysId, "justification", true, false, false)

Field Validation (ES5)

Dictionary Attribute Validation

javascript
// Add validation to dictionary field (ES5 ONLY!)
var field = new GlideRecord("sys_dictionary")
if (field.get("name", "incident").get("element", "u_email")) {
  // Add regex validation
  field.setValue("attributes", "validate=email")
  field.update()
}

// Common validation attributes
var VALIDATION_ATTRIBUTES = {
  EMAIL: "validate=email",
  PHONE: "validate=phone_number",
  URL: "validate=url",
  CUSTOM: "validate=script", // Uses script in Calculated Value
}

Script Validation

javascript
// Calculated field with validation (ES5 ONLY!)
// Set in Dictionary > Calculated Value

// Check phone format
;(function calculate() {
  var phone = current.getValue("u_phone")
  if (!phone) return ""

  // Format validation
  var phonePattern = /^\+?[1-9]\d{1,14}$/
  if (!phonePattern.test(phone.replace(/[\s\-\(\)]/g, ""))) {
    gs.addErrorMessage("Invalid phone number format")
    return ""
  }

  return phone
})()

Schema Queries (ES5)

Get Table Fields

javascript
// Get all fields for a table (ES5 ONLY!)
function getTableFields(tableName) {
  var fields = []

  var dict = new GlideRecord("sys_dictionary")
  dict.addQuery("name", tableName)
  dict.addQuery("internal_type", "!=", "collection")
  dict.addQuery("active", true)
  dict.orderBy("element")
  dict.query()

  while (dict.next()) {
    fields.push({
      name: dict.getValue("element"),
      label: dict.getValue("column_label"),
      type: dict.getValue("internal_type"),
      mandatory: dict.getValue("mandatory") === "true",
      reference: dict.getValue("reference"),
      maxLength: dict.getValue("max_length"),
    })
  }

  return fields
}

Check Field Exists

javascript
// Check if field exists on table (ES5 ONLY!)
function fieldExists(tableName, fieldName) {
  var dict = new GlideRecord("sys_dictionary")
  dict.addQuery("name", tableName)
  dict.addQuery("element", fieldName)
  dict.query()
  return dict.hasNext()
}

MCP Tool Integration

Available Tools

ToolPurpose
snow_query_tableQuery dictionary & data policies
snow_discover_table_fieldsGet field definitions
snow_execute_scriptTest dictionary scripts

Example Workflow

javascript
// 1. Get table fields
await snow_discover_table_fields({
  table_name: "incident",
})

// 2. Query data policies
await snow_query_table({
  table: "sys_data_policy2",
  query: "model_table=incident^active=true",
  fields: "short_description,conditions,apply_to_client",
})

// 3. Check dictionary overrides
await snow_query_table({
  table: "sys_dictionary_override",
  query: "name=u_custom_table",
  fields: "base_element,column_label,mandatory,read_only",
})

Best Practices

  1. Schema Planning - Design before implementation
  2. Field Naming - u_ prefix for custom fields
  3. Data Types - Use appropriate types
  4. Mandatory Fields - Only when truly required
  5. Data Policies - Enforce business rules
  6. Performance - Avoid complex calculated fields
  7. Documentation - Document custom schema
  8. ES5 Only - No modern JavaScript syntax

Frequently asked questions

What does the Data Policies AI skill do?

Manage ServiceNow dictionary (sys_dictionary), table/field creation, choice lists, dictionary overrides, and sys_data_policy2 rules that enforce mandatory/read-only/visible field behavior on the data layer.

Why use Data Policies on TypingMind?

Because you install it once and use it with any model. Data Policies 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 Data Policies in TypingMind?

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

Which AI models can use Data Policies?

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 Data Policies?

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

Is the Data Policies 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 👇