---
sourceDocument: Brazil Enable AI
sourceDocumentLink: https://www.servicenow.com/docs/r/intelligent-experiences

 Release :

    - brazil

ft:locale :

    - en-US

ft:publication_title :

    - Brazil Enable AI

ft:clusterId :

    - platai

bundleId :

    - platai

workflow :

    - Platform


---

# Clone and edit a ServiceNow skill

# Clone and edit a ServiceNow skill {#ariaid-title1}

Release version: Brazil  
Updated September 23, 2026  
![](https://www.servicenow.com/docs/portal-asset/ico-clock) 2 minutes to read  
Clone an eligible skill provided in ServiceNow Otto applications in AI Skill Kit so that you can edit its prompt or change its AI service provider. Editing the prompt lets you control the format and content of the large language model (LLM) response.

## Before you begin

Role required: sn_skill_builder.admin

## Procedure

1. Navigate to AllAI Skill KitHome.
2. Select ServiceNow skills
3. Select the ServiceNow skill that you want to clone.
4. Select Clone Skill.
5. On the form, fill in the fields.  
   {#clone-and-edit-servicenow-skill__table_chg_qth_lcc__entry__2}

   | Field | Description |
   |-|-|
   | Skill name | Name of the skill. |
   | Description | Description of the skill. |
   | Default provider | Available providers: * Now LLM Service * External LLM * Spokes * Custom LLMFor more information on setting up a custom large language model (LLM), see [Configure a generic large language model (LLM) connector](https://www.servicenow.com/docs/rcXZxDkgb0dTbdO5zMrroA "Connect an external LLM to the ServiceNow AI Platform by using a generic LLM connector. With a connector, you can write your own prompts to send to the LLM and create your own generative AI capabilities.") {#clone-and-edit-servicenow-skill__ul_oxt_tth_lcc} {#clone-and-edit-servicenow-skill__ul_nxt_tth_lcc} Available prebuilt spokes that enable you to connect with an external LLM: * Microsoft Azure OpenAI Generative AI Spoke * OpenAI Generative AI Spoke * Aleph Alpha * IBM watsonx * Google Gemini (MakerSuite and Vertex AI) {#clone-and-edit-servicenow-skill__ul_jss_vth_lcc} Note: The spokes don't consume Integration Hub transactions. The spokes consume assists. |
   | Provider API | Provider of the API for the selected LLM. |
   [Table 1. Clone skill form]

   {#clone-and-edit-servicenow-skill__table_chg_qth_lcc}
6. Select Clone.  
   Note:  
   When you clone a skill, you can't change the skill outputs, tools, or deployment settings.
7. Select the edit icon to add skill inputs.  
   {#clone-and-edit-servicenow-skill__table_u5k_ygv_mhc__entry__2}

   | Section | Description |
   |-|-|
   | Base input table fields | Each skill relies on a base input table and input fields with descriptions to provide context for the LLM to generate a response. |
   | Rule conditions | Rule conditions determine when the input template is used. By default, record state determines which input template the LLM uses. |
   | Additional input data sources | You can add input data sources such as related tables, activity streams, and relationships to provide more context to the LLM. You can also add rule conditions to these additional data sources. |
   [Table 2. Edit inputs form]

   {#clone-and-edit-servicenow-skill__table_u5k_ygv_mhc}
8. **Optional:** Select Clone prompt to edit the prompt.  
   The list shows all prompts that use the same supporting skill for each provider.
9. Add Prompt usage conditions.  
   Prompt usage conditions determine when a prompt runs.
10. To test the prompt, select Run test and add test values.
11. Select the Skill settings tab.
12. **Optional:** In the General information section, select the toggle to change the default provider.

## What to do next

Create your skill prompt. To learn more about creating a prompt, see [Create a prompt](https://www.servicenow.com/docs/aCf5iZh_zstaWO9wW1FCeQ "After you create a custom skill, create a prompt. The prompt defines the instructions that the skill sends to the LLM and the skill inputs that it uses.").

After you clone and edit the skill and prompt, you can evaluate your prompt. To learn more about evaluating a prompt, see [Evaluate a prompt](https://www.servicenow.com/docs/dmWxQaJDYd4ukGuGzxtfRA "Use the AI Skill Kit evaluation tools to measure how your skill prompts perform against a dataset, using automated metrics and human feedback.").

*[\>]: and then