> For the complete documentation index, see [llms.txt](https://docs.duplocloud.com/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.duplocloud.com/docs/marketplace-agents/aws-extension/customizing/skill-mapping.md).

# Skill Mapping

Override the default provisioning skill for a specific resource type with a custom skill.

Skill Mapping lets you override the platform default skill for a specific ticket origin and sub type. When a ticket is created that matches the override, the AI agent loads your custom skill instead of the platform default — without any change to the resource configuration or ticket setup.

For the Infrastructure Agent, this means you can replace a default infrastructure provisioning skill with one that incorporates your organization's specific requirements: custom tagging, different templates, additional compliance checks, or modified approval workflows.

## How it works

Each cloud has its own platform default skill for infrastructure provisioning. It handles provisioning and deprovisioning for Networks, Clusters, and Resource Groups on that cloud:

| Cloud                                                                                                            | Default skill       |
| ---------------------------------------------------------------------------------------------------------------- | ------------------- |
| AWS                                                                                                              | `duplo-aws-infra`   |
| Azure                                                                                                            | `duplo-azure-infra` |
| Oracle Cloud (OCI)                                                                                               | `duplo-oci-infra`   |
| When a provisioning ticket is created for any of these resource types, the agent loads this skill automatically. |                     |

With Skill Mapping, you can:

* Create a custom skill that extends or replaces the default skill, for example `duplo-aws-infra`
* Map it as an override for a specific resource type (e.g. Network Baseline provisioning only)
* All subsequent provisioning tickets for that resource type will use your custom skill instead

The platform default continues to apply to any resource type without an override.

## Setting up a Skill Mapping Override

For the full step-by-step guide, see [Platform Skills and Overrides](https://docs.duplocloud.com/docs/concepts/skills/platform-skills-and-overrides.md).

{% content-ref url="/pages/UuIqQI84Dm3Z4zvkIvo8" %}
[Platform Skills and Overrides](https://docs.duplocloud.com/docs/concepts/skills/platform-skills-and-overrides.md)
{% endcontent-ref %}

## Example: Enforcing a Tagging Policy

This example uses AWS. Your organization requires that all AWS resources are tagged with `team`, `cost-center`, and `environment`. The platform default skill does not know about these requirements.

{% stepper %}
{% step %}

### Fork the default skill

Copy the `duplo-aws-infra` skill and add tagging instructions to the network and cluster provisioning sections.
{% endstep %}

{% step %}

### Add a Skill Mapping override

Navigate to **AI Admin → Skills → Skill Mapping**, click **Add Override**, and add an override mapping the Network Baseline and Cluster Baseline origin types to your custom skill.
{% endstep %}

{% step %}

### Verify

Create a new Network Baseline provisioning ticket. The agent loads your custom skill and enforces the tagging requirement during provisioning.
{% endstep %}
{% endstepper %}


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.duplocloud.com/docs/marketplace-agents/aws-extension/customizing/skill-mapping.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
