# AgentSkillScriptDefinition

> Tracon documentation. Tracon is a .NET package family that adds a control
> plane on Microsoft Agent Framework, published as NuGet packages that run
> inside your own ASP.NET Core application.
>
> Page: https://tracon.dev/http-api/schemas/agentskillscriptdefinition/
> Summary: OpenAPI request or response schema for AgentSkillScriptDefinition, including required fields, defaults, constraints, and linked nested types.

[← All HTTP schemas](/http-api/schemas/)

A server-executable script stored together with an AgentSkillDefinition.

**Shape:** `object`

| Property | Required | Type | Description | Rules |
|---|---|---|---|---|
| `name` | yes | `string` | The script name, unique within the skill. | — |
| `description` | no | `string` | A description telling the model what the script does. | — |
| `extension` | yes | `string` | The file extension (without the dot, for example `py`). The interpreter is selected from the allowlist through this value. | — |
| `content` | yes | `string` | The script's source text. | — |
| `parametersSchema` | no | `string` | The argument schema reported to the model. Must be a valid JSON Schema object; if `null`, the script is called with no arguments. | — |
| `contentHash` | no | `string` | The hash of what runs: the extension, the content, and the argument schema. Computed, never stored; a value sent in a request is ignored. | — |
