Dry-run a skill once

POST

/skills/{action_id}/test

• Production
• QA

SPENDS NOTHING. One DRY run from a saved case or ad-hoc inputs: returns the resolved prompt (llm skills) or the unsent request with secrets masked (api skills). Never calls a model, never sends, never writes an execution.

Authorizations

• BearerAuth

Parameters

Path Parameters

action_id

required

Skill (action) id.

string

>= 1 characters

Skill (action) id.

Header Parameters

X-Target-Org-Id

Any of:

string

string

null

null

Request Body ^required

Voice SkillTestRunRequest: one dry run, from a saved case OR ad-hoc inputs.

object

assertion_config

Any of:

object

object

key

additional properties

any

null

null

assertion_type

Any of:

string

string

Allowed values: exact contains llm_judge

null

null

expected_output

Any of:

unknown

null

null

input_data

Any of:

object

object

key

additional properties

any

null

null

test_case_id

Any of:

string

string

null

null

triggered_by

Any of:

string

string

null

null

Responses

200

Successful Response

object

data

required

One voice object - a collection, an agent, a route, a chat.

Open-shaped: voice adds fields to these bodies on its own release cadence and a dropped-or-added key must not be a 500 in this service.

object

key

additional properties

any

pagination

Any of:

PaginationMeta

object

has_next

required

Whether there are more pages

boolean

limit

required

Items per page

integer

next_cursor

Any of:

string

string

null

null

notes

Any of:

Array<string>

Array<string>

null

null

page

required

Current page number (1-indexed)

integer

total

required

Total number of items

integer

total_available

Any of:

integer

integer

null

null

total_is_lower_bound

Any of:

boolean

boolean

null

null

null

null

422

Validation Error

object

detail

Array<object>

object

loc

required

Array

msg

required

string

type

required

string