/execute command lets you run a task directly from a YAML configuration file. Instead of entering parameters interactively, you define everything in a config file and execute it in one step. This is useful for reproducible experiments, batch processing, and reusing task configurations.
Usage
Only
.yaml and .yml files are supported. You must provide exactly one file path with no additional key=value arguments.Configuration File Structure
The configuration file is a YAML mapping that must include atask field and any required parameters for that task.
Required Field
Task-Specific Parameters
The remaining fields depend on the task type. Refer to each task’s documentation for required and optional parameters:- Data Generate -
data-generate - Data Repair -
data-repair - Data Audit -
data-audit - Schema Polish -
schema-polish - Schema-Triggered Patch -
schema-triggered-patch
Example Configuration
Here is an example configuration file for agenerate task:
Validation
Before executing, the CLI validates your configuration file:- File format - Must be a valid
.yamlor.ymlfile - Required
taskfield - Thetaskfield must be present and set to a supported task - Unknown fields - Any field not recognized for the specified task causes an error
- Required parameters - All required parameters for the task must be provided
- Schema source exclusivity - If both
schema_fileandmcp_server_urlare provided, the CLI reports a conflict
Validation Error Examples
Missing task field:Confirmation Flow
After validation passes, the/execute command enters the same interactive confirmation flow as any other task. You can review the configuration, modify parameters, or confirm execution.