deepwork_jobs.define

To define a multi-step AI workflow, you need a structured YAML schema that captures goals, inputs, outputs, and dependencies. This skill interactively gathers these requirements and automatically generates a complete job.yml specification conforming to the DeepWork schema.

Generating a job.yml for automation workflows requires capturing precise inputs, dependencies, and stop-hooks. By undergoing structured questioning about your project goals and success criteria, you obtain a schema-compliant YAML file with proper doc-spec references and changelog entries for future maintenance.

Interactive questioning structures workflow definitions by systematically extracting high-level goals, major phases, and deliverables from the user. This discovery process ensures the resulting AI job specification rigorously defines all necessary inputs, outputs, and dependencies without missing critical configuration details.

Yes, you can add quality checks and stop-hooks to your workflow YAML. The definition process provides specific guidance for integrating these quality assurance measures, ensuring your multi-step AI workflow includes proper validation and conditional stopping points.

No, you do not need prior knowledge of the DeepWork schema to define a new job spec. The skill guides you through a structured discovery process asking for your project goal and deliverables, then automatically handles the YAML formatting and schema compliance for you.

You should use an interactive job.yml generator instead of writing YAML manually when starting new multi-step workflows that require rigorous definitions. It prevents configuration errors by ensuring all inputs, outputs, dependencies, and doc-spec references are captured through guided questioning rather than manual coding.