Our review

Creates and manages multi-step AI workflows by defining, implementing, and improving DeepWork jobs.

Strengths

Automates complex processes through chained steps
Interactive job specification generation
Learns from conversations to refine instructions
Uses Skill tool to prevent copy-paste errors

Limitations

Requires prior understanding of DeepWork workflows
Depends on the Skill tool for correct execution
Can be rigid if steps must follow a fixed order

When to use it

Use this skill when you need to define a new multi-step workflow or improve an existing job based on execution feedback.

When not to use it

Do not use for simple one-step tasks or when you want to run an isolated command without workflow structure.

Examples

Define a new job

/deepwork_jobs define I need a workflow that first scans a codebase for TODOs, then generates a report, and finally creates issues in a tracker.

Learn from a job run

/deepwork_jobs learn Review the last conversation where we ran the 'report_gen' job and improve its instructions.

Implement from spec

/deepwork_jobs implement Generate the step instruction files for the job spec I just defined.

name: deepwork_jobs description: "Creates and manages multi-step AI workflows. Use when defining, implementing, or improving DeepWork jobs."

deepwork_jobs

Multi-step workflow: Creates and manages multi-step AI workflows. Use when defining, implementing, or improving DeepWork jobs.

CRITICAL: Always invoke steps using the Skill tool. Never copy/paste step instructions directly.

Core commands for managing DeepWork jobs. These commands help you define new multi-step workflows and learn from running them.

The define command guides you through an interactive process to create a new job by asking structured questions about your workflow, understanding each step's inputs and outputs, and generating all necessary files.

The learn command reflects on conversations where DeepWork jobs were run, identifies confusion or inefficiencies, and improves job instructions. It also captures bespoke learnings specific to the current run into AGENTS.md files in the working folder.

Available Steps

define - Creates a job.yml specification by gathering workflow requirements through structured questions. Use when starting a new multi-step workflow.
review_job_spec - Reviews job.yml against quality criteria using a sub-agent for unbiased validation. Use after defining a job specification. (requires: define)
implement - Generates step instruction files and syncs slash commands from the job.yml specification. Use after job spec review passes. (requires: review_job_spec)
learn - Analyzes conversation history to improve job instructions and capture learnings. Use after running a job to refine it.

Execution Instructions

Step 1: Analyze Intent

Parse any text following /deepwork_jobs to determine user intent:

"define" or related terms → start at deepwork_jobs.define
"review_job_spec" or related terms → start at deepwork_jobs.review_job_spec
"implement" or related terms → start at deepwork_jobs.implement
"learn" or related terms → start at deepwork_jobs.learn

Step 2: Invoke Starting Step

Use the Skill tool to invoke the identified starting step:

Skill tool: deepwork_jobs.define

Step 3: Continue Workflow Automatically

After each step completes:

Check if there's a next step in the sequence
Invoke the next step using the Skill tool
Repeat until workflow is complete or user intervenes

Handling Ambiguous Intent

If user intent is unclear, use AskUserQuestion to clarify:

Present available steps as numbered options
Let user select the starting point

Guardrails

Do NOT copy/paste step instructions directly; always use the Skill tool to invoke steps
Do NOT skip steps in the workflow unless the user explicitly requests it
Do NOT proceed to the next step if the current step's outputs are incomplete
Do NOT make assumptions about user intent; ask for clarification when ambiguous

Context Files

Job definition: .deepwork/jobs/deepwork_jobs/job.yml

DeepWork Jobs Management

Recommended for