What problem does it solve? Large or ambiguous work items from Azure DevOps, Jira, or GitHub are hard to hand to a fast interactive coding agent. This Skill audits a work item, inspects the relevant repository areas, and breaks it into small, independent, verifiable implementation tasks sized for Codex Spark. ## Core Features & Use Cases - Work-item audit: Reads title, description, acceptance criteria, comments, and linked artifacts, then inspects affected code boundaries and test coverage to establish evidence. - Spark suitability test: Classifies each task against criteria like one-sentence outcomes, narrow file scope, simple verification commands, and low blast radius, flagging long-horizon or human-decision work separately. - Structured backlog output: Produces a dependency-ordered task table with goals, scope, acceptance checks, and ready-to-send Spark prompts, plus an execution order with parallelizable tasks. - Use Case: Paste a Jira story asking to add a new API endpoint and receive a breakdown separating contract definition, implementation, focused tests, and documentation, each with its own Spark prompt. ## Quick Start Ask the agent to audit this work item and break it into Spark-sized implementation tasks with acceptance checks and prompts.
