What problem does it solve? It turns an OpenSpec change's task list into working code by guiding the AI through selecting the change, reading its context files, implementing each task, and tracking progress until completion. ## Core Features & Use Cases - Change Selection: Picks a change by name, conversation context, or by listing available changes when ambiguous, with support for named OpenSpec stores via --store. - Status-Aware Workflow: Reads openspec status and openspec instructions apply JSON output to understand the schema, progress, context files, and blocked or all-done states. - Task Implementation Loop: Works through pending tasks one by one, marking each - [x] in the tasks file, and pauses on ambiguity, design issues, or scope creep instead of guessing. - Use Case: After drafting a spec-driven change with proposal, design, and tasks, invoke this skill to have the AI implement all seven tasks sequentially and report "7/7 tasks complete" with an archive suggestion. ## Quick Start Ask the AI to implement the tasks from your OpenSpec change, optionally naming the change, for example: start implementing the add-auth change.
