What problem does it solve? It turns an OpenSpec change's task list into actual code by guiding the AI through selecting the change, reading its context files, implementing each pending task, and tracking progress until completion. ## Core Features & Use Cases - Change Selection and Status: Resolves the target change by name, context, or interactive prompt, then reads schema, progress, and task state via openspec status and openspec instructions apply. - Guided Task Implementation: Reads all context files (proposal, specs, design, tasks), implements each pending task with minimal scoped edits, and marks tasks complete in the tasks file. - Guardrails and Pause Handling: Pauses on ambiguity, design issues, scope creep, or blockers instead of guessing, and reports structured progress output. - Use Case: A developer has an approved OpenSpec change with 7 tasks and asks the AI to implement it; the skill works through each task, checks them off, and suggests archiving when done. ## Quick Start Ask the AI to implement the OpenSpec change named add-auth by running the openspec-apply-change skill with that change name.