What problem does it solve? Turning a vague task or ticket into an actionable implementation plan usually requires hours of codebase exploration, requirement clarification, and design decisions. This Skill automates that process by researching the codebase, asking targeted clarifying questions scaled to task complexity, and producing a phased, verifiable plan document. ## Core Features & Use Cases - Adaptive Questioning: Scales the number and depth of clarifying questions based on task complexity (LOW/MEDIUM/HIGH) and upstream artifacts like frame briefs and research docs, avoiding redundant questions. - Parallel Codebase Research: Spawns Explore and general-purpose sub-agents to map relevant files, trace data flow, and surface existing patterns before writing the plan. - Structured Plan Output: Writes a phased plan to context/changes/<change-id>/plan.md with success criteria, a two-page plan brief, and a machine-readable Progress section for execution tracking. - Use Case: Given a ticket to add OAuth login, the Skill reads prior research, asks a handful of architecture and edge-case questions, then produces a multi-phase plan with automated and manual verification steps ready for implementation. ## Quick Start Invoke the skill with a change id or task description, for example: create an implementation plan for the oauth-login change using the existing research document.
