What problem does it solve? Turning raw research material into a structured, measurable learning plan is difficult: learners often end up with flat syllabi that lack timelines, dependencies, and objective checkpoints. This Skill orchestrates an adversarial research loop that converts NotebookLM sources into a navigate-ready roadmap aligned with a specific success metric and time budget. ## Core Features & Use Cases - Adversarial Multi-Agent Research: Spawns Theorist, Practitioner, and Auditor subagents to interrogate a NotebookLM RAG source from logic, workflow, and failure-mode perspectives. - Mastery Stack Synthesis: Fuses persona reports into topic modules with difficulty ratings, time estimates, dependencies, and binary pass/fail checkpoints. - Scope & Budget Enforcement: A Re-Planner agent prunes or demotes topics that do not serve the success metric within the time budget, preventing scope creep. - Use Case: A user with 20 hours over 4 weeks wants to reach operational competency in a new framework. After loading sources into NotebookLM, this Skill produces a phased roadmap with weekly timelines, dependency-ordered topics, and measurable milestones. ## Quick Start Run the roadmap skill with my subject 'Kubernetes networking' to build a time-bound learning roadmap from my NotebookLM research sources.
