Research Product Problems With Six-Layer Analysis

Guides you through a structured, six-layer research process that produces a multi-perspective problem definition before solution work begins. Each layer examines the problem through a different lens: what customers say, how the ecosystem interprets the problem, invisible behavioral barriers, what has been tried and why it failed, new technical capabilities that enable solutions, and what you can realistically change. Teams that skip systematic research confuse symptoms with root causes and build solutions to the wrong problem.

You invoke the skill with your product domain and select Quick mode (desk research, 2-4 hours across five 10-minute layers) or Full mode (primary research with interviews and deep analysis, spanning multiple sessions). Claude works through all six layers in sequence, gathering evidence via web search and document fetching, showing you findings and synthesis after each layer. You can pause between layers, ask follow-up questions, or re-run individual layers to update perspectives. After all six complete, the skill produces a unified problem statement grounded in all six lenses, a solution direction pointing toward feasible opportunities, and a convergence analysis showing patterns and tensions across layers. Output: 14-20 research documents including raw research quotes, layer syntheses, cross-layer synthesis, problem statement, solution direction, and indexed sources.

Requires Claude Code or Claude with code interpreter support, because the skill uses WebSearch and WebFetch to gather live research data during execution. Layer output is saved as markdown documents to disk (default location is docs/research/ in your project), allowing you to pause between layers and resume without losing work. Completed layers are preserved; if a session is interrupted, you can restart from the next incomplete layer.