What problem does it solve? Before investing days in a real implementation, you often need to know whether an idea is even technically feasible — will websockets stream fast enough, can this library parse your PDFs, does approach A beat approach B. This Skill structures that uncertainty into small, disposable experiments with clear verdicts, so you stop guessing and start deciding with evidence. ## Core Features & Use Cases - Decompose ideas into feasibility questions: Breaks a vague idea into 2-5 independent spikes framed as Given/When/Then statements, ordered by risk so the idea-killing question runs first. - Guided research and build loop: For each spike, surfaces competing libraries or approaches, picks one with justification, then builds a minimal runnable prototype (CLI, HTML page, or single endpoint) in its own spikes/NNN-name/ directory. - Comparison spikes and verdicts: Runs head-to-head variants (e.g., pdfjs vs camelot) with parallel subagent delegation, then records a VALIDATED, PARTIAL, or INVALIDATED verdict with surprises and recommendations in each spike's README. - Use Case: You want to add real-time streaming to your app but aren't sure websockets will meet your latency target. The Skill creates spikes/001-websocket-streaming/, builds a runnable prototype, tests edge cases, and delivers a verdict with a recommendation for the real build. ## Quick Start Ask the agent to spike whether your chosen library can handle your workload before you commit to building the feature.
