What problem does it solve? Committing to a full implementation before knowing whether an idea is technically feasible wastes time and money. This Skill structures quick, disposable experiments (spikes) that answer concrete feasibility questions with observable evidence, so you can kill bad ideas early and proceed with confidence on good ones. ## Core Features & Use Cases - Structured Spike Loop: Decomposes an idea into 2-5 independent feasibility questions framed as Given/When/Then, ordered by risk so the idea-killing question runs first. - Comparison Spikes: Builds competing approaches side by side (e.g., pdfjs vs camelot for PDF parsing) and produces a head-to-head verdict table with a clear winner recommendation. - Evidence-Based Verdicts: Every spike closes with a VALIDATED, PARTIAL, or INVALIDATED verdict documenting what worked, what failed, surprises, and recommendations for the real build. - Use Case: Before building a real-time chat feature, spike whether websocket streaming delivers LLM tokens to the client under 100ms, then throw the prototype away and start the real implementation informed by the results. ## Quick Start Ask the agent to spike out whether your idea is feasible, for example by saying "spike whether I can stream LLM tokens over websockets with under 100ms latency before I commit to this architecture."
