What problem does it solve? Teams often commit to architectures or libraries before knowing whether they actually work, wasting days on dead ends. This Skill structures quick, disposable experiments that answer feasibility questions with evidence before any production code is written. ## Core Features & Use Cases - Decompose ideas into spikes: Break a vague idea into 2-5 independent feasibility questions framed as Given/When/Then statements, ordered by risk. - Comparison spikes: Build competing approaches side by side (e.g., pdfjs vs camelot for PDF parsing) and produce a head-to-head verdict table. - Structured verdicts: Every spike ends with a VALIDATED, PARTIAL, or INVALIDATED verdict documenting what worked, what failed, 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 with confidence. ## Quick Start Ask the agent to spike whether your chosen library or approach actually works for your use case before you commit to building the real feature.
