What problem does it solve? It answers feasibility questions about an idea before you invest in production code, by building small disposable prototypes that produce observable evidence instead of assumptions. ## Core Features & Use Cases - Decompose ideas into spikes: Breaks a vague idea into 2-5 independent feasibility questions framed as Given/When/Then statements, ordered by risk. - Research then build: Surveys competing libraries and approaches, picks one, and builds a runnable CLI, HTML page, or small server per spike in a spikes/ directory. - Comparison spikes and verdicts: Runs parallel head-to-head variants (e.g., pdfjs vs camelot) and closes each spike with a VALIDATED, PARTIAL, or INVALIDATED verdict plus a recommendation for the real build. - Use Case: Before committing to a websocket-based streaming architecture, spike whether LLM token chunks reach the client under 100ms, then throw the code away once the verdict is in. ## Quick Start Ask the agent to spike whether your idea is feasible, for example: "Spike whether I can stream LLM tokens over websockets to the browser with low latency."
