spike

Run disposable feasibility experiments and document VALIDATED, PARTIAL, or INVALIDATED verdicts.

Updated May 26, 2026
One-click install
npx skills add https://github.com/ruiyangruiyi/hermes-agent --skill spike-ruiyangruiyi
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: spike
Source: https://github.com/ruiyangruiyi/hermes-agent/tree/main/skills/software-development/spike
Command: npx skills add https://github.com/ruiyangruiyi/hermes-agent --skill spike-ruiyangruiyi

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you de-risk product and engineering decisions by quickly testing whether an idea is feasible before investing in a full build.

Core Features & Use Cases

  • Feasibility-first spike loop: Decompose an idea into 2–5 targeted questions, research just enough to choose an approach, build a minimal runnable prototype, then deliver a verdict.
  • Risk-ordered experimentation: Start with the most idea-killing unknowns, especially where unknown constraints would make a full build fail.
  • Comparison spikes: Run parallel alternatives (e.g., two PDF parsing approaches) and produce a head-to-head winner based on observable evidence.

Quick Start

Tell the agent what you want to prototype (for example: "Spike whether websocket streaming meets my <100ms chunk requirement for my client").

Frequently Asked Questions about spike

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I test if a software idea is feasible before committing to a full build?

A feasibility spike de-risks software ideas by decomposing them into 2-5 targeted questions, building minimal runnable prototypes, and delivering an evidence-based VALIDATED, PARTIAL, or INVALIDATED verdict before full investment.

What is the best way to compare two technical approaches for the same feature?

Run comparison spikes by building parallel minimal prototypes for each approach, then produce a head-to-head winner based on observable evidence from the interactive prototypes to determine the optimal architecture.

How do I structure feasibility testing questions for software planning?

Decompose your software planning idea into 2-5 targeted Given/When/Then feasibility questions, prioritizing the most idea-killing unknowns first to validate architecture constraints before building.

Can I use spike methodology for architecture validation and tool selection?

Yes, you can use spikes for architecture validation and tool selection by performing minimal research to choose an approach, building an observable interactive prototype, and documenting the outcome.

When should I not use a disposable prototype for software planning?

Avoid using disposable prototypes when your software planning questions are well-understood and lack unknown constraints, as the spike loop is designed specifically to de-risk high-uncertainty feasibility decisions.