spike

Decompose complex ideas into executable spikes with feasibility verdicts.

Updated May 2, 2026
One-click install
npx skills add https://github.com/AlvaroBiano/hermes-agent --skill spike-alvarobiano
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: spike
Source: https://github.com/AlvaroBiano/hermes-agent/tree/main/skills/software-development/spike
Command: npx skills add https://github.com/AlvaroBiano/hermes-agent --skill spike-alvarobiano

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Spikes provide a lightweight, disposable way to validate ideas before committing to a full build, reducing risk and wasted effort.

Core Features & Use Cases

  • Decompose ideas into small, testable spikes with Given/When/Then framing.
  • Align, research, build, and verdict workflows to iteratively validate feasibility.
  • Produce a concrete spike artifact (README + code skeleton) that can be discarded or extended into a real project.

Quick Start

Outline a single spike plan and run a tiny, observable experiment to validate the idea.

Frequently Asked Questions about spike

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

FAQPage Schema
What is a spike in product development and when should I use one?

A spike is a throwaway experiment to validate feasibility before committing to a full build. Use spikes to reduce risk and wasted effort when evaluating complex product ideas, architecture choices, or experimental features.

How do I validate feasibility for a new architecture choice?

Validate architecture feasibility by decomposing the idea into 2–5 spike hypotheses with Given/When/Then framing. Follow the Decompose, Align, Research, Build, and Verdict workflow to generate a clear pass or fail verdict for each hypothesis.

How do I plan and structure a prototype experiment?

Plan a prototype experiment by outlining a single spike plan and running a tiny, observable test. The workflow generates a spikes/ directory containing per-spike READMEs and a minimal, portable artifact to guide your decision making.

Can I use throwaway experiments to test multiple product ideas at once?

Yes, you can test multiple product ideas by decomposing a complex concept into 2–5 executable, disposable spikes. Each spike receives its own README and a clear verdict, allowing rapid parallel validation without committing to full builds.

What is the difference between a spike and a full feature build?

A spike is a lightweight, disposable experiment designed purely to validate feasibility, whereas a full build is a committed implementation. Spikes produce a code skeleton and artifact that can be discarded or later extended into a real project.

What are the limitations of using disposable spikes for product planning?

Spikes are throwaway experiments meant for validation, not production. They produce minimal, portable artifacts and code skeletons that must be discarded or fully rebuilt, making them unsuitable as final deliverables for production-ready features.