spike

Validate idea feasibility through throwaway prototypes and risk-ordered experiments.

Updated May 14, 2026
One-click install
npx skills add https://github.com/SethyPagna/Secretary-Jarvis --skill spike-sethypagna
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: spike
Source: https://github.com/SethyPagna/Secretary-Jarvis/tree/main/src/capabilities/skills/software-development/spike
Command: npx skills add https://github.com/SethyPagna/Secretary-Jarvis --skill spike-sethypagna

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Use this Skill when you need to test whether an idea is worth building before you invest in a full implementation. It turns uncertainty into small, disposable experiments so you can confirm feasibility, compare approaches, and uncover hidden risks early.

Core Features & Use Cases

  • Breaks vague ideas into 2-5 focused feasibility questions.
  • Guides research, prototype building, and evidence-based verdicts.
  • Supports comparison spikes for competing approaches and frontier mode for choosing the next risk to test.
  • Useful for validating integrations, parsing strategies, streaming behavior, or other high-uncertainty technical choices.

Quick Start

Ask the Spike skill to break your idea into risk-ordered feasibility questions, research the best approach, build a throwaway prototype, and return a verdict.

Frequently Asked Questions about spike

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

FAQPage Schema
How do I validate the feasibility of an idea before committing to a full build?

To validate feasibility before a full build, use a decompose-research-build-verdict workflow to create throwaway prototypes that uncover hidden risks and confirm whether an idea is worth implementing.

What is a spike in software engineering and when do I need it?

A spike is a time-boxed experiment used to test technical feasibility and reduce uncertainty. You need it when evaluating high-uncertainty features, integrations, or implementation approaches before full development.

How do I compare competing technical approaches for an integration?

Comparing competing approaches involves running comparison spikes to build disposable prototypes for each option, allowing you to evaluate parsing strategies or integration behaviors and return an evidence-based verdict.

Can I test streaming behavior with a throwaway prototype?

Yes, you can test streaming behavior using throwaway prototypes designed to validate specific technical choices. This process isolates uncertain integrations and returns explicit validation outcomes without requiring a full build.

What is the best way to break down a vague feature idea for testing?

The best way to break down a vague idea is to decompose it into two to five focused, risk-ordered feasibility questions, prioritizing the highest uncertainty areas for prototype testing first.