spike

Coordinate spike experiments to validate ideas and issue verdicts.

12|2|Updated Feb 2, 2020
One-click install
npx skills add https://github.com/servitola/dotfiles --skill spike-servitola
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: spike
Source: https://github.com/servitola/dotfiles/tree/main/claude-code/skills/spike
Command: npx skills add https://github.com/servitola/dotfiles --skill spike-servitola

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides a structured approach to quickly validate ideas through disposable spike experiments, generating concrete artifacts and a verdict to guide decision-making.

Core Features & Use Cases

  • Structured spike workflow (decompose, align, research, build, verdict) to surface core feasibility questions.
  • Standalone spike directories under spikes/ with README and outputs to illustrate results.
  • Safe, throwaway experiments designed for learning, iteration, and fast decision-making.

Quick Start

Create a new spikes/NNN-descriptive-name/ directory and write a README.md documenting the spike question, approach, and verdict.

Frequently Asked Questions about spike

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

FAQPage Schema
How do I validate technical feasibility before committing to a full implementation?

Use a structured spike workflow to decompose ideas, research feasible approaches, build observable throwaway artifacts, and issue a formal verdict across multiple spikes to guide fast decision-making.

What is the best way to structure disposable prototype experiments for rapid learning?

Structure disposable prototype experiments by creating standalone spike directories under a spikes/ folder, using a README to document the spike question, approach, and verdict for repeatability.

How do I run multiple spike experiments to compare different approaches?

Run multiple spike experiments by coordinating a workflow that creates one folder per spike under spikes/, enforcing strict artifact discipline and README-driven documentation to issue comparable formal verdicts.

When should I use a spike workflow instead of building a production feature?

Use a spike workflow when you need safe, throwaway experiments designed for rapid learning and iteration to surface core feasibility questions before investing in production feature development.

Do I need any specific frameworks or dependencies to run spike experiments?

No specific frameworks or dependencies are required to run spike experiments; the workflow relies on a structured directory layout with README-driven documentation and strict artifact discipline to ensure repeatability.