skills.rest
xu1713
xu1713COMMUNITY
Explore all skills by this author →
GitHub

spike

Build throwaway prototypes to validate technical feasibility before committing to a real build.

Updated Jun 5, 2026
Search Tags:#validation#feasibility#exploration#prototype#proof-of-concept#experiment#spike
One-click install
npx skills add https://github.com/xu1713/openhorse --skill spike-xu1713
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: spike
Source: https://github.com/xu1713/openhorse/tree/main/openhorse/openhorse/skills/software-development/spike
Command: npx skills add https://github.com/xu1713/openhorse --skill spike-xu1713

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? It answers feasibility questions that research alone cannot resolve by building small, disposable experiments, so you avoid committing to an architecture or library before knowing it actually works. ## Core Features & Use Cases - Structured Spike Workflow: Decompose an idea into 2-5 risk-ordered feasibility questions framed as Given/When/Then, then research, build, and deliver a verdict per spike. - Comparison Spikes: Build competing approaches side by side (e.g., pdfjs vs camelot for PDF parsing) and produce a head-to-head comparison table with a winner recommendation. - Verdict Reporting: Each spike closes with a VALIDATED, PARTIAL, or INVALIDATED verdict documenting what worked, what failed, surprises, and recommendations for the real build. - Use Case: Before building a real-time chat feature, spike websocket streaming to confirm the client receives LLM token chunks under 100ms, then throw the code away. ## Quick Start Ask the agent to spike whether your chosen approach works, for example: "Spike whether websockets can stream LLM tokens to the browser with under 100ms latency before I commit to this architecture."

Frequently Asked Questions about spike

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

FAQPage Schema
How do I validate a technical idea before building it?▼

Run a spike: decompose the idea into 2-5 specific feasibility questions, order them by risk, build a minimal throwaway prototype for each, and record a verdict. The goal is evidence, not production code.

What is a spike in software development?▼

A spike is a disposable experiment that answers a specific feasibility question, such as whether a library can stream data fast enough. It follows a decompose, research, build, verdict loop and is thrown away once it has answered the question.

How do I compare two libraries for the same task?▼

Build comparison spikes with a shared number and letter suffix, such as 002a and 002b, implementing the same question with each library. Then write a head-to-head table covering quality, setup complexity, and performance, and declare a winner for your use case.

When should I not use a spike?▼

Skip spiking when the answer is knowable from documentation or reading existing code, when the work is on the production path and needs real planning, or when the idea is already validated and you can jump straight to implementation.

What makes a good spike question?▼

A good spike question targets specific feasibility with observable output, framed as Given/When/Then. Avoid questions that are too broad, have no observable result, or could be answered by simply reading documentation.

Related Skills

Explore More Software Engineering Skills→
open-platform-modelopen-platform-model

openspec-explore

Guide problem exploration and requirement clarification with clarifying questions and ASCII diagrams.

Official
Intermediate
jedmamostojedmamosto

gsd-spike

Validate product or engineering ideas through structured spike experiments.

Community
Intermediate
arbisoftarbisoft
4

architecture-decision-records

Generate structured ADR documents with context, decision, alternatives, and consequences.

Official
Advanced
DagimAlemayehuuDagimAlemayehuu

prototype

Builds throwaway terminal or UI prototypes to validate state models and design options.

Community
Intermediate