๐Ÿงช
AI EngineeringPython

Spike

by HezaoHezao

Spike is an AI Engineering skill for Claude Code, published by HezaoHezao in poirot.

185 stars8 forkson HezaoHezao/poirotAdded 2026/08/11+48% in starsRepository updated 2026/07/28
agentagent-memoryagent-skillagent-skillsagentic-aiagentsai-agentai-agentsai-codingmemorymemory-systemmulti-agent
Install in seconds
Install Spike
Copy Spike into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/HezaoHezao/poirot/tree/master/poirot/backend/agents/skill/builtin_skills/core/spike ~/.claude/skills/spike

Requires Node.js. Downloads this skill only โ€” not the rest of the repository โ€” into your Claude Code skills folder.

Without Node.js

git clone https://github.com/HezaoHezao/poirot.git

Clones the whole repository, then copy the skillโ€™s own directory into your skills folder yourself.

In this catalog

Source file
poirot/backend/agents/skill/builtin_skills/core/spike/SKILL.md in HezaoHezao/poirot
Installs to
~/.claude/skills/spike
Collection
One of 37 skills cataloged from this repository
Category
AI Engineering โ€” 2451 skills

What Spike does

Run disposable experiments to validate technical feasibility, compare approaches, and surface unknowns before committing to a full build. Spikes are thrown away after providing insight.

Spike is cataloged under AI Engineering on DirSkills. Spike comes from a repository tagged agent, agent-memory, agent-skill, agent-skills and agentic-ai.

Documentation

README

Spike

Use this skill when the user wants to feel out an idea before committing to a real build โ€” validating feasibility, comparing approaches, or surfacing unknowns that no amount of research will answer. Spikes are disposable by design. Throw them away once they've paid their debt.

Load this when the user says things like "let me try this", "I want to see if X works", "spike this out", "before I commit to Y", "quick prototype of Z", "is this even possible?", or "compare A vs B".

When NOT to use this

  • The answer is knowable from docs or reading code โ€” just do research, don't build
  • The work is production path โ€” use the plan skill instead
  • The idea is already validated โ€” jump straight to implementation

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Spike

  • What else does HezaoHezao publish alongside Spike?

    Spike is one of 37 skills that DirSkills catalogs from HezaoHezao/poirot, the repository it ships in. Its siblings there include Academic Paper Review, ArXiv Research and Architecture Diagram. Each one is a separate skill with its own page in this directory, installs the same way Spike does, and is maintained by HezaoHezao in that same repository. The rest of the collection is listed on the HezaoHezao/poirot page.

  • How does Spike compare to other AI Engineering skills?

    Spike ranks #2231 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Spike against them. Open each page to compare what they document and how they install.