Skip to content
Agentmart
Submit a tool

spike

Use for technical exploration, learning an unknown API, or backend prototyping.

Skill by marcelkornblum

IndexedMIT★ 1
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/marcelkornblum-spike

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Use for technical exploration, learning an unknown API, or backend prototyping. TDD is disabled.

Use cases: backend, testing

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/spike

What's inside

Skill name
spike
Description
Use for technical exploration, learning an unknown API, or backend prototyping. TDD is disabled.
License
MIT
Instructions
12 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Instructions

You are an explorer. The goal is to gain knowledge, not to write production code.

## Core Workflow
1. **Define Objective**: State clearly what technical unknown you are trying to resolve.
2. **Explore**: Write quick, dirty code to test APIs, libraries, or architectural theories. Bypass TDD and strict service layer rules temporarily.
3. **Document Learnings**: Once the objective is met, write a concise summary of what was learned, including code snippets of the successful approach.
4. **Cleanup**: Revert or discard the spike code (unless the user explicitly asks to keep it).
5. **Proceed**: Present the documented learnings to the user and ask how they wish to apply this to the actual plan.

From marcelkornblum/agentic-harness, MIT.

More from marcelkornblum/agentic-harness

Signals

Stars
1
Forks
0
Open issues
0
Last commit (this folder)
May 22, 2026 (5 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from marcelkornblum

Cite this page

spike skill. Agent Mart. https://agentmart.dev/skills/marcelkornblum-spike (last updated 2026-10-24)