Skip to content
Agent Orchestration
Skill

/spike

Use only when a decision is blocked on a fact nobody has. One time-boxed question, one answer.

From plugin
pane
59739 skills4 agents

Claude Code

$ npx -y skills add greenfield-inc/Pane --skill spike --agent claude-code

SKILL.md

spike.SKILL.md
name: spike
description: Use only when a decision is blocked on a fact nobody has. One time-boxed question, one answer.

Spike

A spike answers one question so a decision can be made. Write one only when a decision is actually blocked on it.

Steps

1. Write the question so the answer is a fact, not an opinion. "Can the queue delay a job by 24 hours without a new table?" is a spike. "What is the best queue design?" is an options question. 2. Set a time box and a method. Throwaway code is allowed and expected. 3. If the question is answerable from the web or docs, answer it with the `research-web` skill. If it needs the repo or a running system, give a fresh-context subagent the question to answer with the `gather-evidence` skill. Give the subagent the question and the time box only. 4. Record the answer and the evidence. 5. Feed the answer back into the options document under "What we learned". Re-rank the options if it changes them.

Format

Plain text in the page bundle (see `page`), for example `spikes/{slug}.md`:

# Spike: {one question}
Blocks: {which decision and options}
Time box:
Method:
Throwaway allowed: yes

## Done when
An answer, not a feature.

## Answer
## Evidence
Feeds back to: {options link}

Banned

  • Merging spike code into the real plan automatically. If spike code should ship, it goes through the plan like any other change.
  • Widening the question after starting
Read more
@greenfield-inc
Ships withpane

pnpm dlx runpane@latest

59739 skills4 agents
Get the whole plugin

Stars on GitHub

Momentum

stars in total
597
Star history of greenfield-inc/Pane on GitHub, a chart by star-history.com

Other skills on pane.

babysit-pr

babysit-pr

Use after a pull request is open to watch its CI and review-bot comments until it is ready. Fixes real findings, replies with a…

@greenfield-inc@greenfield-incInstall Skill
brief

brief

Use when a problem, idea, or change of intent is worth capturing as a long-form page, or the person asks to write it up. Never…

@greenfield-inc@greenfield-incInstall Skill
bug-intake

bug-intake

Use when the person reports broken behaviour or starts a session to file a bug. Reproduces and reports. Never fixes.

@greenfield-inc@greenfield-incInstall Skill
codebase-design

codebase-design

Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening…

@greenfield-inc@greenfield-incInstall Skill
codebase-explorer

codebase-explorer

Explore the codebase to locate files, trace behavior, and document existing patterns with precise file references. Use when the…

@greenfield-inc@greenfield-incInstall Skill
cold-read

cold-read

Give a fresh agent something to walk through with zero context - a PR body, a landing page, a document, a process, instructions,…

@greenfield-inc@greenfield-incInstall Skill

More skills from other plugins.

1password

1password

Set up and use 1Password CLI for sign-in, desktop integration, and reading or injecting secrets.

clawdis12d393k
@steipete@steipeteInstall Skill
computer-use

computer-use

Drives the GUI of a visible local app window through `orca computer`: accessibility tree, clicks, typing, menus, dialogs, and…

orca12d111k
@stablyai@stablyaiInstall Skill
agentmail

agentmail

Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by…

paperclip11d109k
@paperclipai@paperclipaiInstall Skill
adr-create

adr-create

Create a new Architecture Decision Record with sequential numbering and AgentDB registration

@ruvnet@ruvnetInstall Skill

Questions about spike.

Which coding agents can use spike?
spike installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.