Skill

spike

Time-boxed technical investigation with structured output. Use for feasibility studies, architecture exploration, integration assessment, performance analysis, or risk evaluation. Creates spike tasks in ohno, enforces time-boxing, generates spike reports, and creates actionable follow-up tasks.

Install

npx claudepluginhub srstomp/pokayokay --plugin pokayokay

Tool Access

This skill uses the workspace's default tool permissions.

Preview

Structured technical investigation to reduce uncertainty. Answer specific questions, not "explore X."

Supporting Assets

references/output-templates.mdreferences/question-patterns.mdreferences/spike-types.md

SKILL.md

Similar Skills

kotlin-ktor-patterns

Provides Ktor server patterns for routing DSL, plugins (auth, CORS, serialization), Koin DI, WebSockets, services, and testApplication testing.

everything-claude-code

163.2k

deep-research

Conducts multi-source web research with firecrawl and exa MCPs: searches, scrapes pages, synthesizes cited reports. For deep dives, competitive analysis, tech evaluations, or due diligence.

everything-claude-code

163.2k

inventory-demand-planning

Provides demand forecasting, safety stock optimization, replenishment planning, and promotional lift estimation for multi-location retailers managing 300-800 SKUs.

everything-claude-code

163.2k

Stats

Parent Repo Stars4

Parent Repo Forks0

Last CommitFeb 7, 2026

Actions

View Source View Plugin View on GitHub View README

spike

Spike

Structured technical investigation to reduce uncertainty. Answer specific questions, not "explore X."

Key Principles

Every spike answers a specific, measurable question

Strict time-box (default 4h) — produce a decision at the end, even if incomplete

Output is a decision (GO/NO-GO/PIVOT/MORE-INFO), not a general exploration

Create follow-up tasks from findings, not just a report

When NOT to Use

Multi-day evaluations — Use deep-research for comprehensive technology evaluations with stakeholder reports

Already know what to build — Skip straight to implementation; spikes are for reducing uncertainty, not planning known work

Bug investigation — Use error-handling or /fix; bugs have reproduction steps, spikes have open questions

Quick Start Checklist

Define the question clearly (what are we trying to learn?)

Set a time-box (hours, not days — use deep-research for multi-day)

Identify evaluation criteria upfront

Investigate with focused experiments or prototypes

Checkpoint at 50% — assess progress, decide if pivoting

Produce mandatory conclusion: GO / NO-GO / PIVOT / MORE-INFO

Mandatory Outputs

Decision: GO, NO-GO, PIVOT, or MORE-INFO

Evidence: What was tested, results observed

Follow-up tasks: Created in ohno if GO

Report: Saved to .claude/spikes/[name]-[date].md

References

Reference

Description

spike-types.md

Feasibility, architecture, integration, performance spikes

question-patterns.md

How to frame good spike questions

output-templates.md

Spike report templates and examples

Spike

Structured technical investigation to reduce uncertainty. Answer specific questions, not "explore X."

Key Principles

Every spike answers a specific, measurable question
Strict time-box (default 4h) — produce a decision at the end, even if incomplete
Output is a decision (GO/NO-GO/PIVOT/MORE-INFO), not a general exploration
Create follow-up tasks from findings, not just a report

When NOT to Use

Multi-day evaluations — Use deep-research for comprehensive technology evaluations with stakeholder reports
Already know what to build — Skip straight to implementation; spikes are for reducing uncertainty, not planning known work
Bug investigation — Use error-handling or /fix; bugs have reproduction steps, spikes have open questions

Quick Start Checklist

Define the question clearly (what are we trying to learn?)
Set a time-box (hours, not days — use deep-research for multi-day)
Identify evaluation criteria upfront
Investigate with focused experiments or prototypes
Checkpoint at 50% — assess progress, decide if pivoting
Produce mandatory conclusion: GO / NO-GO / PIVOT / MORE-INFO

Mandatory Outputs

Decision: GO, NO-GO, PIVOT, or MORE-INFO
Evidence: What was tested, results observed
Follow-up tasks: Created in ohno if GO
Report: Saved to .claude/spikes/[name]-[date].md

References

Reference	Description
spike-types.md	Feasibility, architecture, integration, performance spikes
question-patterns.md	How to frame good spike questions
output-templates.md	Spike report templates and examples