Skip to main content
skill CX Codex

spike · openclaw — Claude Code skill: what it does, how to install

spike runs throwaway prototypes to test technical feasibility, compare alternate approaches, and deliver an evidence-based verdict before building.

MIT 296 installs ★ 395,001 updated 2026-10-25

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add openclaw/openclaw --skill spike -a claude-code
Open on GitHub

What spike does

The skill handles structured technical spikes. It states the core question, looks into relevant docs, builds the smallest runnable artifact, and exercises an edge case. After running the test, it returns an explicit verdict: VALIDATED, PARTIAL, or INVALIDATED, complete with reproduction commands and recommendations.

Files live in .tmp/openclaw-spikes/<slug> by default, or inside spikes/<NNN-slug>/ with a local README.md when tracked code is requested. It prefers isolated CLI tools, single endpoints, or bare HTML snippets over heavy frameworks, container images, or environment setup files.

Spike code must never be merged directly into a production codebase without a full rewrite. It serves only to answer questions early, ruling out dead ends before real implementation begins.

What it helps with

  • test feasibility with runnable code before committing resources
  • compare competing approaches on equal terms and shared metrics
  • inspect external dependencies for maintenance activity and licensing
  • document evidence for abandoning an unworkable architecture path

Example prompts for the agent

  • Spike this library to see if it parses our legacy data format
  • Build a quick prototype comparing approach A and B for this endpoint
  • Is this background sync pattern possible before we build the feature?

How to install spike

1Skills CLI (Vercel)

npx skills add openclaw/openclaw --skill spike -a claude-code

2Manually: put the files in place

~/.claude/skills/spike/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/spike/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about spike

How do I install spike in Claude Code?

Run npx skills add openclaw/openclaw --skill spike -a claude-code. Alternatively, place the definition at ~/.claude/skills/spike/SKILL.md.

When should spike not be used?

Skip it if the question is easily answered by checking docs or reading existing code, or whenever production-ready implementation is requested upfront.

Where does the skill write prototype files?

It creates files in .tmp/openclaw-spikes/<slug> by default, or under spikes/<NNN-slug>/ with a README.md if repository tracking is explicitly requested.

Source text

SKILL.md · MIT
---
name: spike
description: Run throwaway prototypes to validate feasibility, compare approaches, and report a verdict.
metadata: { "openclaw": { "emoji": "🧪" } }
---

# Spike

Use when the user wants to test an idea before committing to a real build: "spike this", "quick prototype", "is this possible", "compare A/B", "before we build".

Do not use when reading docs/code can answer the question, or when the user clearly asked for production implementation.

Loop

1. Question: state the concrete feasibility question.
2. Research: read enough docs/source to choose credible approach.
3. Build: create the smallest runnable artifact that validates or invalidates the idea.
4. Stress: try one edge case or failure mode.
5. Verdict: `VALIDATED`, `PARTIAL`, or `INVALIDATED`.

Output shape

- Default workspace: `.tmp/openclaw-spikes/<slug>` unless user asks for a tracked repo-local path.
- Repo-local option: `spikes/<NNN-slug>/` with `README.md` and minimal code.
- Prefer runnable CLI, tiny HTML, one endpoint, or focused test.
- Avoid package sprawl, Docker, env files, app frameworks, and production cleanup.

Multi-spike ideas

- Split into 2-5 independent questions.
- Run the riskiest question first.
- For A/B comparisons, keep inputs equal and measure the same dimensions.
- Ask before building all variants if the work is more than a small prototype.

Verdict format

```markdown
## Verdict: VALIDATED | PARTIAL | INVALIDATED

Question: ...
Evidence: exact command/output/measurement.
What worked: ...
What failed or surprised us: ...
Recommendation: ship / adjust / avoid, with the next production step.
```

Rules

- An invalidated spike is useful when it rules out a path with evidence.
- Do not merge spike code into production without rewriting it normally.
- If external dependencies are evaluated, check health: recent release/commit, docs, license, install friction.

© openclaw · MIT · openclaw/openclaw

Similar skills

All skills for Agent setup: memory, context, orchestration →

spike by other authors comes first.

spike Hermes Agent (adapted from gsd-build/get-shit-done) spike — a skill for throwaway experiments that validate an idea before you commit to building. Creates prototypes, compares approaches, and documents findings. CX Codex +1 437installs Prototype Designer daffy0208 Prototype Designer is a skill for Claude Code that helps design user flows, build interactive prototypes, and test ideas before implementation. CX Codex +1 278installs Technical spike research mode official github The Technical spike research mode subagent investigates technical spikes through documentation, code, and experiments. It needs the spike document path before starting. CX Codex +1 ★ 41,430repo stars create-technical-spike official github create-technical-spike is a GitHub Copilot skill that structures time-boxed research into a technical decision. It activates when a question needs resolution before implementation can move ahead. CX Codex +1 9,000installs 05-spike AI-Driven Dev 05-spike turns one blocking unknown into a bounded spike: frames the question, gathers evidence, writes the outcome. CX Codex +1 ★ 571repo stars develop-spike-summary product-on-purpose develop-spike-summary documents the results of a completed technical or design spike. It captures findings, evidence, and a clear recommendation so the team avoids re-litigating decisions. CX Codex +1 816installs gsd-spike open-gsd The gsd-spike Claude Code skill explores an app idea through focused experiments. It can also inspect past spikes and suggest what to investigate next. CX Codex +1 569installs

From the same set54

The whole set →
node-connect node-connect is a Claude Code skill that diagnoses OpenClaw Control UI and native node connection failures. It traces route, authentication, pairing, and reconnect issues. CX Codex +1 806installs diagram-maker diagram-maker — a skill for Claude Code, Codex, Cursor and other platforms that generates SVG/HTML or Excalidraw diagrams. Activates when you need to visualize architecture, a process, or a concept. CX Codex +1 524installs meme-maker meme-maker searches meme templates from a curated registry, suggests formats for your joke, and renders images locally (SVG or PNG) or via Imgflip. CX Codex +1 350installs python-debugpy python-debugpy guides interactive Python debugging with pdb and debugpy remote attach. Useful for tracking down broken tests, state mutations, and headless processes. CX Codex +1 343installs node-inspect-debugger node-inspect-debugger is a Claude Code skill for debugging Node.js with node inspect, breakpoints, CPU profiles, and heap snapshots. It investigates async hangs that logs don't explain. CX Codex +1 299installs canvas Controls widget panel visibility and navigation on a connected Mac through Canvas actions. CX Codex +1 147installs feishu-wiki Navigates Feishu knowledge spaces, inspects tree nodes, and extracts document tokens with feishu_wiki. CX Codex +1 ★ 395,001repo stars feishu-drive This skill handles Feishu Drive files, folders, and document discussions. Use it when an agent needs to inspect, move, or comment on shared files. CX Codex +1 ★ 395,001repo stars

Project sponsors

Companies that keep this analytics open