NeuraCerebra-AI

Shipworthy — Testing skill for Claude Code

Testing community

AI-agent-driven end-to-end & frontend testing + backend-symptom analysis — free, read-only Claude Code/Codex skill.

How to install Shipworthy

This entry records only its repository, not the path inside it, so there is no exact command to give. Open NeuraCerebra-AI/Shipworthy and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Shipworthy does

AI-agent-driven end-to-end & frontend testing + backend-symptom analysis — free, read-only Claude Code/Codex skill.

Alternatives in Testing

AI Contribution Skills (Engram) — branch-pr: clean branch and PR workflow 2.5k ★
Playwright Automation — git clone Browser automation skill for end-to-end testing and web interaction 2.3k ★
Spec Kitty — Spec-Driven Development for serious software developers 1.6k ★

README

Shipworthy — free, open-source AI testing agent for automated frontend, end-to-end (E2E), and backend-symptom testing of web apps and AI agents. Walks every safe user path, proves it's ready to ship, never overclaims.

Automated frontend & end-to-end (E2E) testing + backend-symptom analysis — an AI agent that proves your app is ready to ship.

It walks your whole product like your most paranoid senior engineer — every safe, discoverable screen and path, plus the backend underneath — then proves whether you're ready to ship.

Point it at your app, ask **"Are we shipworthy?"**, and get a proof-backed ship-or-don't verdict.

[![GitHub stars](https://img.shields.io/github/stars/NeuraCerebra-AI/shipworthy?style=social)](https://github.com/NeuraCerebra-AI/shipworthy) [![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](LICENSE) [![Skills](https://img.shields.io/badge/skills-4-8A2BE2?style=flat-square)](#-the-four-skills) [![Version](https://img.shields.io/badge/version-0.1.0-blue?style=flat-square)](https://github.com/NeuraCerebra-AI/shipworthy/releases)

**Read-only · self-contained markdown · no telemetry · no credential access · no auto-update**

**Shipworthy** is a free, open-source **AI testing agent** that runs **automated frontend and end-to-end (E2E) tests** on your web app — and analyzes the **backend symptoms** behind each path. It walks every safe user path like a real user (browser, Playwright, or Computer Use), catches failures the UI hides (a 500 behind a "success" screen, data that never saved), installs as a **Claude Code or Codex skill**, runs **read-only**, and returns a proof-backed *ship-or-don't* verdict: **ready, conditionally ready, not ready, or cannot determine**. It works on normal apps and on AI-built ("vibe-coded") apps and AI agents — and it never overclaims.