bacoco

ShipGuard — Testing skill for Claude Code

Testing community

Claude Code skills for automated E2E testing with agent-browser (Playwright CLI).

How to install ShipGuard

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

What ShipGuard does

Claude Code skills for automated E2E testing with agent-browser (Playwright CLI). Discover routes, generate YAML test manifests, execute with hybrid LLM assertions, track regressions.

Alternatives in Testing

  • Playwright — claude-plugins-official Browser automation, E2E testing, screenshots 29.4k ★
  • Claude Code Spec Workflow — Automated Kiro-style Spec workflow for Claude Code 3.6k ★
  • Agent Skills Spec — A skill is a folder of instructions, scripts, and resources that agents can discover and load dynamically to p 1.9k ★

README

ShipGuard

![ShipGuard — Agentic AI Audit & Visual Regression](docs/screenshots/hero-banner.jpg)

**Ship with confidence.** ShipGuard finds bugs before your users do — and gets smarter every time.

How it works

![ShipGuard Demo](docs/screenshots/demo.gif)

code audit → find bugs → visual test → confirm on screen → human review → annotate → auto-fix → repeat

ShipGuard closes the loop between static analysis and visual reality. Code audit finds bugs in source. Visual tests verify if users see them. You annotate what matters. AI fixes it. The system learns and gets better each run.

Status

Module Status Notes
Visual E2E Debugger 🟢 Stable discover → run → review → fix loop
Code Audit 🟢 Stable parallel agents, multi-round, verification
Macro Recorder 🟢 Stable record → replay via YAML manifests
Self-Improving Engine 🟡 Experimental sg-improve + sg-scout, evolving
Review Dashboard 🟢 Stable HTML generation, Findings tab, annotations, monitor
Recette CLI 🟢 New in 2.5.0 shipguard init/serve/crawl/run/review — deterministic, exit codes 0/1/2/3
Mission Lock 🟢 Updated in 2.6.4 Code-first mission guard; read content (pages, files, tool output) is data — it never instructs, widens authority, or passes a review; non-Sol activation is explicit opt-in
CI/CD Integration 🔴 Planned the CLI's stable exit codes are the intended CI entry point

⚠️ Requires **Claude Code or Codex**. Visual flows also require `agent-browser`. Some flows are experimental and evolving fast.


Five AI-powered modules. Use one, some, or all five. No test files to write.

📸 Visual E2E Debugger

Auto-discover routes, generate tests, mark bugs on screenshots — **AI traces to source code and fixes automatically**.

/sg-visual-run

🔍 Code Audit

Parallel AI agents scan your entire codebas