Resources
Playbooks, guides, and best practices for AI-native E2E testing.
Claude Code vs Antigravity: Terminal Agent or Agent-First IDE
Claude Code is a terminal agent extended through MCP, Skills, hooks, and subagents. Google Antigravity is an agent-first platform with an IDE, a CLI, and an Agent Manager for parallel work. This comparison walks the mechanisms: where each agent lives, which models it runs, how you extend it, and what each can verify.
How to Create a Claude Code Skill, Step by Step
A skill is one folder and one file away. This tutorial walks through creating a Claude Code skill: the SKILL.md format, the frontmatter fields that control loading, writing a description that actually triggers, and testing that it fires.
Cursor Rules: How They Work and When a Rule Beats a Skill
Cursor rules are persistent instructions the agent loads into context, defined as .mdc files under .cursor/rules. This guide covers the four rule types, the legacy .cursorrules migration, AGENTS.md, and a decision framework for when a rule, a skill, or an MCP server is the right tool.
How to Test Code Written by GitHub Copilot
Copilot went from autocomplete to an agent that edits across files and opens pull requests. The bugs changed with it: less syntax, more integration. Here is how to add a verification layer to Copilot's output, from unit tests it already handles to browser E2E it cannot do alone.
Pre-Action Checks for AI Coding Agents: Tools and Patterns
Pre-action checks stop an AI coding agent before it runs a dangerous command or edits a protected file: permission prompts, plan review, PreToolUse hooks, sandboxes, and branch rules. This guide covers the seven mechanisms that matter, and where each one fits against post-action verification.
Shiplight vs Momentic: AI E2E Testing Platforms Compared (2026)
Both turn plain-language intent into E2E tests stored as YAML in your repo. The difference is the exit path, the run economics, and whose subscription pays for authoring. An honest head-to-head.