Security & Testing Claude 技能

Browser E2E Tester

Automates browser-based end-to-end testing to verify that feature implementations meet specific acceptance criteria.

AC Criteria Validator

Validates feature implementation against acceptance criteria through automated test execution and code analysis.

Code Quality Validator

Validates source code against quality standards, style guidelines, and security best practices across multiple programming languages.

EKS Security Hardener

Hardens Amazon EKS clusters using 2025 security best practices for infrastructure, workloads, and secrets management.

AC Criteria Validator

Validates feature implementation against acceptance criteria and automated test results to ensure software requirements are met.

AC Test Generator

Automates the creation of comprehensive test suites following Test-Driven Development principles to ensure high code quality and feature coverage.

Multi-AI Research & Analysis

Conducts deep, multi-perspective technical audits and research by orchestrating Claude, Gemini, and Codex AI systems.

Testing Validator

Validates Claude Code skill functionality through automated example execution, integration checks, and systematic regression testing.

Test Writing Expert

Generates comprehensive unit, integration, and E2E tests using industry-standard patterns and robust edge case detection.

Analyze-Verify 150 Protocol

Verifies critical claims and factual assertions through source-backed evidence and recursive confidence-building loops.

TDD Test Generator

Generates comprehensive test suites following Test-Driven Development principles to ensure robust feature coverage and automated validation.

Security Sandbox

Safeguards autonomous coding operations using command validation, allowlists, and real-time execution hooks.

Security Sandbox

Protects autonomous coding environments by validating commands through customizable allowlists and execution hooks.

Coding Agent TDD

Implements software features using an incremental Test-Driven Development (TDD) workflow and automated git commits.

Skill Tester

Validates Claude Code skills through hands-on scenario testing, example verification, and usability assessments.

Safe Command Policy

Enforces a safety layer for terminal command execution by requiring explicit user confirmation for destructive or high-impact operations.

Amazon Bedrock Guardrails

Implements comprehensive AI safety policies and content moderation using Amazon Bedrock's multi-layered safeguard framework.

Multi-AI Verification Pyramid

Validates code quality through a comprehensive 5-layer pyramid using independent LLM-as-judge evaluation for production readiness.

Bedrock AgentCore Evaluations

Automates AI agent quality testing and monitoring using built-in metrics and custom LLM-as-judge evaluation patterns.

Network Lab 101

Configures and tests common network services like HTTP, SNMP, and SMB to create controlled penetration testing lab environments.

Playwright Component Testing

Performs isolated UI component testing for React, Vue, and Svelte using Playwright's experimental component testing framework.

Multi-AI Quality Verification

Implements a 5-layer verification pyramid to ensure production-grade code quality through automated checks and LLM-as-judge evaluation.

Comprehensive Code Quality Validator

Executes an intensive code quality suite combining ESLint, TypeScript compilation, and unused code detection to maintain high development standards.

Skill Tester

Validates Claude Code skill functionality and usability through comprehensive scenario-based testing operations.

Visual Testing

Automates visual regression testing and UI consistency checks using Chromatic, Lost Pixel, and Playwright snapshots.

Mobile Emulation & Testing

Emulates diverse mobile devices and responsive environments using Playwright to ensure seamless cross-platform web performance.

Test Writing Standards

Enforces standardized testing protocols and best practices to ensure high-quality, maintainable test suites.

TDD Workflow

Enforces a strict test-driven development cycle using a multi-agent red-green-refactor orchestration.

AC Security Sandbox

Protects autonomous coding environments by enforcing command allowlists, filesystem permissions, and execution sandboxing.

Systematic Debugging

Enforces a rigorous, root-cause-first framework for resolving bugs by eliminating guesswork and prioritizing evidence-based investigation.