Security & Testing Claude 스킬

Web Application Testing

Automates local web application testing and debugging using Playwright for comprehensive frontend verification and UI interaction.

Test Plan Generator

Generates intelligent, non-redundant test plans by analyzing code changes to ensure comprehensive coverage without over-testing.

Agent Performance Evaluation

Builds comprehensive evaluation frameworks to measure, validate, and optimize AI agent performance and context engineering strategies.

Web Application Testing

Automates browser-based testing and UI verification for local web applications using Playwright.

Test Executor

Executes tests adaptively across any framework or language, analyzes failures, and generates detailed diagnostic reports to facilitate rapid iteration.

Artifact Collector

Collects and manages forensic evidence from endpoints, including memory dumps, system logs, and network traffic, using the LimaCharlie security platform.

Multi-AI Research & Analysis

Conducts deep, multi-perspective technical research and analysis using integrated Claude, Gemini, and Codex agents for verified, production-ready results.

Fear-of-Falling Preflight Guardrails

Enforces data integrity and R-script coding standards through strict, diff-aware guardrail checks.

Codex Authentication Manager

Configures and manages OpenAI Codex CLI authentication, including OAuth login, API key orchestration, and secure multi-account switching.

TDD Workflow

Implements a structured Red-Green-Refactor cycle for autonomous feature development and high-quality code implementation.

TDD Issues Workflow

Executes a systematic Test-Driven Development workflow to resolve software issues with strict coverage requirements and browser-based verification.

Bedrock AgentCore Policy

Defines and enforces deterministic security boundaries for Amazon Bedrock agents using natural language and Cedar policy logic.

Ralph Research & Analysis

Generates structured research and analysis prompts for systematic codebase investigation and architectural planning.

Multi-AI Code Review

Automates multi-perspective code reviews by orchestrating Claude, Gemini, and Codex to perform deep analysis across five critical dimensions.

Web Application Testing Toolkit

Automates local web application testing and browser interaction using Playwright and integrated server management.

Playwright Pro Test Generator

Generates production-ready Playwright end-to-end tests based on features, components, or user stories.

Core Development Standards

Enforces standardized development principles across security, testing, performance, and documentation to ensure high-quality software engineering.

Review Helper

Analyzes source code to identify bugs, security risks, regressions, and gaps in test coverage.

Bedrock Automated Reasoning

Mathematically verifies AI-generated responses against formal policy rules with up to 99% accuracy to ensure deterministic compliance.

Multi-AI Testing & TDD

Implements rigorous test-driven development workflows using independent multi-agent verification to ensure high code coverage and prevent test gaming.

Review Workflow Orchestrator

Orchestrates a comprehensive three-stage quality assurance pipeline including validation, multi-dimensional scoring, and functional scenario testing.

Ralph Prompt Research

Generates structured, multi-phase research prompts for deep codebase analysis, security audits, and architectural planning.

Authentication Implementation Patterns

Implements secure authentication and authorization systems using industry-standard patterns like JWT, OAuth2, and RBAC.

AI Quality Assurance Reviewer

Automates comprehensive quality assurance reviews for feature implementations by evaluating code standards, security, performance, and documentation.

Searchlite Unit Testing

Implements standardized patterns for writing hermetic, deterministic unit tests for the Searchlite embedded search engine.

AC QA Reviewer

Performs automated quality assurance reviews on code implementations to ensure adherence to clean code, security, and performance standards.

Ralph Wiggum Autonomous TDD Loop

Automates the software development lifecycle using a parallel agent swarm and rigorous test-driven development to ensure codebase stability and high-quality convergence.

Security Standards

Implements comprehensive security protocols and OWASP-compliant coding patterns to protect applications from common vulnerabilities.

Systematic Debugging

Resolves complex software anomalies using a rigorous 7-step methodology inspired by medical differential diagnosis and evidence-based reasoning.

Web Testing Patterns

Implements robust testing strategies and patterns for full-stack React, GraphQL, and Prisma applications.