Security & Testing Claudeスキル

Foundations for Claude Code

Standardizes code quality, security protocols, and engineering conventions for high-performance AI development.

Test-Driven Development (TDD)

Enforces a strict Red-Green-Refactor workflow to ensure all production code is verified by failing tests first.

Runtime Security Guardian

Protects system integrity by auditing execution plans and intercepting high-risk shell commands before they run.

Move Code Quality Checker

Audits Move language packages for Move 2024 Edition compliance and official code quality standards.

Automated Test Fixing

Systematically identifies, groups, and resolves failing test suites using an intelligent, priority-based debugging workflow.

Web Application Testing

Streamlines local web application testing and interaction using Playwright and automated server management.

Web Application Testing

Automates and tests local web applications using Playwright scripts for reliable frontend verification and UI debugging.

UI Visual Validator

Validates UI modifications, design system compliance, and accessibility standards through rigorous visual analysis and regression testing.

FFUF Web Fuzzing

Accelerates web security testing by providing expert guidance for high-performance fuzzing, directory discovery, and vulnerability research.

PICT Test Designer

Generates comprehensive, pairwise test cases from requirements or code using the PICT methodology to ensure maximum coverage with minimum effort.

Verification Before Completion

Enforces a mandatory evidence-based protocol requiring terminal command verification before any task is marked as complete or successful.

Pentest Toolkit

Automates comprehensive security vulnerability discovery and penetration testing with AI-optimized JSON outputs.

Interactive CLI & TUI Testing (tmux)

Enables automated end-to-end testing and interaction with Terminal User Interfaces using isolated tmux sessions.

Playwright Web Application Testing

Automates and validates local web applications using Playwright to ensure seamless UI functionality and reliable user flows.

Systematic Debugging

Enforces a rigorous, root-cause-first debugging methodology to eliminate guesswork and prevent regressions during the troubleshooting process.

Python Testing Patterns

Implements comprehensive Python testing strategies using pytest, advanced mocking, and fixtures to ensure code reliability.

Task-AI: Test Verification

Runs domain-adapted tests and verification procedures to provide structured evidence for task completion and quality.

Claude Vault: Secure Secrets Manager

Protects sensitive API keys and credentials by executing commands through self-destructing scripts that prevent leakage into session logs.

QA Engineer

Automates and validates software quality through comprehensive unit, integration, and end-to-end testing protocols.

Backend Testing & Automation

Implements comprehensive backend testing strategies including unit, integration, E2E, and load testing using industry best practices.

ChatGPT App Golden Prompt Generator

Generates comprehensive sets of test prompts to validate tool invocation and intent recognition for ChatGPT Apps.

ChatGPT App Auth Integrator

Configures secure user authentication for ChatGPT applications using Auth0 or Supabase Auth for multi-user support.

MCP Server Testing Suite

Validates and tests Model Context Protocol (MCP) servers using automated scripts, manual curl commands, and the MCP Inspector GUI.

ATR Behavior Testing

Executes automated browser-based behavior tests using natural language specifications and AI-driven navigation.

JavaScript Testing Standards

Enforces rigorous standards for JavaScript and TypeScript testing using Bun Test, fake timers, and mutation testing quality gates.

Mutation Testing Auditor

Audits test suite quality by injecting semantic code mutations to identify zombie tests and automate test suite refactoring.

E2E Testing & Bugfix Specialist

Diagnoses and resolves end-to-end testing failures in Playwright and Cypress using a structured classification and confidence-scoring system.

Agentic Test Runner (ATR) Analyze

Automates the investigation and debugging of test failures and command errors using AI-powered root cause analysis.

Quality Gates & Iterative Workflows

Implements rigorous quality checkpoints, user approval gates, and iterative refinement loops for high-reliability AI development.

ChatGPT App Test Suite

Automates comprehensive testing for ChatGPT Apps using MCP Inspector, schema validation, and golden prompt verification.