security & testing Claude 스킬을 발견하세요. 105개의 스킬을 탐색하고 AI 워크플로우에 완벽한 기능을 찾아보세요.
Evaluates and benchmarks LLM agents using behavioral testing, reliability metrics, and adversarial assessments to ensure production-grade performance.
Enforces a strict Red-Green-Refactor cycle to ensure all production code is verified by failing tests before implementation.
Enforces a rigorous evidence-based workflow that requires real-time command output before any task is marked as complete.
Facilitates end-to-end testing and UI debugging of local web applications using Playwright scripts and automated server management.
Implements trading strategies using test-driven development and rigorous postmortem compliance to prevent architectural regressions.
Implements robust testing architectures and best practices using Jest, Vitest, and Testing Library for JavaScript and TypeScript projects.
Generates comprehensive Vitest and React Testing Library tests for frontend components, hooks, and utilities following project-specific conventions.
Conducts automated reviews of TypeScript and JavaScript code to identify performance bottlenecks, quality issues, and logic errors.
Implements robust Python testing strategies using pytest, fixtures, mocking, and test-driven development best practices.
Enforces a rigorous, multi-phase debugging process that requires proof of root cause before allowing any code modifications.
Generates comprehensive Pest test suites for Laravel projects, ensuring high coverage across controllers, services, and Livewire components with standardized organizational patterns.
Conducts multi-dimensional security, quality, and postmortem compliance audits for trading strategies before deployment.
Automates HashiCorp Vault administration, secret management, and secure identity-based access control.
Conducts comprehensive security assessments and penetration tests across AWS, Azure, and Google Cloud Platform environments.
Conducts comprehensive security audits and vulnerability scans using OWASP patterns, CWE analysis, and STRIDE threat modeling.
Implements a robust Red-Green-Refactor cycle for building high-quality Rust and TypeScript applications.
Provides comprehensive methodologies and command references for auditing Microsoft Active Directory environments during authorized penetration tests.
Enforces a strict Red-Green-Refactor workflow to ensure every line of production code is verified by a failing test first.
Conducts comprehensive SSH security assessments including enumeration, credential attacks, and configuration auditing.
Stress-tests architectural assumptions by simulating extreme scaling scenarios to identify fundamental system limits and bottlenecks.
Performs comprehensive security assessments of SMTP servers to identify vulnerabilities like open relays, user enumeration, and weak authentication.
Automates the generation and execution of RSpec tests for Ruby applications with support for complex mocking and hooks.
Generates and executes xUnit tests for C# projects with integrated support for FluentAssertions and Moq.
Guides users through a comprehensive, multi-phase methodology for planning, executing, and remediating professional penetration tests.
Validates factual claims, assesses implementation quality, and ensures AI outputs meet production-grade standards through automated self-verification.
Provides systematic methodologies and commands for discovering and exploiting privilege escalation vulnerabilities on Windows systems during security audits.
Debugs and resolves Content Security Policy (CSP) and Subresource Integrity (SRI) violations in Astro-based web applications.
Generates robust pytest suites for Python applications with specialized support for fixtures, parametrization, and PyTorch-based operations.
Debugs frontend UI/UX issues, console errors, and network failures through empirical browser observation and systematic investigation using Chrome DevTools.
Performs comprehensive security audits to identify, exploit, and mitigate file path traversal and Local File Inclusion (LFI) vulnerabilities.
Scroll for more results...