security & testing Claude 스킬을 발견하세요. 105개의 스킬을 탐색하고 AI 워크플로우에 완벽한 기능을 찾아보세요.
Implements a high-confidence, three-tiered testing framework for TypeScript using dependency injection and behavior-driven patterns.
Implements type-safe, test-driven TypeScript features following strict dependency injection patterns.
Streamlines end-to-end testing by providing expert guidance on Playwright configuration, resilient locator strategies, and robust automation patterns.
Assesses implementation risks using P×I scoring to prioritize test scenarios and inform quality gates.
Audits Claude Code components for effectiveness, security, and usability through systematic quality scoring and optimization suggestions.
Hardens Kubernetes clusters using zero-trust models, RBAC design, and automated policy enforcement for production-grade security.
Systematically identifies and resolves failing tests using intelligent error grouping and prioritized fixing strategies.
Ensures code quality and project standards by performing automatic linting, type-checking, and static analysis after every modification.
Automates reconnaissance and security vulnerability discovery using proven red team methodologies and industry-standard toolsets.
Orchestrates eight specialized AI agents to perform deep code reviews across naming, security, complexity, and testing dimensions.
Evaluates and benchmarks LLM agents using behavioral testing, reliability metrics, and regression analysis to ensure production readiness.
Enforces high-quality testing standards by preventing mock-related errors and production code pollution during the development process.
Orchestrates multiple external AI models and specialized subagents to provide consensus-driven code reviews and architectural guidance.
Enforces an evidence-based gate function that requires fresh command output and validation before any task is marked as complete.
Enforces a disciplined Red-Green-Refactor cycle to ensure every line of production code is validated by a failing test.
Implements comprehensive testing suites using pytest, covering unit tests, integration tests, and detailed coverage reporting.
Enforces reproducible testing and evidence-driven verification to ensure every code change is proven reliable before merging.
Standardizes multi-agent code reviews through structured response formats, expertise weighting, and automated false-positive filtering.
Systematic debugging playbook for tracing failures backward through the call chain to identify and fix bugs at their origin.
Enforces a disciplined, four-phase debugging process to identify root causes and implement stable fixes.
Systematically identifies, groups, and resolves failing test suites using a prioritized multi-stage debugging strategy.
Guides professional penetration testing workflows, vulnerability exploitation, and payload generation using the Metasploit Framework.
Implements proactive threat modeling and security-first development practices to minimize attack surfaces and ensure data safety.
Validates Claude Code plugin structures and audits hook scripts to prevent silent failures and ensure schema compliance.
Implements resilient, domain-rich business logic using behavior-focused test-driven development and clean architecture patterns.
Analyzes RSpec failures to provide immediate root-cause diagnosis and actionable debugging steps for Ruby applications.
Conducts comprehensive security audits and vulnerability assessments on WordPress installations using industry-standard tools and methodologies.
Generates professional security policies, incident response plans, and compliance documentation to strengthen organizational security posture.
Performs deep security audits, vulnerability scans, and penetration testing workflows for WordPress installations.
Performs automated, deep AI code reviews locally to identify security risks, concurrency issues, and complex logic flaws.
Scroll for more results...