security & testing Claude 스킬을 발견하세요. 105개의 스킬을 탐색하고 AI 워크플로우에 완벽한 기능을 찾아보세요.
Executes commands and code in secure, isolated microVMs and containers to protect your host system during AI-driven development.
Implements robust API testing strategies for REST and GraphQL services using agentic patterns and contract validation.
Enforces a strict Red-Green-Refactor workflow to ensure high-quality, bug-free production code through test-first implementation.
Automates local web application testing and UI debugging using Playwright and managed server lifecycles.
Navigates and manages the Lean 4 and Mathlib nightly testing infrastructure for toolchain updates and CI troubleshooting.
Guides Claude through the formal verification process in Lean by enforcing a rigorous, incremental proof methodology.
Generates minimal working examples (MWEs) from Lean 4 errors and panics to streamline bug reporting and debugging.
Automates the selection and execution of 242+ specialized Fabric CLI patterns for advanced text processing, security analysis, and summarization.
Orchestrates a fleet of 19 specialized AI agents to automate and scale quality engineering through proactive analysis, autonomous testing, and collaborative feedback loops.
Triggers immediate validation and auditing rounds to ensure code quality and security within the RU workflow.
Audits test suites with Google-level SRE scrutiny to eliminate vanity metrics and ensure genuine code reliability.
Automates disposable email management and QA testing workflows using the Mailsac API.
Implements realistic behavior-driven unit testing patterns for .NET domain services using EF Core InMemory and custom fakes.
Provides a structured methodology for writing, debugging, and fixing tests using TDD principles and agent-optimized workflows.
Audits Claude Code plugins and skills for malicious code and prompt injections using AI-driven semantic analysis.
Evaluates and scores code implementations using a standardized five-criteria quality framework.
Analyzes completed code for security vulnerabilities, quality issues, and technical debt to ensure production-grade standards.
Analyzes codebases to discover, document, and enforce consistent coding standards through evidence-based pattern detection.
Identifies and prevents dangerous coding patterns in real-time to ensure application security during the development process.
Conducts systematic audits of CLI safety patterns to identify security gaps, detect regressions, and generate actionable improvement reports.
Simulates realistic user personas to perform objective, documentation-driven exploratory testing for CLI tools.
Standardizes safety validation and command auditing when integrating new LLM inference backends into the Caro Rust CLI.
Guides developers through a rigorous Test-Driven Development workflow for creating and implementing safety patterns in command-line tools.
Enforces project-specific standards, configuration consistency, and security-hardened installation patterns through automated validation.
Enforces strict test-driven development cycles through an automated Red-Green-Refactor workflow for production-grade software.
Optimizes command generation patterns through iterative test cycles, root cause analysis, and specificity-based refinement.
Enforces robust React patterns and architectural standards to prevent common AI coding errors in testability and prop control.
Generates exhaustive, browser-testable E2E test plans with 100% navigation coverage for Laravel Filament applications.
Executes comprehensive role-based end-to-end testing using Playwright to verify access controls and role-specific user flows.
Performs deep security audits, threat modeling, and compliance checks to harden applications against vulnerabilities and data breaches.
Scroll for more results...