Discover Agent Skills for security & testing. Browse 105 skills for Claude, ChatGPT & Codex.
Implements a vendor-agnostic, AI-powered software testing intelligence protocol covering 24 distinct test types for any tech stack.
Automates comprehensive pull request reviews using a coordinated multi-agent system to analyze security, performance, architecture, and code quality.
Identifies security vulnerabilities, injection attacks, and hardcoded secrets through deep analysis of authentication and configuration files.
Automates a continuous quality assurance cycle by integrating linting, testing, and build verification into the AI development workflow.
Identifies critical logic errors, race conditions, and edge cases during code reviews to ensure production stability.
Validates complex data structures by enforcing size, relationship, and consistency constraints to ensure internal integrity.
Retrieves and communicates sensitive credentials by orchestrating interactions between specialized secret-management agents.
Ensures code reliability and output accuracy through real-time truth scoring, automated quality checks, and intelligent rollbacks.
Conducts comprehensive security audits and applies best-practice patterns to C++ codebases to prevent vulnerabilities.
Analyzes project architecture, detects code smells, and identifies optimization opportunities for improved code quality and performance.
Enforces a rigorous test-driven development cycle for C++ projects using Google Test and CMake to ensure high code quality and coverage.
Writes, executes, and analyzes robust UI component tests using Vitest and React Testing Library with a focus on accessibility and coverage.
Secures web applications by identifying vulnerabilities, implementing XSS/CSRF protections, and auditing authentication flows.
Implements a formal evaluation framework for Claude Code sessions to enable reliable, test-driven AI development.
Orchestrates RAN security using cognitive threat detection, predictive modeling, and intelligent policy management for 5G networks.
Performs systematic security threat modeling and architectural risk assessments using the STRIDE methodology.
Automates a comprehensive multi-phase quality assurance process including builds, type checking, testing, and security scans for Claude Code sessions.
Automates REST API fuzz testing to identify security vulnerabilities, input validation failures, and unexpected edge cases.
Diagnoses software defects by tracing errors backward to their source instead of applying superficial symptom-level patches.
Implements a rigorous five-step methodology to eliminate guesswork and resolve software bugs through reproduction, isolation, and root-cause analysis.
Enforces strict command-based verification and evidence gathering before any task is marked as complete.
Audits and scans installed Claude Code plugins for security vulnerabilities, malicious code, and privacy risks using parallel subagents.
Validates and audits Claude Code plugin structures to ensure compliance with official specifications and best practices.
Implements a multi-layered validation strategy to identify and resolve bugs across syntax, logic, and integration phases before deployment.
Diagnoses and resolves Rust compiler errors, borrow-checker conflicts, and runtime panics with idiomatic solutions.
Implements a rigorous test-driven development cycle to ensure code quality and reliability through systematic red-green-refactor iterations.
Verifies code integrity and quality through automated testing, linting, and build validation.
Performs deep security inspections of Claude Code skills to detect malicious patterns, vulnerabilities, and supply chain risks.
Performs comprehensive security audits including OWASP Top 10 checks, secret detection, and dependency vulnerability scanning.
Audits Rust codebases for idiomatic patterns, performance bottlenecks, and adherence to Apollo best practices.
Scroll for more results...