Discover Agent Skills for security & testing. Browse 105skills for Claude, ChatGPT & Codex.
Validates and refines process documentation using a Test-Driven Development cycle to ensure reliability under high-pressure scenarios.
Applies Test-Driven Development principles to process documentation to ensure agents follow complex rules under pressure without rationalizing failures.
Manages unexpected test behaviors and implements structured recovery protocols during the Test-Driven Development cycle.
Identifies and resolves complex software issues across UI, backend, and database layers using a systematic, iterative debugging workflow.
Implements robust Python testing suites using pytest, advanced mocking strategies, and test-driven development best practices.
Streamlines the internal development of the Metalama framework by providing guidance on aspect testing, debugging build issues, and maintaining engineering standards.
Enforces standardized testing coverage protocols to ensure code reliability and adherence to project quality metrics.
Automates Ruby code quality audits and regression analysis to maintain high standards throughout the development lifecycle.
Generates, reviews, and executes comprehensive pytest-based testing suites to ensure code reliability, security, and performance.
Performs comprehensive code quality, security, and performance validation using deep research-driven analysis for production readiness.
Generates comprehensive unit, integration, and end-to-end tests across multiple programming languages and frameworks using standardized templates.
Tests React components and user flows using React Testing Library and Playwright to ensure frontend reliability and accessibility.
Employs a rigorous, evidence-based methodology to identify and resolve the root cause of software bugs and test failures.
Performs comprehensive security audits across codebases, dependencies, and infrastructure to identify vulnerabilities and provide automated remediation plans.
Guides the design, testing, and implementation of scalable relationship-based access control using OpenFGA best practices.
Hardens software projects through automated security scanning, vulnerability detection, and comprehensive compliance auditing.
Performs systematic code audits to identify security vulnerabilities, logic bugs, and maintainability issues with actionable feedback.
Guides Product Owners through manual verification steps to validate features before they are merged into production.
Implements stateful AI operator flows for automated security gate systems using the LangGraph framework and real-time OCR integrations.
Generates and submits professionally formatted GitHub Issues directly from the development environment, complete with reproduction steps, technical analysis, and recommended E2E tests.
Implements comprehensive, multi-layered input validation and sanitization to ensure data integrity and prevent security vulnerabilities across all application entry points.
Enforces consistent formatting, naming conventions, and type safety across PHP and TypeScript environments while automating code quality standards.
Implements inclusive user interfaces using semantic HTML, WCAG-compliant color contrast, and robust keyboard navigation.
Identifies and removes unused code, commented blocks, unreachable paths, and redundant imports to streamline codebase maintainability.
Automates comprehensive UI testing and bug discovery using browser automation to ensure high-quality frontend deployments.
Implements robust Python testing suites using pytest, focusing on isolated test design, mocking external dependencies, and asynchronous execution patterns.
Enforces security best practices for Perplexity API keys, access controls, and secret management.
Enforces human-in-the-loop validation for security-sensitive paths and high-complexity code changes within the Claude Code environment.
Develops strategic, behavior-focused unit and end-to-end tests using Vitest and Playwright to ensure robust application functionality and reliability.
Standardizes and compares AI-generated evaluations to ensure consistency, accuracy, and reproducibility across multiple runs.
Scroll for more results...