Discover Agent Skills for security & testing. Browse 105 skills for Claude, ChatGPT & Codex.
Applies the RED-GREEN-REFACTOR cycle to process documentation to ensure AI agents follow instructions under high-pressure scenarios.
Eliminates flaky tests and race conditions by replacing arbitrary timeouts with intelligent state-based condition polling.
Implements multi-tiered data validation strategies to prevent deep execution failures and make software bugs structurally impossible.
Systematically traces bugs through the call stack to identify original triggers and implement long-term fixes.
Eliminates common testing mistakes by enforcing strict TDD principles and preventing mock-related technical debt.
Implements a rigorous four-phase framework to identify root causes and resolve complex technical issues without introducing regressions.
Accelerates debugging by dispatching multiple independent Claude agents to investigate and resolve concurrent system failures.
Conducts comprehensive security assessments and penetration tests across AWS, Azure, and Google Cloud Platform environments.
Enforces rigorous, evidence-based verification before claiming any programming task or bug fix is complete.
Conducts a rigorous 20-metric technical audit to evaluate code quality, production readiness, and AI-generated slop.
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.
Provides expert techniques and commands for escalating user privileges on compromised Linux and Windows systems.
Performs comprehensive security assessments to identify, exploit, and remediate Cross-Site Scripting (XSS) and HTML injection vulnerabilities in web applications.
Conducts comprehensive security assessments to identify and demonstrate cross-site scripting and HTML injection vulnerabilities in web applications.
Provides comprehensive methodologies and commands for elevating user privileges on Linux and Windows systems during security assessments.
Automates the planning, implementation, and verification of unit and integration tests across multiple programming domains.
Triages Java-related findings and static analysis issues during the finalization phase of the AI coding workflow.
Manages WebFetch permissions through security assessment patterns and trusted domain verification standards.
Automates the retrieval, triage, and resolution of SonarQube issues within your development workflow.
Streamlines the triage of marketplace plugin findings by providing decision-making guidelines for testing and validation errors.
Enforces a strict verification protocol that halts execution on errors or workarounds to ensure reliable AI orchestration and root cause resolution.
Enforces standardized Java testing patterns using CUI libraries for reliable data generation and contract validation.
Standardizes Java unit testing using JUnit 5 with the Arrange-Act-Assert (AAA) pattern and strict coverage requirements.
Conducts comprehensive security audits, threat modeling, and remediation guidance for software projects using standardized safety frameworks.
Enforces standardized Jest unit testing patterns and coverage requirements for reliable JavaScript development.
Streamlines Java code maintenance by enforcing prioritization frameworks, refactoring triggers, and compliance verification standards.
Streamlines Quarkus development with CDI patterns, native image optimization, and standardized testing frameworks.
Diagnoses and audits Claude Code permission settings to identify security risks, syntax errors, and redundant configurations.
Standardizes Maven integration testing by configuring the Failsafe plugin, naming conventions, and dedicated build profiles.
Scroll for more results...