Discover Agent Skills for security & testing. Browse 105 skills for Claude, ChatGPT & Codex.
Orchestrates multiple sub-agents to concurrently investigate and resolve independent test failures and bugs.
Enforces rigorous Test-Driven Development (TDD) practices with mandatory 80% coverage across unit, integration, and E2E tests.
Analyzes email messages and mailbox archives to investigate phishing, business email compromise, and security threats.
Ensures skill and Model Context Protocol (MCP) implementations align with their manifests by performing Codex-powered semantic comparisons of code against descriptions, preconditions, and effects.
Implements rigorous financial reporting controls and audit trails to meet Sarbanes-Oxley (SOX) regulatory requirements.
Simplifies the setup, management, and automation of MailHog servers for local email testing and development workflows.
Integrates and configures Better Auth, a comprehensive TypeScript authentication framework, using industry-standard security patterns.
Analyzes massive codebases and complex directories by leveraging Google Gemini's large context window and flexible file-inclusion syntax.
Implements robust security protocols, quality assurance standards, and OWASP-aligned coding practices for resilient software.
Enforces robust testing standards by preventing brittle mocks, production code pollution, and implementation-detail testing.
Verifies skill reliability and pressure resistance through a quantitative TDD cycle and compliance scoring.
Eliminates trial-and-error fixing by enforcing a rigorous four-phase root cause analysis and debugging process.
Enforces strict test-driven development cycles and comprehensive coverage requirements for robust, bug-free code implementation.
Enforces standardized testing conventions, file structures, and assertion patterns across unit, component, integration, and E2E tests.
Executes and manages Playwright E2E tests within Docker environments while ensuring reliable browser lifecycle management.
Implements secure, runtime-aware authentication and authorization systems for Hono-based TypeScript backends.
Hardens Cloudflare Workers and Pages APIs using WAF-style protections, rate limiting, and secure implementation patterns.
Replaces arbitrary timeouts with intelligent condition polling and event-based waiting to eliminate flaky tests and race conditions.
Implements an Eval-Driven Development (EDD) framework to measure and improve AI coding reliability through structured testing and metrics.
Standardizes and executes build and test tasks using VS Code's tasks.json schema across multiple programming languages.
Implements a strict Red-Green-Refactor testing cycle based on Anthropic's best practices for robust software development.
Audits and hardens system infrastructure and repository security to prevent credential leaks and vulnerabilities.
Conducts comprehensive Go code reviews by analyzing architecture, security, and test quality against idiomatic patterns and project-specific standards.
Systematically identifies the original source of software bugs by tracing execution flow backwards through the call stack.
Implements a rigorous testing methodology for Claude skills using subagent-driven pressure scenarios and test-driven development principles.
Generates bidirectional traceability matrices mapping acceptance criteria to implementation evidence and test coverage.
Automates the testing and validation of authenticated API routes using cookie-based JWT authentication and mock testing patterns.
Generates comprehensive code quality audits by validating TypeScript types, linting, formatting, and analyzing test coverage.
Audits and manages quarantined code items to ensure security compliance before integration into active development environments.
Audits Python and Node packages for malicious patterns and security vulnerabilities before they are installed in your environment.
Scroll for more results...