Discover Agent Skills for security & testing. Browse 105 skills for Claude, ChatGPT & Codex.
Enforces a strict Red-Green-Refactor cycle to ensure code reliability and quality through test-first implementation.
Validates source code against technical specifications and functional requirements to ensure full implementation alignment.
Applies a rigorous, hypothesis-driven methodology to identify and resolve the root causes of complex software bugs and test failures.
Performs professional-grade security audits and performance optimizations for Ethereum smart contracts using industry-standard vulnerability patterns.
Implements a rigorous, four-phase debugging methodology to identify root causes and eliminate trial-and-error bug fixing.
Simplifies the transition from legacy authentication providers to Clerk with automated migration scripts and strategy guides.
Generates comprehensive unit and integration test suites that cover edge cases and follow project-specific testing standards.
Employs a rigorous, evidence-based methodology to identify root causes and implement precise fixes for software bugs and test failures.
Enforces rigorous, evidence-based verification protocols before allowing any claims of task completion or code success.
Enforces a rigorous test-driven development cycle with standardized patterns for unit, integration, and E2E testing.
Enforces application safety by applying comprehensive security checklists and implementation patterns for authentication, data validation, and secrets management.
Enforces a rigorous test-driven development (TDD) and systematic debugging protocol to ensure production-grade code quality and reliability.
Automates a comprehensive multi-phase quality assurance workflow including builds, type checking, testing, and security scanning.
Enforces a strict Red-Green-Refactor workflow to ensure high-quality code through mandatory test-first implementation.
Enforces objective analysis and mitigates 12 common AI pitfalls during open-source software evaluations.
Implements Eval-Driven Development (EDD) to rigorously test, validate, and track the reliability of AI-assisted code changes.
Audits codebases for vulnerabilities and enforces industry-standard security patterns for data protection and authentication.
Implements eval-driven development principles to systematically test, track, and validate AI-generated code quality.
Implements an omniscient, zero-iteration debugging workflow that guarantees surgical code fixes through rigorous evidence-based deduction.
Implements a disciplined, four-phase debugging methodology to identify root causes and eliminate recurring software bugs.
Validates and debugs Claude Code hooks through unit testing, direct payload invocation, and headless CLI integration.
Enforces a strict Red-Green-Refactor cycle to ensure all production code is verified by failing tests first.
Enforces a rigorous, evidence-based methodology to identify root causes and implement reliable fixes for complex software bugs.
Implements industry-standard security practices for LangChain applications to prevent prompt injection and secure sensitive data.
Provides a comprehensive framework for stress testing and validating the Navigator browser automation CLI.
Orchestrates a specialized three-phase TDD pipeline using AI subagents for testing, implementation, and mandatory code review.
Enforces strict, evidence-based verification protocols before any task is marked as complete or fixed.
Validates Model Context Protocol (MCP) server implementations for browser automation via automated JSON-RPC testing.
Configures and optimizes Static Application Security Testing (SAST) tools to automate code vulnerability detection and enforce security standards.
Implement robust, comprehensive testing strategies using industry-standard patterns and best practices for high-quality software delivery.
Scroll for more results...