Discover Agent Skills for security & testing. Browse 105 skills for Claude, ChatGPT & Codex.
Ensures the accuracy of AI outputs by systematically cross-referencing all claims with file-based evidence and real-world data.
Maps product features to test suites to identify critical testing gaps and perform risk-based quality analysis.
Analyzes test coverage in depth to identify uncovered lines, branches, and functions with actionable reporting.
Validates software specifications against requirements to ensure completeness, consistency, and testability within development workflows.
Performs comprehensive WCAG 2.1 AA accessibility audits to ensure web applications are inclusive and compliant.
Standardizes Semgrep integrations with specific rules for API communication, security validation, and automated vulnerability remediation.
Automates visual regression testing to detect UI inconsistencies across browsers and viewports using tools like Percy, Chromatic, and Playwright.
Measures test suite effectiveness by injecting artificial bugs into code to identify gaps in test coverage and logic.
Generates comprehensive traceability matrices mapping requirements to test cases for complete software coverage visibility.
Generates comprehensive, multi-framework unit tests by analyzing code structure and identifying critical edge cases.
Generates comprehensive unit and integration tests across multiple programming languages by following local project conventions.
Implements comprehensive software testing frameworks using standardized unit, integration, and performance testing patterns.
Tests Datarails finance API field compatibility to optimize data aggregation performance and reliability.
Analyzes source code for quality, security vulnerabilities, and anti-patterns to ensure production-grade standards.
Conducts comprehensive OWASP-style security audits to identify and remediate vulnerabilities within your codebase.
Automates the Red-Green-Refactor cycle to ensure code reliability and high-quality implementation through test-driven development.
Implements comprehensive testing architectures including unit, integration, and end-to-end tests using industry-standard patterns and coverage metrics.
Implements a strict Red-Green-Refactor methodology to ensure high-quality, tested code through automated multi-agent orchestration.
Validates code implementations against requirements through automated linting, testing, and requirement matching.
Performs comprehensive OWASP-style security audits to identify vulnerabilities and provide actionable remediation steps within your codebase.
Verifies that code changes satisfy original requirements through automated syntax checks, testing, and regression scans.
Generates and executes comprehensive end-to-end tests across multiple frameworks and browsers to ensure robust user journeys.
Enforces strict multi-tenant data isolation by ensuring communityId is applied to all MongoDB queries and service logic.
Verifies research claims and prevents hallucinations using Goal-Oriented Action Planning combined with Ed25519 cryptographic signatures.
Implements robust software through a strict Red-Green-Refactor cycle to ensure high code quality and reliability.
Automates end-to-end testing and browser interactions for local web applications using Playwright and custom server management.
Performs high-stakes research using Goal-Oriented Action Planning and Ed25519 cryptographic signatures to eliminate hallucinations and verify source integrity.
Conducts verifiable, high-stakes research using Goal-Oriented Action Planning and Ed25519 cryptographic signatures to prevent AI hallucinations.
Automates end-to-end testing and browser interactions for local web applications using Playwright and Python.
Implements automated user provisioning and lifecycle management via Scalekit's Directory API and real-time webhooks.
Scroll for more results...