Discover Agent Skills for security & testing. Browse 105 skills for Claude, ChatGPT & Codex.
Automates the creation and configuration of Claude Code hooks for linting, formatting, and static analysis.
Provides core concepts, entity relationships, and configuration references for the Testany automation and testing platform.
Integrates Google Gemini CLI to provide holistic codebase analysis, architectural peer reviews, and multi-perspective design validation for high-stakes development decisions.
Conducts comprehensive, agent-led code reviews and security audits with actionable fixes and clear pass/fail verdicts.
Automates visual quality assurance by capturing and analyzing screenshots across web and mobile platforms using Claude's vision capabilities.
Provides standardized guidelines and best practices for conducting effective code reviews and delivering constructive feedback.
Maintains the integrity of the Claude Skill ecosystem by analyzing file changes and mapping them to mandatory verification validators.
Validates workflow schemas, error handling patterns, and multi-part agent structures to ensure consistent agent orchestration.
Automates deterministic end-to-end HTTP testing for ACP-based plugins using JSON-driven specifications.
Validates that project configuration files remain within defined token limits to ensure optimal model performance and context management.
Executes a comprehensive suite of validation checks to ensure project integrity and multi-agent system consistency.
Validates the configuration and structural integrity of the team-shinchan memory system and documentation files.
Automates the UI testing workflow by using screenshots and Claude Vision to identify layout issues and visual bugs without writing test code.
Diagnoses Testany automated test failures by analyzing execution logs and identifying root causes with secure data retrieval.
Automates end-to-end testing with AI-powered self-healing capabilities to maintain robust UI test suites.
Automates test suite generation and increases code coverage using AI-driven semantic analysis and edge-case detection.
Conducts deep code investigations to identify and resolve the underlying source of bugs rather than patching superficial symptoms.
Automates comprehensive security audits and vulnerability scanning across source code, dependencies, and infrastructure.
Automates and optimizes modern end-to-end testing workflows using the Playwright framework for robust web application verification.
Validates Claude Code skill files for schema compliance, naming conventions, and input validation rules.
Hardens operational security and minimizes surveillance exposure for privacy-critical applications and communications infrastructure.
Generates comprehensive test case documentation and Testany-compatible automation scripts from natural language requirements.
Automates the creation and improvement of test suites using AI-driven tools and coverage gap analysis.
Verifies the global consistency of modular code structures and data schemas using mathematical Čech cohomology principles.
Transforms mathematical proofs into interactive games using Gödel's Dialectica interpretation for formal verification and strategy extraction.
Organizes software implementation into test-driven vertical slices that deliver demonstrable value in every development cycle.
Automates local web application testing and interaction using Playwright and managed server lifecycles.
Enforces a rigorous Red-Green-Refactor cycle by requiring failing tests before any production code is implemented.
Implements comprehensive security testing strategies including SAST, DAST, and manual penetration testing patterns.
Implements robust Python testing strategies using pytest, mocking, and property-based testing patterns.
Scroll for more results...