Discover Agent Skills for security & testing. Browse 105 skills for Claude, ChatGPT & Codex.
Tests React components and user flows using React Testing Library and Playwright to ensure frontend reliability and accessibility.
Guides Product Owners through systematic acceptance testing to verify user stories against defined criteria before final approval.
Automates thorough code reviews and complex architectural investigations using the Codex CLI as a specialized sub-agent.
Employs a rigorous, evidence-based methodology to identify and resolve the root cause of software bugs and test failures.
Performs comprehensive security audits across codebases, dependencies, and infrastructure to identify vulnerabilities and provide automated remediation plans.
Standardizes the developer self-review and verification process to ensure story completion before handoff or pull request.
Guides the design, testing, and implementation of scalable relationship-based access control using OpenFGA best practices.
Hardens software projects through automated security scanning, vulnerability detection, and comprehensive compliance auditing.
Enforces professional Deno TypeScript standards for project configuration, dependency management, and secure runtime permissions.
Configures LUKS disk encryption, TPM auto-unlock, and system-level security settings for Bazzite Linux.
Enforces human-in-the-loop validation for security-sensitive paths and high-complexity code changes within the Claude Code environment.
Manages overlay testing sessions and live editing of justfiles on immutable Linux systems for Bazzite-AI development.
Verifies Bazzite AI installations through comprehensive runtime tests for GPU detection, CUDA functionality, and service health.
Automates comprehensive authentication and authorization smoke tests to validate login flows, token security, and access control during release cycles.
Increases repository test coverage by identifying logic gaps, proposing high-impact test cases, and automating the verification workflow.
Automates the creation of resilient, maintainable end-to-end tests using Playwright best practices and robust selector strategies.
Validates end-to-end business flows and critical user journeys to ensure production readiness during release cycles.
Diagnoses and resolves Vue.js 3 application issues ranging from reactivity failures to SSR hydration mismatches.
Implements a root-cause-first approach to troubleshooting bugs, test failures, and unexpected software behaviors.
Systematically identifies and evaluates LLM vulnerabilities using a comprehensive 10x10 quality-diversity taxonomy for adversarial testing.
Standardizes and compares AI-generated evaluations to ensure consistency, accuracy, and reproducibility across multiple runs.
Automates pre-merge security scans to detect hardcoded secrets, insecure SSH configurations, and non-portable paths.
Validates py_trees behavior trees for syntactic correctness, action availability, and semantic consistency in robotic workflows.
Standardizes multi-layer testing workflows including Playwright E2E, Vitest components, and automated UI verification.
Implements a rigorous four-phase framework to identify root causes and apply permanent fixes for technical bugs and system failures.
Implements a rigorous four-phase framework to identify root causes and eliminate bugs through evidence-based analysis rather than guesswork.
Performs a multi-dimensional security audit by running parallel review agents and generating actionable remediation tasks.
Conducts comprehensive, multi-dimensional code reviews by running parallel agents to evaluate correctness, security, testing, and maintainability.
Performs an exhaustive 30-point automated code review covering security, architecture, performance, and UX in parallel.
Implements a rigorous, four-phase debugging methodology to identify root causes and prevent guesswork in software troubleshooting.
Scroll for more results...