Discover Agent Skills for security & testing. Browse 105 skills for Claude, ChatGPT & Codex.
Diagnoses and resolves behavioral inconsistencies between Erlang and JavaScript targets in cross-platform Gleam projects.
Performs comprehensive security audits and provides implementation patterns to protect applications against common vulnerabilities and data exposure.
Audits code for vulnerabilities and enforces industry-standard security patterns for authentication, data handling, and API development.
Automates a multi-phase verification process to ensure code quality through builds, type checking, testing, and security scans.
Performs rapid security assessments on code changes to identify common vulnerabilities and risks before deployment.
Verifies code quality and logic by cross-referencing implementation details across multiple AI models including GPT and Gemini.
Performs automated daily configuration audits and provides actionable improvement suggestions for your project environment.
Diagnoses and fixes complex bugs in full-stack .NET and Angular applications using a systematic, evidence-based approach.
Provides comprehensive testing patterns and implementation guides for Next.js App Router and Supabase applications using Vitest and Playwright.
Enforces project standards and syntax correctness through automated linting and static analysis tools.
Automates comprehensive quality checks, build verification, and error remediation loops within the Plan Marshall workflow.
Automates the creation, configuration, and coverage analysis of Jest unit tests for JavaScript applications.
Implements secure, framework-agnostic authentication and authorization systems using the Better Auth TypeScript framework.
Configures secure execution environments for Claude Code with granular file system and network isolation boundaries.
Orchestrates systematic JavaScript test quality improvements and coverage enhancements while strictly maintaining production code integrity.
Validates AI-driven coding workflows using a hybrid system of automated scripts and LLM-as-judge assessments to ensure reliability.
Analyzes and consolidates WebFetch domain permissions with automated security research and validation for Claude Code.
Systematically identifies and destroys flaws in code, architecture, and plans through a disciplined falsification process.
Masters the Bash Automated Testing System (Bats) to create comprehensive unit tests and CI/CD validation for shell scripts.
Implements a robust workflow that prioritizes algorithmic correctness through naive implementations before applying performance optimizations.
Identifies and validates hidden technical assumptions to prevent logic errors and edge-case bugs before implementation.
Automates deep QA processes including edge case verification, code quality audits, and comprehensive test reporting.
Designs comprehensive end-to-end test patterns based on user stories and critical verification checkpoints.
Implements Test-Driven Development patterns to enable LLM self-correction and autonomous iteration through feedback loops.
Generates and analyzes JavaScript test coverage reports to identify untested code paths and improve application reliability.
Orchestrates parallel analysis agents to assess Java code quality, test coverage, and standards compliance in a single command.
Identifies and resolves software bugs by performing deep root cause analysis and implementing mandatory regression tests.
Streamlines the creation, debugging, and optimization of TypeScript and NestJS unit tests using Jest and industry-standard mocking patterns.
Streamlines end-to-end and integration testing for NestJS projects using real infrastructure, Docker, and the Given-When-Then pattern.
Generates zero-drift, enterprise-grade code for the APEX OmniHub ecosystem, specializing in Web2/Web3 bridges and rigorous ARMAGEDDON testing.
Scroll for more results...