Discover Agent Skills for security & testing. Browse 105 skills for Claude, ChatGPT & Codex.
Manages centralized configuration storage in LimaCharlie, including secrets, detection rules, YARA rules, and lookup tables.
Enforces a strict evidence-based workflow by requiring fresh verification output before any task is marked as complete or successful.
Executes comprehensive security incident response workflows including threat investigation, containment, and forensic evidence collection using LimaCharlie's capabilities.
Guides the development, testing, and deployment of custom LimaCharlie extensions to integrate third-party tools and automate security workflows.
Designs and implements Python-based automated response workflows and security orchestration scripts within the LimaCharlie platform.
Automates the retrieval, triage, and resolution of SonarQube issues within your development workflow.
Automates the implementation of production-ready email and password authentication for Next.js applications using Supabase.
Streamlines the triage of marketplace plugin findings by providing decision-making guidelines for testing and validation errors.
Validates and optimizes Solidity smart contracts using professional testing frameworks like Hardhat and Foundry.
Detects and prevents the exposure of credentials, API keys, and sensitive data within code and configuration files.
Performs deep, multi-step technical investigations and complex reasoning using high-effort analysis patterns.
Enforces rigorous Cypress E2E testing standards to ensure reliable, high-quality browser automation in CUI projects.
Builds reliable end-to-end and component tests using Playwright, TypeScript, and modern architectural patterns like the Page Object Model.
Validates experimental lab procedures against LA-Bench standards using automated scripts and semantic subagent analysis to ensure technical accuracy and format compliance.
Executes a systematic, hypothesis-driven workflow to reproduce, isolate, and fix complex software bugs while ensuring code remains lint-clean and regression-free.
Scans infrastructure configuration files for security vulnerabilities and misconfigurations in Docker, Kubernetes, and Terraform.
Generates high-quality acceptance criteria and test specifications using industry-standard Behavior-Driven Development (BDD) and Gherkin syntax.
Implements comprehensive Python testing strategies using pytest, fixtures, and mocking to ensure high-quality, reliable codebases.
Implements secure authentication and authorization systems using JWT, OAuth2, and robust access control patterns.
Implements comprehensive Python testing strategies using pytest, mocking, and test-driven development best practices.
Ensures process documentation and skills remain effective under pressure by applying a rigorous Red-Green-Refactor testing cycle to prevent agent rationalization.
End of results