Security & Testing Agent Skills

Software Security

Embeds secure-by-default practices into AI coding workflows to prevent vulnerabilities and ensure robust data protection across various programming languages.

Gemini Context & Review

Enables high-context code reviews and architectural analysis using Gemini 3 Pro with support for processing over 200k tokens.

QA Test Planner

Streamlines quality assurance workflows by generating structured test plans, manual test cases, and design-to-code validation reports.

Behavior-Driven Development (BDD)

Implements high-quality software features and bug fixes using Gherkin scenarios and the Red-Green-Refactor cycle.

Systematic Debugging Methodology

Implements a rigorous 4-phase debugging framework to identify root causes and prevent regression bugs.

Skill Security Scanner

Scans Claude Code skills for security vulnerabilities including prompt injection, malicious scripts, and excessive permissions.

Django Access Control & IDOR Review

Investigates and secures Django applications against Broken Object Level Authorization (BOLA/IDOR) and access control vulnerabilities through deep code tracing.

Terraform Testing Framework

Automates the creation and validation of Terraform test files to ensure infrastructure stability and code quality.

Terraform Acceptance Testing

Automates and guides the execution of Go-based acceptance tests for Terraform providers.

Kosmos E2E Testing

Automates comprehensive end-to-end testing for the Kosmos autonomous AI scientist using local models, external APIs, and Docker sandboxes.

CloudBase Auth

Simplifies the design and implementation of CloudBase Auth v2 across Web SDKs, Node.js, and HTTP APIs to manage secure user identities and authentication flows.

Bkend.ai Auth & Security

Implements secure authentication systems and access control policies for bkend.ai applications.

Delivery Validation

Automates the final verification of code changes by running tests, builds, and requirement checks before shipping.

Multi-Pass Code Review Orchestrator

Automates comprehensive, multi-layered code reviews using specialized agents to detect and fix quality, security, and performance issues.

Hook Auditor & Safety Guard

Analyzes and fixes Claude Code hook scripts to ensure security, proper error handling, and lifecycle compliance.

Performance Benchmarker

Conducts standardized performance benchmarks with strict duration rules to ensure accurate baselines and regression detection.

Performance Theory Tester

Executes controlled performance experiments to validate hypotheses with scientific rigor and repeatable metrics.

Plugin & MCP Schema Optimizer

Audits and optimizes AI plugin structures, MCP tool schemas, and security patterns for Claude Code and related platforms.

Next.js Authentication Security

Implements secure HttpOnly cookie storage and middleware patterns for Next.js applications following industry best practices.

Senior QA

Automates the generation of comprehensive test suites, performs deep coverage analysis, and scaffolds end-to-end testing frameworks for modern web applications.

Senior Security

Secures applications through automated threat modeling, penetration testing, security auditing, and robust cryptographic implementations.

Senior SecOps

Provides comprehensive application security scanning, vulnerability management, and compliance auditing tools to ensure production-grade security standards.

Code Reviewer

Automates comprehensive code reviews, security scans, and quality assessments across multiple programming languages and frameworks.

Ark Dashboard Testing & PR Visuals

Automates UI testing for the Ark dashboard using Playwright and manages visual documentation for pull requests.

Ark Chainsaw Testing

Executes and authors end-to-end tests for agentic resources using the Chainsaw framework and mock LLM configurations.

Ark Vulnerability Fixer

Automates CVE research and security patching workflows for the Ark agentic resource framework.

Ark Pentest Issue Resolver

Identifies and remediates security vulnerabilities from penetration testing reports and OWASP Top 10 audits within the Ark platform.

AI Skill Security & Quality Auditor

Audits and remediates security vulnerabilities and quality issues in AI agent skills using third-party scanning and review tools.

Agent Evaluation & Quality Assurance

Evaluates and optimizes Claude Code agents using multi-dimensional rubrics and LLM-as-judge methodologies to improve reliability and performance.

Code Review

Analyzes code for security vulnerabilities, performance bottlenecks, and adherence to Rust-specific best practices to ensure high-quality, maintainable software.