Security & Testing Agent Skills

Test-Driven Development (TDD) Mastery

Enforces a strict Red-Green-Refactor workflow to ensure all production code is verified by failing tests before implementation.

Rigorous Task Verification

Enforces evidence-based reporting by requiring fresh command execution and output validation before any task is marked as complete.

Test-Driven Development (TDD) Mastery

Enforces a strict Red-Green-Refactor cycle to ensure code reliability and eliminate technical debt through test-first implementation.

Systematic Debugging

Implements a rigorous, four-phase debugging framework to identify root causes and prevent regressions before applying code fixes.

Systematic Debugging

Implements a rigorous, four-phase methodology to identify root causes and eliminate software bugs without trial-and-error thrashing.

Verification Before Completion

Enforces a strict evidence-based protocol for verifying code changes and task completion before making success claims.

Clerk Security Hardening

Secures Clerk authentication implementations by enforcing best practices for environment variables, middleware, and webhook verification.

E2E Testing Specialist

Automates the creation, maintenance, and execution of comprehensive end-to-end testing suites to ensure robust web application performance.

Aegis Multi-Tenancy Enforcer

Enforces strict data isolation by ensuring every MongoDB query and service method includes a verified tenant identifier.

Linear API Security & OAuth

Hardens Linear integrations by implementing secure API key management, OAuth 2.0 flows, and timing-safe webhook verification.

Web Application Testing Toolkit

Automates end-to-end web application testing using Playwright with integrated server lifecycle management and UI debugging tools.

Security-First Guardrails

Implement proactive security safeguards to prevent OWASP vulnerabilities across authentication, database queries, and external API integrations.

Code Quality Guardrail

Enforces a rigorous quality framework by mandating structured planning, validation phases, and best-practice adherence before any code is modified.

Dependency Check & Optimization

Evaluates and optimizes project dependencies by suggesting native alternatives and verifying package health before installation.

Test-Driven Development (TDD) Guide

Enforces a strict Red-Green-Refactor workflow by generating failing tests before implementation to ensure high code quality and test coverage.

Dead Code Refactor

Safely removes unused code, exports, and dependencies through automated analysis and rigorous test-driven verification.

Automated Test Coverage Optimizer

Analyzes codebase test coverage reports to automatically generate missing unit, integration, and end-to-end tests.

BDD Feature Discovery

Facilitates interactive Behavior-Driven Development sessions to explore system requirements, define business rules, and generate structured Gherkin feature files.

Critic Agent

Provides skeptical, second-opinion reviews of implementation plans and conclusions to identify logical flaws and untested assumptions.

AcademicOps QA & Verification

Provides comprehensive quality assurance, verification, and criteria design to ensure code and agent sessions meet rigorous standards.

Aristotle Formal Math Prover

Translates natural language mathematical queries into Lean 4 and generates verified formal proofs or counterexamples using the Aristotle API.

QA Agent Team

Deploys a specialized team of autonomous AI agents to perform comprehensive end-to-end quality assurance across visual, functional, and UX dimensions.

OpenSpec Implementation Verifier

Verifies that code implementations align perfectly with specification, task, and design artifacts before archiving changes.

Test-Driven Development Mastery

Enforces a rigorous Red-Green-Refactor workflow to ensure high-quality, verified production code through strict TDD principles.

Ecodesign & Green IT Audit

Analyzes web applications to improve energy efficiency and digital sobriety using industry-standard eco-design practices.

Claude Eval Harness

Implements a formal evaluation framework for Claude Code sessions using Eval-Driven Development (EDD) principles.

PICT Test Designer

Generates optimized pairwise test cases and combinatorial models from software requirements or code.

TDD Workflow Enforcer

Implements a rigorous test-driven development cycle ensuring 80% code coverage across unit, integration, and end-to-end tests.

Verification Loop

Standardizes code quality through a rigorous six-phase verification process covering builds, types, linting, tests, security, and diffs.

Shell Script Input Validation

Protects shell scripts from command injection vulnerabilities by validating user-provided input against dangerous patterns.