Security & Testing Agent Skills

Testing & Test Writing

Develops strategic, behavior-focused unit and end-to-end tests using Vitest and Playwright to ensure robust application functionality and reliability.

Verified Completion Guardrail

Enforces rigorous verification and evidence collection before any task completion or status claim is made.

Permissions Configuration Wizard

Configures Claude Code tool permissions and security rules to control access to files, commands, and web tools.

Clerk Authentication Specialist

Implements modern, secure authentication flows using Clerk, including WebAuthn, passkeys, and pre-built UI components.

Verification & Quality Assurance

Ensures code reliability and agent output quality using real-time truth scoring and automated rollback systems.

Test-Driven Development (TDD)

Enforces a strict Red-Green-Refactor workflow to ensure high-quality, verified code implementation for every feature and bugfix.

Security Audit & OWASP Compliance

Performs comprehensive security reviews and code audits using the OWASP Top 10 framework to identify and remediate vulnerabilities.

Stateful Rule Designer

Designs complex stateful Detection & Response (D&R) rules for LimaCharlie to correlate events over time and track process tree relationships.

MoAI AST-Grep Code Intelligence

Performs structural code search, security scanning, and semantic refactoring using Abstract Syntax Tree analysis across 40+ languages.

Moai Foundation Quality

Orchestrates enterprise-grade code quality through systematic TRUST 5 validation and proactive automated standards enforcement.

Contract Schema Validator

Validates JSON schemas and fixtures to ensure data integrity and prevent breaking format changes in contract-driven applications.

Agent Check

Automatically identifies and maps project files to specialized domain agents for comprehensive code audits and workflows.

Code Health & Technical Debt Analyzer

Audits codebase quality by identifying technical debt, test coverage gaps, code duplication, and documentation issues across multiple programming languages.

Safety Memory

Implements specific coding standards and protocols for managing safety memory within agentic environments.

Testing Skills

Verifies and bulletproofs process documentation by applying Red-Green-Refactor cycles through realistic pressure scenarios.

Collect Selector

Identifies or generates the optimal data-testid selector for Playwright end-to-end testing based on a strict priority hierarchy.

Systematic Debugging

Implements a disciplined, four-phase methodology to identify and resolve the root causes of technical issues through structured investigation and hypothesis testing.

Always Works Testing Standard

Ensures code reliability by enforcing mandatory execution validation and systematic verification before any implementation is finalized.

Self-Directed Debugging

Automates quality assurance by proactively identifying requirements, verifying implementations, and auto-fixing linter errors.

Browser Testing Setup

Configures environment credentials and organization settings for automated end-to-end browser testing workflows.

Saudi Telehealth AI Testing

Validates diagnostic accuracy and clinical safety for AI-driven telehealth consultations involving Saudi patient profiles.

Safety Verification

Ensures adherence to safety standards and verification protocols during code generation and modification.

Registry Publishing Test Skill

Validates production registry publishing workflows including packaging, indexing, and installation processes.

Inclusive Design Auditor

Analyzes code to identify and mitigate hidden assumptions regarding user ability, identity, and circumstance to ensure equitable software design.

Test Fixer

Resolves failing tests automatically by analyzing error reports, diagnosing root causes, and implementing verified fixes across any framework.

Test Plan Generator

Generates optimized, multi-tier test plans by analyzing code changes to ensure comprehensive coverage without redundancy.

Inclusion Charter Setup

Configures project-specific inclusion, accessibility, and ethical design standards through an interactive setup process.

Inclusive Name Generator

Generates culturally diverse and edge-case name data to improve software representation and catch internationalization bugs.

Security Orchestrator

Conducts comprehensive security vulnerability assessments by performing deep architectural analysis of codebases to identify risks and compliance issues.

Skill Quality Gate

Validates Claude Code skill structure and content against standardized quality requirements before deployment.