Security & Testing Habilidades de Claude

Agent Skill Evaluator

Performs comprehensive security and safety assessments of agent skills and MCP servers to identify prompt injection risks, malicious code, and data exfiltration attempts.

Smart Test Fixer

Systematically identifies, groups, and resolves failing tests to restore codebase stability and achieve a green test suite.

Python Testing Patterns

Implements comprehensive Python testing strategies using pytest, fixtures, mocking, and test-driven development best practices.

JavaScript Testing Patterns

Implement robust testing strategies for JavaScript and TypeScript applications using modern frameworks like Jest and Vitest.

SAST Configuration & Security Scanning

Configures and automates Static Application Security Testing (SAST) tools for comprehensive vulnerability detection in application code.

Root Cause Tracing

Systematically traces bugs through call stacks to identify and fix the original source of errors rather than just their symptoms.

Solidity Smart Contract Security

Implements secure smart contract development patterns and identifies critical vulnerabilities in Solidity code to ensure robust blockchain applications.

Web3 Smart Contract Testing

Implements comprehensive smart contract testing suites using Hardhat and Foundry to ensure blockchain security and gas efficiency.

VS Code Bug Hunter

Detects hidden bugs, memory leaks, and race conditions in VS Code extensions using systematic static and dynamic analysis techniques.

Eval Harness (Frozen Evaluation)

Gates and validates self-improvement cycles through frozen benchmarks and regression testing to prevent AI quality degradation.

Testing Strategy Builder

Architects comprehensive software quality frameworks by providing structured templates, coverage targets, and cross-platform testing methodologies for unit, integration, and E2E validation.

Security & Vulnerability Assessment

Conducts evidence-based security audits and vulnerability assessments to ensure production-grade application hardening.

Code Review Playbook

Facilitates high-quality software development through structured review processes, standardized comment patterns, and comprehensive quality checklists.

Self-Test Skill Invocation

Verifies that the skill loading and invocation framework is functioning correctly by returning a specific canary phrase.

OWASP Mobile Security Checker

Analyzes Flutter and mobile applications for security vulnerabilities based on the 2024 OWASP Mobile Top 10 guidelines.

Test Writing Standards

Generates focused, behavior-driven tests for core user flows and business logic while prioritizing clear naming and execution speed.

Global Error Handling

Implements resilient error management systems using specific exception types, centralized boundaries, and user-friendly messaging to ensure application stability.

Workflow Testing with Subagents

Validates the clarity of orchestrator prompts and workflow documentation by simulating real-world execution failures with subagents.

Security Assessment Tools

Performs comprehensive security audits, network reconnaissance, and vulnerability management directly from the command line using Shodan, OSV, and KEV integrations.

Bitcoin Auth Diagnostics

Diagnoses and troubleshoots authentication failures, signature verification errors, and integration issues within the bitcoin-auth library ecosystem.

Root Cause Tracing

Systematically traces bugs backward through the call stack to identify and fix the original trigger rather than the symptom.

BAP Identity Management

Manages Bitcoin Attestation Protocol (BAP) identities and encrypted .bep backup files using specialized command-line tools.

Buck2 Test Workflow

Executes a systematic multi-level testing strategy for Buck2 builds to ensure local changes don't break immediate targets or downstream dependencies.

Test-Driven Development (TDD)

Enforces a strict Red-Green-Refactor workflow to ensure high-quality, verified code through test-first implementation.

Smart Test Fixing

Systematically identifies, groups, and resolves failing test suites using an intelligent prioritization workflow and smart error analysis.

Systematic Debugging

Implements a rigorous four-phase framework to identify root causes and ensure permanent fixes before modifying code.

Global Validation

Implements comprehensive, secure input validation across client and server layers using allowlists and sanitization to protect against injection attacks.

Valid Test Skill

Validates skill scanner directory traversal and YAML frontmatter extraction using standardized metadata structures.

Prompt Optimization Analyzer

Analyzes and optimizes AI skill prompts to improve trigger reliability, reduce token consumption, and eliminate common anti-patterns.

Quarkus Native Test

Executes native image tests using GraalVM or Mandrel to validate that Quarkus applications compile and function correctly in native environments.