Security & Testing Claude 技能

Solidity Function Audit Team

Orchestrates a multi-agent team to perform deep, structured security audits of Solidity smart contracts with human-in-the-loop oversight.

SAST Security Configuration

Configures and optimizes Static Application Security Testing (SAST) tools to automate vulnerability detection in source code.

Temporal Python Testing

Streamlines testing for Temporal workflows and activities in Python using time-skipping, mocking, and determinism validation.

Maestro E2E Testing

Executes comprehensive end-to-end testing for data persistence pipelines within the Maestro ecosystem.

AI Code Reviewer

Performs deep, multi-model code analysis and security scanning using external AI engines to identify vulnerabilities and architectural improvements.

Lindy AI Security Essentials

Implements industry-standard security practices and configuration patterns for Lindy AI integrations and agent deployments.

Verification & Quality Assurance

Ensures codebase reliability and agent output accuracy through real-time truth scoring, automated quality checks, and intelligent Git-based rollbacks.

Code Review Expert

Analyzes, debugs, and refactors code across multiple languages to improve security, performance, and maintainability.

Beads Feature Verifier

Validates feature completion by auditing child tasks and executing comprehensive automated verification suites.

Verify Epic Completion

Validates project epic completion by auditing child features and executing cross-feature integration tests.

Multi-Dimensional Skill Reviewer

Conducts comprehensive quality assurance reviews of Claude Code skills using standardized rubrics and automated validation.

Async REPL Protocol

Standardizes asynchronous code execution and tool interactions within the Agentica REPL testing harness.

Codex Auth Manager

Simplifies OpenAI Codex CLI authentication using OAuth, API keys, and multi-account configurations.

Multi-AI Testing

Implements test-driven development workflows with independent verification to ensure high-quality code and comprehensive test coverage.

Task Verification Utility

Verifies completion of Beads tasks by executing build system validation targets including tests, linting, and security checks.

API Testing with Playwright

Automates REST and GraphQL API validation using Playwright's native testing capabilities and implementation patterns.

Review Workflow

Orchestrates a comprehensive three-step quality assurance process including validation, multi-dimensional scoring, and functional testing.

Bedrock Automated Reasoning

Mathematically verifies AI-generated responses against formal policy rules to ensure 99% compliance accuracy in high-stakes domains.

Contract Fixtures Generator

Generates valid and invalid JSON test fixtures for Command and Decision DTOs based on current contract schemas.

Amazon Bedrock AgentCore Policy

Defines and enforces deterministic security boundaries for Amazon Bedrock agents using natural language and Cedar policies.

Mini App Testing Workflow

Automates comprehensive testing for mini-apps by generating functional test cases, UI checks, and quality control reports.

API Testing with Playwright

Automates REST and GraphQL API testing, response validation, and endpoint mocking using Playwright's native capabilities.

Maestro Wiring Verification

Ensures infrastructure components are properly integrated and reachable within the execution path to eliminate dead code.

Automated TDD Runner

Automates the complete Red-Green-Refactor cycle to ensure test-driven development standards for every feature.

Bug Investigation & Root Cause Analysis

Conducts systematic debugging and root cause analysis to identify, isolate, and resolve software defects using a structured framework.

Prompt Injection Security Defense

Protects AI applications against prompt injection attacks by managing security patterns and automating regression testing.

Multi-Dimensional Skill Reviewer

Conducts comprehensive, systematic quality assessments and production-readiness reviews for Claude Code skills across five key dimensions.

Browser E2E Tester

Automates browser-based end-to-end testing to verify that feature implementations meet specific acceptance criteria.

CUI Java Unit Testing Expert

Standardizes and automates high-quality unit testing for CUI Java projects using JUnit 5 and specialized generator frameworks.

AC Criteria Validator

Validates feature implementation against acceptance criteria through automated test execution and code analysis.