Security & Testing Claude 技能
发现security & testing类别的 Claude 技能。浏览 105 个技能，找到适合您 AI 工作流程的完美功能。
Claude Plugin Auditor
Validates Claude Code plugins for structural integrity, quality standards, and development best practices.
Planning & Testing Architect
Guides project planning and implementation using specialized sub-agents and rigorous TypeScript type-testing patterns.
Technical Debt Assessment
Analyzes, quantifies, and prioritizes codebase technical debt to inform data-driven refactoring and architectural decisions.
Security Audit Logging
Implements robust, structured logging systems for security events, compliance auditing, and SIEM integration across multiple languages.
Test-Driven Development (TDD)
Implements a disciplined Red-Green-Refactor workflow for TypeScript and Rust projects within Claude Code.
Claude Code Testing Guide (zh-TW)
Standardizes software testing strategies and naming conventions using industry-recognized frameworks like ISTQB and the Testing Pyramid.
Rails Testing with Minitest
Implements rigorous Test-Driven Development (TDD) using Minitest and Rails-native patterns to ensure high-quality, maintainable codebases.
LLM Evaluation & Testing
Implements systematic evaluation patterns and metrics to measure LLM performance, validate prompt quality, and detect hallucinations.
Outfitter Stack Reviewer
Audits TypeScript code for compliance with Outfitter Stack patterns, focusing on Result types, error handling, and path safety.
Regulatory Template Generator - Gate 3
Automates the generation of production-ready regulatory templates with validated field mappings and documentation.
Regulatory Template Technical Validator
Validates mapping uncertainties and enforces rigorous testing thresholds for regulatory data templates.
Pre-Dev Dependency Mapper
Enforces explicit, versioned, and validated technology selections for software projects using standardized engineering quality gates.
Ring Installer Testing Fixture
Provides a standardized fixture for validating Ring multi-platform installer transformations and integration tests.
Shell Testing Framework
Implements comprehensive shell script testing using professional methodologies, 100% coverage standards, and structured performance validation.
Code Implementation (Gate 0)
Enforces a rigorous Test-Driven Development (TDD) workflow by routing tasks to specialized language agents.
Pytest Patterns
Implements robust Python testing suites using advanced pytest patterns for fixtures, mocking, and parametrization.
Jest React Testing
Implements comprehensive React component testing patterns using Jest and React Testing Library, covering configuration, mocking, and asynchronous interaction strategies.
Pytest Advanced Support Testing
Implements advanced Python unit and integration testing patterns for complex backend support systems using the pytest framework.
Skill Testing with Subagents
Validates AI skill reliability using a Red-Green-Refactor methodology and high-pressure compliance testing.
Condition-Based Test Waiting
Eliminates flaky tests by replacing non-deterministic timeouts with robust, state-aware condition polling.
Systematic Debugging
Enforces a disciplined, four-phase approach to identifying and resolving software bugs at their root cause.
N-Version Programming Workflow
Generates and evaluates multiple independent solutions for critical code implementations to ensure maximum reliability and security.
Systematic Debugging
Implements a rigorous four-phase debugging framework that ensures the root cause is fully understood before any code fixes are attempted.
Test-Driven Development (TDD)
Enforces a strict Red-Green-Refactor cycle to ensure code reliability and quality through test-first implementation.
Testing Anti-Pattern Guard
Enforces high-quality testing standards by preventing mock-testing, production code pollution, and brittle dependency isolation.
Agent Testing with Subagents
Implements a strict Test-Driven Development (TDD) methodology for AI agents to ensure accurate, well-structured, and reliable outputs.
Test-Driven Development (TDD) Enforcer
Enforces the Red-Green-Refactor methodology with strict quality gates and mandatory code deletion for violations.
Multi-Agent Parallel Code Review
Dispatches specialized AI reviewers in parallel to provide comprehensive feedback on architecture, business logic, and security vulnerabilities.
Dev Review (Gate 4)
Orchestrates mandatory parallel code reviews using three specialized AI agents to enforce security, logic, and quality standards.
Regulatory Template Mapping Gate 1
Maps regulatory template placeholders to backend data sources while enforcing strict naming conventions and audit-ready data lineage.
Scroll for more results...