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。
Validates that code implementation strictly adheres to PRD specifications without unauthorized substitutions or omissions.
Applies a rigorous TDD cycle to verify and harden Claude Code skills against pressure and rationalization.
Enforces a strict Red-Green-Refactor cycle to ensure code reliability and high test coverage.
Conducts comprehensive security audits, threat modeling, and remediation guidance for software projects using standardized safety frameworks.
Implements a rigorous four-phase framework to identify root causes and ensure stable bug fixes before implementation.
Enforces best practices in software testing by preventing mock reliance, production code pollution, and incomplete test doubles.
Benchmarks and validates Nablarch-specific AI skills using isolated sub-agent execution to ensure high-precision performance and regression detection.
Validates JSON schemas and fixtures to ensure data integrity and prevent breaking format changes in contract-driven applications.
Implements multi-layered data validation across system boundaries to make software bugs structurally impossible.
Validates and audits Supabase Row Level Security (RLS) policies using automated test patterns for user isolation and multi-tenant security.
Implements production-ready Row Level Security (RLS) policies and security audits for Supabase applications.
Implements secure Clerk authentication patterns for Next.js applications using both App Router and Pages Router.
Validates Clerk authentication setups and automates security audits, E2E testing, and unit test generation for robust user identity management.
Guides developers through the refactoring stage of the Test-Driven Development cycle to enhance code quality without altering behavior.
Orchestrates enterprise-grade code quality through systematic TRUST 5 validation and proactive automated standards enforcement.
Performs structural code search, security scanning, and semantic refactoring using Abstract Syntax Tree analysis across 40+ languages.
Performs comprehensive security reviews and code audits using the OWASP Top 10 framework to identify and remediate vulnerabilities.
Generates robust unit, integration, and end-to-end test suites to ensure code reliability and comprehensive edge case coverage.
Ensures code reliability and agent output quality using real-time truth scoring and automated rollback systems.
Ensures financial models and underwriting tools are accurate, reasonable, and defensible through systematic cross-checking and automated testing.
Streamlines the configuration and testing of 19+ OAuth authentication providers for Clerk-powered applications.
Implements modern, secure authentication flows using Clerk, including WebAuthn, passkeys, and pre-built UI components.
Automates the Test-Driven Development cycle for autonomous feature implementation and high-integrity code generation.
Implements a hypothesis-driven workflow to isolate root causes and resolve complex software regressions with precision.
Automates the full development lifecycle from test-driven development and debugging to performance optimization and multi-agent code reviews.
Analyzes project dependencies across multiple ecosystems to detect, report, and automatically fix known security vulnerabilities and CVEs.
Validates and registers version-controlled hook manifests to automate governance and enforcement within the Betty infrastructure.
Ensures code excellence and security by performing systematic reviews based on industry best practices and rigorous safety standards.
Analyzes, documents, and dissects complex network protocols for security research, debugging, and interoperability.
Tests and validates Betty Framework hook manifests to ensure correct trigger logic and command execution before deployment.
Scroll for more results...