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。
Systematically diagnoses and repairs failing test suites using smart error grouping and prioritized resolution strategies.
Provides standardized patterns and implementations for unit testing external REST API integrations using WireMock.
Implements efficient JUnit 5 parameterized testing patterns to execute single test methods with multiple data combinations and boundary cases.
Generates robust JUnit 5 test suites for Java utility classes and static methods using AssertJ assertions and edge-case validation.
Implements robust, performance-optimized testing suites for Spring Boot applications using modern patterns and Testcontainers.
Generates comprehensive unit tests for Spring Boot REST controllers using MockMvc and Mockito to validate API endpoints in isolation.
Establishes robust frameworks for measuring, testing, and optimizing AI agent performance through multi-dimensional rubrics and LLM-as-judge methodologies.
Automates the creation of detailed GitHub issues for local integration test failures by analyzing logs and agent metadata.
Conducts rigorous, adversarial code reviews across multiple languages to identify security vulnerabilities, performance bottlenecks, and poor coding patterns.
Streamlines web application testing with comprehensive E2E strategies, Playwright automation, and systematic deep audit workflows.
Enforces safety guardrails and coding standards by creating custom behavioral rules for Claude Code.
Conducts systematic architectural audits using the Functional, Practical, and Foundation (FPF) framework to evaluate system design and quality.
Validates Claude Code skills using a TDD-style methodology and fresh subagent instances to eliminate priming bias.
Audits shell and Bash scripts for correctness, safety, and cross-platform portability to ensure reliable automation.
Enforces rigorous validation, testing, and evidence-based reporting before any task is declared complete.
Resolves software defects through mandatory root cause analysis, automated regression testing, and structured verification.
Automates comprehensive code reviews using the Codex CLI to identify bugs, security vulnerabilities, and logic errors.
Detects project test frameworks and executes suites to generate structured JSON checkpoints of pass/fail results.
Performs systematic security audits to identify exploitable vulnerabilities like XSS, SQL injection, and authentication flaws with high-confidence reporting.
Audits Claude Code skills for security vulnerabilities, prompt injection, and malicious patterns before installation.
Analyzes code changes and executes configurable AI skills to generate structured security and bug reports.
Identifies security vulnerabilities, logical bugs, and code quality issues in local git branch changes.
Transforms AI-detected code findings into permanent, deterministic lint rules to prevent recurring bugs.
Performs deep security audits on Django applications to identify and fix Broken Object Level Authorization (BOLA) and IDOR vulnerabilities.
Streamlines Clerk authentication setup with patterns for Next.js 16, API keys beta, and 2025-11-10 breaking changes.
Streamlines the implementation of secure, self-hosted authentication systems for TypeScript and Cloudflare Workers environments.
Implements privacy-first bot protection and CAPTCHA alternatives for web applications and forms.
Implements production-grade security patterns for authentication, input validation, OWASP compliance, and LLM safety.
Performs a comprehensive 44-dimension audit of codebases to ensure production readiness and alignment with Ring engineering standards.
Redirects to specialized testing sub-skills for unit, E2E, integration, LLM, and performance testing automation.
Scroll for more results...