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。
Implement reliable, high-performance end-to-end test suites using industry-standard patterns for Playwright and Cypress.
Builds robust evaluation frameworks to measure performance, validate context engineering, and track improvements in agentic systems.
Implements comprehensive Python testing strategies using pytest, including unit tests, integration tests, and advanced mocking patterns.
Analyzes Git history to map code ownership, identify security risks like low bus factors, and visualize developer-to-file topologies.
Audits and aligns project dependencies with infrastructure documentation to ensure security, consistency, and clean codebases.
Automates comprehensive code audits using research-backed security standards, performance pattern detection, and automated quality enforcement.
Prevents redundant troubleshooting by integrating a persistent, searchable memory system for software bugs and resolutions.
Validates that code implementations align perfectly with specifications, tasks, and design documents before archiving changes.
Implements professional TypeScript testing patterns using Jest and Vitest to ensure high-quality, reliable code.
Enforces BDD-style unit testing practices and standardizes Golang test structures using Ginkgo and Gomega.
Audits TON blockchain smart contracts written in FunC to identify critical security vulnerabilities and logic errors.
Enforces a rigorous, four-phase debugging methodology to identify root causes and implement stable fixes without guesswork.
Enforces a strict test-first development workflow by requiring failing tests before any production code is written.
Enforces a strict evidence-based workflow requiring successful command execution and output validation before any task is marked as complete.
Verifies code implementation and document accuracy using multi-model consensus to ensure high-quality, machine-actionable results.
Analyzes implementation changes for security vulnerabilities and risks using a structured framework based on industry best practices.
Employs a disciplined methodology to identify and resolve the root causes of software bugs rather than masking symptoms.
Streamlines the configuration and execution of promptfoo for rigorous LLM evaluation and regression testing.
Audits project dependencies for security vulnerabilities, license compliance risks, and version staleness across multiple programming ecosystems.
Generates comprehensive, framework-agnostic test suites with deep coverage analysis and parallel test writing.
Performs automated security audits and OWASP Top 10 compliance checks on pull requests, commits, or entire codebases.
Automates the creation of secure 1Password items including logins, API keys, and notes via the 1Password CLI.
Resolves software defects through automated test-driven reproduction, root cause analysis, and rigorous regression verification.
Retrieves credentials, API keys, and secure documents from 1Password using the official op CLI integration.
Orchestrates a multi-agent team of specialized AI reviewers to perform comprehensive security, architectural, and performance code reviews.
Refactors complex codebases safely using characterization tests, incremental changes, and automated verification to ensure behavior preservation.
Validates code quality and applies precision fixes using an isolated, 6-phase automated workflow.
Implements a comprehensive three-layer testing strategy covering structural validation, semantic intent, and system performance optimization.
Validates infrastructure configurations and deployments through automated security scanning, cost analysis, and post-deployment verification.
Implements robust pytest-style evaluation frameworks to measure LLM performance, RAG quality, and output faithfulness.
Scroll for more results...