security & testing向けのClaudeスキルを発見してください。105個のスキルを閲覧し、AIワークフローに最適な機能を見つけましょう。
Executes comprehensive verification suites including tests, builds, and linting to ensure project readiness and plan completion.
Analyzes Go code performance by running benchmarks, identifying memory bottlenecks, and suggesting high-impact optimizations.
Evaluates open source projects against standardized health and performance metrics using multi-agent research.
Implements the GARY (Go Ahead, Repeat Yourself) principle to write highly readable and maintainable RSpec tests.
Implements a systematic, TDD-driven debugging workflow that identifies root causes and verifies fixes through hypothesis testing and localized Czech triggers.
Protects AI workflows by implementing runtime secret scanning, PII masking, and prompt injection defense mechanisms.
Ensures Claude Code skills meet structural, naming, and security standards through automated auditing.
Orchestrates comprehensive multi-perspective code audits by automatically routing changes to specialized security, database, and API review agents.
Performs automated OWASP Top 10 security audits to identify vulnerabilities like SQL injection, XSS, and broken authentication in application code.
Streamlines API mocking using MSW handlers and environment-specific setups for consistent development and testing.
Validates Rust CLI behavior through automated smoke checks, dry-runs, and artifact generation to ensure system stability.
Implements an inverted testing pyramid strategy using Playwright for E2E workflows and Vitest for pure function unit tests.
Implements robust end-to-end testing suites using Cypress patterns for resilient, deterministic, and accessible web application verification.
Audits Go codebases for common anti-patterns, goroutine leaks, and error handling issues to ensure production-grade quality.
Executes Go test suites, performs deep coverage analysis, and identifies logic gaps to ensure production-grade code reliability.
Implements robust end-to-end web testing using Playwright with a focus on accessibility-first locators, page object models, and reliable auto-waiting assertions.
Streamlines Galaxy Project test execution and authoring using pytest and the specialized run_tests.sh environment.
Implements robust end-to-end web testing patterns using Playwright to verify complete user workflows through real browsers.
Implements robust React component tests using accessibility-first queries and realistic user event simulations.
Implements standardized Vue 3 component testing patterns for rendering, user interactions, and state management mocking.
Implements resilient React error handling patterns using error boundaries, fallback UIs, and recovery mechanisms to prevent application crashes.
Implements standardized Vue 3 component testing patterns using Vue Test Utils for reliable interaction and state verification.
Automates local web application testing and UI debugging using Playwright and integrated server lifecycle management.
Automates API contract validation, performance benchmarking, and gRPC service testing using declarative HTTP tools and load testing frameworks.
Guides developers through the Red-Green-Refactor discipline to build robust, behavior-driven software with optimal test coverage.
Simplifies web discovery and penetration testing by providing expert command templates and analysis patterns for the FFUF tool.
Conducts comprehensive security audits and vulnerability assessments to identify and remediate code and infrastructure risks.
Implements a rigorous four-phase debugging methodology to identify root causes and ensure stable, long-term software fixes.
Builds robust, maintainable end-to-end browser tests using Playwright best practices and the Page Object Model.
Enforces safe Git workflows by blocking direct pushes to primary branches and preventing unapproved force pushes within Claude Code.
Scroll for more results...