Language:JapaneseEnglish

Topic: Code Quality, Review & Testing

36 items in the "Code Quality, Review & Testing" topic.

Plugins (Claude Code)

NameDescriptionCategoryAuthor
42crunch-api-security-testing42Crunch integrates with Claude Code to automatically audit OpenAPI specifications, identify OWASP-aligned vulnerabilities like BOLA/BFLA, and apply AI-driven fixes within a continuous security validation cycle.Security42Crunch
aws-agents-for-devsecopsAWS DevOps Agent and AWS Security Agent assist software teams by investigating incidents, reviewing code, conducting user acceptance testing before releases, scanning for vulnerabilities, and performing penetration tests.DevelopmentAmazon Web Services
browser-useEnables Claude to control a real browser—local Chrome or a cloud-based instance—for web tasks like browsing, scraping, form filling, site testing, screenshot capture, and workflow automation.AutomationBrowser Use
chrome-devtools-mcpThis tool lets coding agents control and inspect a live Chrome browser, capturing performance traces, network requests, console logs with stack traces, and automating actions via Puppeteer.Development
claude-securityPerforms in-depth code vulnerability scanning within Claude Code sessions at adjustable effort levels, verifying findings via code-based tallying and generating agent-panel-checked patches for optional application.SecurityAnthropic
code-reviewThis tool automates pull request code reviews by deploying multiple specialized agents that assign confidence scores to findings, reducing false positive results.ProductivityAnthropic
code-simplifierThis tool refactors recently changed code to improve clarity, consistency, and maintainability without altering its original functionality.ProductivityAnthropic
coderabbitCodeRabbit is an AI-powered code review tool combining specialized architecture with 40+ static analyzers to detect bugs, vulnerabilities, and logic errors, using AST-based context analysis and project guidelines, offering actionable fixes at no cost.Productivity
codspeedCodSpeed is a performance testing toolkit offering benchmarking data, flamegraphs, and comparisons; its MCP server supplies Claude detailed profiling context to identify bottlenecks and independently refine performance.DevelopmentCodSpeed
datahub-skillsA DataHub-focused toolkit supporting connector design, pull request review, catalog search, metadata enhancement, lineage tracking, data quality checks, and connection configuration tasks.DatabaseDataHub
deepevalProvides capabilities for integrating DeepEval into AI applications, covering evaluation setup, tracing, dataset management, Confident AI reporting, and cycles of iterative refinement.DevelopmentConfident AI
feature-devThis tool coordinates specialized agents to explore codebases, design architecture, and review quality throughout the software feature development process.DevelopmentAnthropic
fiftyoneA computer vision tool for building datasets and models, offering visualization, analysis, duplicate detection, inference, evaluation, and custom plugin development.
githubA GitHub MCP server enabling repository management—creating issues, handling pull requests, reviewing code, and searching repos via GitHub's API within Claude Code.Productivity
greptileUses AI to search and interpret codebases, allowing natural-language queries to locate relevant code, trace dependencies, and explain architecture.Development
mattpocock-skillsA collection of practical agent skills by Matt Pocock covering software engineering practices like requirement clarification, spec/ticket workflows, test-driven development, code review, and domain modeling, designed for ready-to-use application rather than improvised coding.DevelopmentMatt Pocock
mergifyA terminal-based skill set for the Mergify CLI, enabling management of merge queues, stacked pull requests, Test Insights (including flaky test detection and quarantine), merge protections, and Mergify configuration.DevelopmentMergify
mlflowA skillset for using MLflow to instrument, trace, evaluate, and iteratively refine AI agents, supporting a complete workflow from monitoring through validation.MonitoringMLflow Team
nightvisionProvides skills for configuring scan targets/authentication/scope, triaging scan results, extracting OpenAPI specs from source code, and integrating scanning into CI/CD pipelines; portable across agent tools like Claude Code, Codex, and Cursor.
pagerdutyAnalyzes code changes by comparing them to historical incident data, generating PagerDuty-based risk scores to flag deployment risks before shipping.Monitoring
playwrightThis MCP server from Microsoft enables browser automation, letting Claude navigate web pages, capture screenshots, complete forms, and run automated testing tasks.Testing
postmanA Claude Code tool for managing the full API lifecycle—syncing collections, generating client code, testing, mocking, publishing docs, and security auditing—via Postman MCP Server.Development
pr-review-toolkitA suite of automated agents that perform thorough pull request reviews, covering comment quality, test coverage, error handling, type design, overall code quality, and simplification opportunities.ProductivityAnthropic
pyright-lspPyright is a Python language server that provides static type checking and enhances code intelligence features like autocompletion and navigation.DevelopmentAnthropic
qodoQodo Skills offers a library of reusable AI agent capabilities enhancing Claude for software development, enabling code quality checks, testing, security scanning, and compliance validation throughout the SDLC.DevelopmentQodo
qt-development-skillsA skill set for Qt software engineering tasks, covering reviewing Qt C++/QML code, writing QML code, and producing documentation for Qt C++/QML codebases.DevelopmentQt Group
security-guidanceThis tool checks Claude-generated code for security issues, combining pattern-based edit warnings, LLM diff review, and commit analysis to detect injection, XSS, SSRF, hardcoded secrets, and other vulnerabilities.SecurityAnthropic
sentrySentry integration for retrieving error reports and stack traces, searching issues by fingerprint, enabling developers to debug production errors from within their development environment.Monitoring
serenaAn MCP server that uses language server protocol integration to analyze code semantically, offering intelligent code comprehension, refactoring recommendations, and navigation across a codebase.Development
sonarqubeIntegrates SonarQube into AI coding agents, automatically checking code quality, security, and secrets across 40+ languages using hooks, CLI, MCP server, and slash commands.SecuritySonarSource
sourcegraphThis tool enables searching, reading, and tracing code references across repositories, assessing refactoring impact, investigating incidents through commit/diff history, and conducting security-focused code scans.Development
stackhawk-hawkscanIntegrates HawkScan DAST scanning into Claude Code by creating stackhawk.yml configuration files, executing scans through CLI or Docker, and converting security findings into prioritized remediation tasks for coding agents.SecurityStackHawk
superpowersSuperpowers is a training resource enabling Claude to brainstorm, use subagent-driven development with code review, debug systematically, apply red/green TDD, and create and test new skills.Development
ui5A plugin that helps coding agents build UI5 projects by supporting creation and validation, API reference access, linting, and adherence to UI5 development best practices.DevelopmentSAP SE

Claude Code Skills

NameDescriptionLicenseAuthor
skill-creatorThis tool supports creating, editing, and refining skills, plus evaluating them through performance benchmarking, variance analysis, and description optimization for improved triggering accuracy.Anthropic
webapp-testingA Playwright-based toolkit for testing local web apps, enabling frontend verification, UI debugging, screenshot capture, and browser log inspection.See LICENSE.txtAnthropic

Claude Code Topics