Playwright plugins

Automate technical debt reduction, dependency updates, and code refactoring by scanning for vulnerabilities and code smells, generating prioritized remediation plans, and leveraging AI-powered test automation and code review.

Delegate expert-level code reviews, security audits, penetration tests, QA automation, accessibility compliance checks, performance optimizations, chaos engineering, and compliance validations to specialized sub-agents across codebases, infrastructure, and systems.

Run Playwright browser automation locally via Claude to perform end-to-end testing, web scraping, and UI interaction — including taking screenshots, filling forms, and clicking elements — without needing any API keys or secrets.

Implement a complete QA and testing workflow: set up A/B tests with hard gates, automate browser testing with Playwright/Puppeteer, enforce code review checklists and TDD, debug systematically, and fix failing tests using pytest patterns.

Run comprehensive SEO audits and optimizations: crawl up to 500 pages, analyze backlinks and Core Web Vitals, validate schema and hreflang, generate content clusters and sitemaps, and track regressions—all from Claude Code.

Drive a real Chrome browser via CDP for automated web scraping, testing, and multi-page workflows using coordinate clicks and screenshots without CSS selectors.

Automate web tasks with natural language: drives a local Playwright browser, captures screenshots and action logs, visually self-verifies results. Also generates reusable Python CLI tools from the workflows.

Semi-automated research assistant for academic literature review, paper writing, and project knowledge management. Integrates with Zotero and Obsidian to search papers, extract writing patterns, generate structured manuscripts, manage citations, and produce conference materials. Also includes general-purpose development tools for code quality, debugging, Git workflows, and project scaffolding.

Generate Playwright tests from specs or user stories, migrate Cypress/Selenium suites, fix flaky failures, and report results to TestRail or Slack — all within your existing Playwright workflow.

Generate and execute end-to-end browser tests for full user workflows spanning frontend and backend using Playwright, Cypress, or Selenium. Create tests with page objects, scenarios, and assertions, then run them to validate complete user journeys in browsers.

Audit web pages and components for WCAG 2.1/2.2 accessibility compliance using axe-core, Playwright, Pa11y, Lighthouse, and more. Detect ARIA errors, keyboard navigation issues, color contrast violations, and screen reader incompatibilities, then generate markdown reports with prioritized fixes and code examples.

Detect UI visual regressions by capturing screenshots of components or pages with Playwright or Cypress, comparing against baselines across responsive breakpoints, generating pixel diffs, analyzing changes, and producing markdown reports with recommendations. Integrates with Percy, Chromatic, BackstopJS, and CI workflows.

Build and test .NET applications with Claude Code using curated skills and agents for modern C# (12+), Akka.NET actors, .NET Aspire orchestration, Playwright/TestContainers/Verify testing, BenchmarkDotNet profiling, EF Core optimization, NuGet/CPM package management, and CI/CD caching.

Generate fast (<5min) smoke test suites in Jest-style JavaScript for critical paths like system health, authentication, and core features, then run them post-deployment via Playwright, curl, Bash scripts, or CI/CD to verify UI, APIs, and functionality.

Design, build, and test Vizro dashboards from concept to deployment using a structured 2-phase workflow that covers requirements, layout design, visualization selection, Python implementation, and Playwright-based testing.

Execute 175 slash commands to automate git workflows like branching/PR creation/issue syncing with Linear, code quality reviews/refactors/fixes, test generation/setup/coverage, CI/CD pipelines, security/performance audits, documentation generation, project scaffolding/setup, and deployments across JS/TS/Python/Go/Rust/Svelte stacks.

Instruct Claude Code to automate browser tasks with Playwright: it auto-detects dev servers, launches a visible browser, runs E2E tests, fills forms, takes screenshots, validates responsive design and UX, handles login flows, checks links, and generates clean scripts in /tmp.

Automate development workflows by walking through code files line-by-line in VSCode or Vim, logging timestamped work sessions with file changes in daily Markdown, generating detailed issue specs staged in Git, engaging in adaptive Socratic quizzes for learning, and delegating UI validation tasks to a browser agent using Chrome DevTools.

Orchestrate complex test workflows across Jest, Vitest, pytest, Playwright, and Cypress with parallel execution, test sharding, dependency management, flakey retries, affected test selection, and result aggregation in GitHub Actions or GitLab CI. Generate optimized configs for CI/CD pipelines.

Create and manage snapshot tests for UI components and data using Jest, Vitest, or pytest to catch regressions. Analyze test failures with intelligent diff reviews, selectively update snapshots for intentional changes, validate and organize snapshot files, then generate detailed analysis reports.

Unified hub for managing and executing skills, agents, and commands in Claude Code. Enables AI-assisted workflows including code review, testing, documentation generation, UI creation, multi-agent coordination, and context optimization. Provides 130+ skills, 5 agents, and 3 commands for automating development tasks.

Integrate Azure SDKs into TypeScript/Node.js apps to build AI-powered services for content moderation, document extraction, translation, voice interaction; manage storage, queues, databases like Cosmos and Postgres; handle authentication, Key Vault secrets, Event Hubs, Service Bus messaging; enable monitoring, real-time Web PubSub, and Playwright testing.

Automate frontend workflows: generate Tailwind-powered landing pages and multi-page marketing sites from briefs with screenshots and videos; set up Tailwind v4 themes and install shadcn/ui components in React/Next.js apps; review visual designs, extract design systems, and audit React performance patterns.

Automate comprehensive project management: audit health and permissions, generate architecture/user docs and roadmaps, handle git workflows/PRs/releases, test UX/onboarding/responsiveness via browser, consult multi-AI models, and post team updates with feedback triage.

Test web apps for cross-browser compatibility using Playwright locally across Chromium, Gecko, WebKit, and mobile viewports, or on real devices via BrowserStack, Sauce Labs, LambdaTest, Kobiton. Run interactive tests, scan JS/CSS risks, and generate reports with browser matrices.

Enforce TDD and SDD workflows with AI-driven agents that scaffold projects, generate tests, debug failures, reverse-engineer docs, and orchestrate batch task execution from design plans.

Build, deploy, debug, and scale Apify Actors for web scraping: scaffold Crawlee crawlers with input schemas and routers, manage datasets/queues/APIs programmatically, set up local dev/CI-CD pipelines with GitHub Actions, diagnose errors/timeouts/proxies, tune performance/costs, secure tokens, and integrate runs into Node.js apps.

Build production web scraping pipelines with Bright Data: authenticate proxies/APIs, scrape JS/SPA sites via Scraping Browser/Playwright/Puppeteer/SERP, debug errors/rate limits, tune costs/performance/caching, deploy to Vercel/GCP/Fly.io, set up CI/CD/tests/webhooks, and monitor usage in Node.js/Python projects.

Build, debug, test, deploy, and optimize browser-based Node.js apps and IDEs using StackBlitz SDK and WebContainers: boot in-browser environments, embed interactive playgrounds in docs, fix common errors, run Playwright CI tests, deploy to Vercel/Netlify with production headers, and tune performance/security.

Execute 16 specialized slash commands to scaffold SvelteKit projects with TypeScript/Tailwind/auth/DB, generate components/tests/Storybook stories, debug errors/migrate versions, optimize performance, audit accessibility, fix tests, and troubleshoot Storybook setups.

Automate browsers and Electron desktop apps like VS Code, Slack, Discord via CLI for AI agents: chain commands to navigate pages, snapshot elements, fill forms, click buttons, take screenshots, scrape data, import auth state, and test web apps end-to-end.

Enhance Claude Code with 14 productivity commands and 11 specialized AI agents for modern web development, including RAG-powered knowledge retrieval, Supabase database queries and schema management, and Playwright-based browser automation and web testing.

Capture baseline screenshots of pages or components across mobile, tablet, and desktop viewports using Playwright, then compare current screenshots against baselines to detect visual regressions via pixel diff with thresholds, generating diff images, pass/fail summaries, and reports.

Record user interactions in web apps to generate cleaned E2E test files for Playwright or Cypress, including assertions, hooks, and verification runs. Execute E2E tests via Playwright, Cypress, or Selenium with framework auto-detection, server startup, test filtering, pass/fail summaries, failure details, and automated fix suggestions.

Scrape any webpage, search Google, and extract structured data from 40+ platforms (Amazon, LinkedIn, Instagram, TikTok, YouTube) via Bright Data's CLI, MCP server, or SDKs, with built-in bot detection bypass, proxy integration, and real-time competitive intelligence.

Capture terminal sessions as VHS animated GIFs and browser interactions as Playwright videos, convert to optimized GIFs via FFmpeg, then compose into stacked, gridded, or picture-in-picture tutorial demos from manifests.

Generate, scaffold, and monetize browser games (Phaser 2D or Three.js 3D) from a single command. Covers prototyping, pixel art/3D model generation, audio, UI polish, multiplayer via PartyKit, automated Playwright QA, and deployment to here.now/GitHub Pages/Vercel/itch.io with optional Play.fun monetization hooks.

Record and replay browser QA sessions with Playwright traces, video, and HAR logs, then triage results in a local viewer. Automate one-off browser tasks like navigation, clicking, filling forms, and scraping. Generate prioritized browser-QA plans from git diffs and optionally record them as verifiable sessions.

Run a local Python MCP server powered by Playwright to deploy AI browser agents that automate web navigation, interactions, data extraction, research, and complex workflows. Enables skill learning, background execution, and multi-source data synthesis without API keys.

Assembles a virtual design team inside the terminal — UI, UX, brand, motion, social, email, data viz, print, and AI media — to produce production-quality designs across web, mobile, social, email, presentations, and print. Orchestrates multi-step design pipelines, audits accessibility and visual quality, generates code and Figma assets, and persists project memory for cross-session consistency.

Enables autonomous agent-driven development loops: scaffolds isolated cloud dev boxes per agent, generates one-command local dev stacks with dependency discovery, adds Playwright-based e2e suites with video evidence, creates file-based knowledge base workstreams, and verifies features via independent sub-agents that open PRs with proof.

Automate end-to-end QA workflows across UI, API, and accessibility testing using Playwright, Selenium, and REST Assured—plan tests, generate ISTQB-aligned artifacts, debug failures, and heal flaky tests through coordinated agent delegation.

Run autonomous full-stack dev workflows in Claude Code: generate PRDs/specs via interviews, execute Ralph/autodev loops for overnight PRD implementation with git branching/testing/committing, parallelize tasks across 12 agents (architect, frontend-dev, code-reviewer), build React/Tailwind/shadcn UIs and FastAPI backends, TDD/E2E test/verify/review code, automate git commits/PRs, and audit harness health.

Publish Markdown files or URLs directly to X (Twitter) Articles with rich text formatting, block-index positioning, automatic cover image uploads, table and diagram PNG conversions, and divider insertions using browser automation.

Decompose features into dependency-ordered specs and autonomously execute them task-by-task across research, requirements, design, and implementation phases, with automated verification, git integration, and epic triage.

Orchestrate a multi-agent AI swarm that autonomously manages the full software development lifecycle — from brainstorming and design review through TDD implementation, PR management, code review, security audit, and release — using Claude Code, Gemini CLI, and Codex CLI with quality gates and knowledge base curation.

Orchestrate Claude Code into autonomous multi-session campaigns with fleet coordination, intent routing, and persistent state across context windows, plus skills for code review, testing, documentation, design manifest enforcement, and research.

Orchestrate a fleet of 11 AI-powered QE agents to automate comprehensive quality engineering: generate unit/integration/E2E tests for Jest/Vitest/Playwright/Pytest, perform sublinear coverage analysis and gap prioritization, run chaos/resilience experiments on Docker/K8s, guide TDD workflows, benchmark performance, enforce git/CI quality gates, detect flakiness/security issues, and produce reports.

Extract Xiaohongshu (RedNote) posts with text, images, and Whisper-transcribed videos into formatted Markdown notes saved to your Obsidian vault. Batch-process multiple links in Peter Thiel style, analyze collections for AI summaries and key extractions, and generate styled cover images from prompts.

Orchestrate 36 specialized AI agents and 281 skills to automate full-stack development workflows: plan/implement features with parallel subagents, generate/run tests, review PRs, enforce code quality/security via hooks, coordinate git worktrees, and produce demos/docs in React/Python/FastAPI stacks.

Generate and automate Playwright test scripts for E2E browser testing in TypeScript, JavaScript, or Python projects. Auto-detects dev servers to interact with pages, fill forms, capture screenshots, validate responsive design, UX flows, login processes, links, and cross-browser compatibility.

Control real web browsers via Claude to automate workflows: navigate pages, fill forms and logins, scrape structured data from JS sites, audit accessibility per WCAG, run end-to-end tests simulating user flows, analyze frameworks like React/Next.js, and download authenticated files.

Orchestrate full SDLC lifecycle phases from Inception through Transition using 58 AI agents and 170+ components to automate requirements, architecture evolution, testing orchestration, security gates, deployments, incident response, and project reporting via workflows, phase transitions, and quality checks.

Extract content from web pages, PDFs, and social media, then automatically organize it into structured notes in Obsidian or Notion using multi-agent pipelines with GraphRAG and real-time dashboards.

Enforce WCAG AA accessibility compliance across web, mobile, and document codebases using 80 specialist agents, 25 commands, and Playwright-based behavioral scanning. Delegates to accessibility-lead for UI code review, runs full audits with prioritized reports, and applies automated fixes to HTML, CSS, JSX, Markdown, Office, and PDF files.

Enforces rigorous verification and quality gates on AI-generated code by intercepting success claims, mandating live tests with screenshots and error logs, and orchestrating task tracking through a MASTER_PLAN.md-driven Kanban dashboard with session monitoring hooks.

Run self-serve browser-based QA to verify frontend PR changes match ticket acceptance criteria before pushing code. Auto-setup detects dev server ports and routes for supported frameworks, indexes Playwright/Cypress tests, handles auth, and executes automated UI/functionality checks.

Autonomously creates software projects from idea to deployed code via a 7-step agent pipeline: onboarding, brainstorm, research, architecture, iterative build, validation, and report. Orchestrates multiple AI models, detects existing codebases, builds UI, runs tests with Playwright, and generates structured reports.

Generate print-ready HTML documents for PDF reports, proposals, flyers, newsletters, fact sheets, annual reports, and presentations using organization branding configs and print CSS patterns. Launch interactive playground with local server and Playwright browser for live editing, layout verification via screenshots, and direct PDF export.

Guides developers through a structured agentic coding workflow with session memory, enforcing TDD, capturing project knowledge, performing code reviews and architecture analysis, and automating PR creation and cleanup tasks.

Accelerate Symfony development with TDD workflows using Pest/PHPUnit, scaffold API Platform resources/DTOs/security, evolve Doctrine entities/migrations/relations, implement Messenger queues/schedulers, add voters/forms validation, run quality checks (PHPStan/CS-Fixer), and apply architecture patterns (CQRS/ports-adapters) via skills, agents, commands, and checkpointed planning/execution for safe, production-grade changes.

Automates the end-to-end development workflow: specify requirements via structured interview, generate a plan with contract-first design, execute with parallel research agents and hook-based guards, and manage PR states from draft to review. Includes autonomous bug diagnosis, multi-source technical research, knowledge extraction from PRs, and verification with static checks, CLI tests, and browser QA.

Adds 100+ battle-tested skills, commands, agents, and hooks that enforce test-driven development, auto-fix build/type errors, review git diffs for security and quality, plan complex features, remove dead code, generate documentation and codemaps, and evolve session patterns into reusable skills for Claude Code.

Build and deploy Databricks apps, dashboards, and visualizations; create declarative automation bundles (DABs) for jobs, pipelines, and alerts; develop Lakeflow jobs and Spark pipelines; manage Lakebase Postgres databases with autoscaling and branching; deploy model serving endpoints; migrate workloads to serverless compute; and operate CLI—all via specialized skills.

Delegate complex software engineering tasks—API design, code quality reviews, database schema optimization, DevOps pipelines, security audits, performance tuning, testing strategies, and UI/UX design—to specialized AI subagents, while explaining codebases and auto-updating project docs.

Build and maintain Playwright + pytest test suites using a Page Object Model governance framework: generate PageObjects and tests from live DOM, replace fragile selectors with stable ones, and diagnose failures by jumping directly to the failing page without login. The agent enforces POM patterns, configures browsers, and analyzes test results with automated fix workflows.

Scrape web pages and extract structured JSON data from e-commerce and search targets using Oxylabs proxy rotation, headless browsers, and anti-bot bypass, including YouTube video metadata extraction with file downloads

Automate real browser interactions from the terminal using a Playwright CLI wrapper to navigate websites, fill forms, capture screenshots and snapshots, extract data, trace actions, and debug UI flows.

Iteratively develop HTML/JS web games through a reliable loop: implement small code changes, run Playwright tests with simulated input bursts and pauses, inspect screenshots and rendered text, and review console errors for rapid feedback and refinement.

Generate complete, tested Python CLIs for closed-source web apps by capturing HTTP traffic with Playwright, reverse-engineering APIs, implementing Click commands with CRUD wrappers, running pytest suites, and validating against standards via a single pipeline command.

Automate software development workflows on GitHub using AI agents: from issue triage and feature implementation to code review, deployment validation, and incident response, all within an orchestrated pipeline that treats GitHub issues as structured knowledge graphs.

Analyze test suites in TypeScript, JavaScript, Python, Playwright, and Bun to detect smells like overmocking, flaky tests, fragile tests, poor assertions, and coverage issues. Assess test correctness, reliability, maintainability, and overall quality during reviews or refactoring workflows.

Build, update, and deploy generative pages for Power Apps model-driven apps using React, TypeScript, Fluent UI V9, and PAC CLI. Automate browser tasks locally with Playwright subprocess for end-to-end testing, screenshots, PDF generation, scraping, and interactive navigation.

Automate structured software development workflows within Claude Code: plan, implement, test, review, and deploy features while enforcing project coding standards and documentation

Orchestrate structured development workflows with adaptive planning, implementation, TDD testing, code review, and deployment readiness verification through specialized subagents

Orchestrate full development workflows in Claude Code using /sc slash commands and 23 specialized AI agents to implement features, analyze code quality/security/performance, generate docs/architecture/tests, automate git/build/deploy, conduct research, and manage projects with MCP server persistence for cross-session context.

Equip Claude Code with 53 GTM skills to generate investor pitch decks, craft personalized sales outreach, audit SEO and LinkedIn profiles, build landing pages and analytics dashboards, strategize pricing and growth loops, and automate CRM integrations for rapid SaaS launches and scaling.

Enforce a complete development lifecycle workflow from requirements to release: structured specifications, BDD/TDD/ATDD test generation, Conventional Commits, code review checklists, CI/CD pipelines, SLOs, changelogs, and security audits — all driven by AI-agent skills and automated quality gates.

A scaffolded game development workflow for Claude Code that enforces production-quality conventions across art, audio, design, code, and release pipelines for Unity, Unreal, Godot, and web projects. Provides layered rules, specialized agents, and reusable skills to keep asset pipelines consistent, performance budgets tracked, and builds release-ready without per-asset fixes.

Orchestrate plan-first AI development with parallel autonomous agents in isolated git worktrees. Plan multi-step tasks, enforce TDD for implementations, dispatch foragers for bugs and features, execute in batched sessions with checkpoints, verify builds/tests/lints, and run systematic code reviews before merging.

Automate end-to-end Testany testing workflows: decompose scenarios into cases with Python/Java/Playwright/Gradle/Maven scripts and ZIP packages, register and manage cases/pipelines, configure Jenkins/GitHub Actions triggers and schedules, monitor executions, debug failures via log analysis, and organize workspaces/teams with permissions.

Run autonomous, role-based development workflows (PM→Lead→Designer→Dev→QA) that clarify requirements, design systems, implement code with tests, review security/quality, manage git commits/PRs, build/deploy, and extract learnings into persistent knowledge—across frontend/backend/mobile/ML projects with safety hooks blocking risks.

Bootstrap AI-orchestrated ClosedLoop coding loops to draft PRDs, generate and refine detailed implementation plans from requirements, implement tasks across multi-repo codebases, review PR diffs for bugs and security issues, validate builds and tests, perform visual QA, and capture learnings with caching for efficiency.

Build, deploy, and manage Power Pages code sites with modern SPAs (React, Angular, Vue, Astro) and Dataverse backend. Scaffolds sites, configures Entra ID auth, sets up tables/permissions, deploys via PAC CLI, and tests with Playwright — all from an AI-driven workflow.

Create, review, and polish Chinese and English documents — from research reports and books to proposals, slides, and posters — with AI-powered writing, translation review, contract annotation, and automated formatting for PDF, DOCX, and HTML output.

Audit web UIs from URLs, screenshots, or images for usability heuristics, WCAG accessibility compliance, visual consistency, component reusability, and design system maturity. Generate prioritized reports with remediation roadmaps using AI vision CLI commands and Playwright-powered agents without writing code.

Orchestrate end-to-end development workflows with automatic context management, safety gates, and multi-agent coordination — plan, code, test, deploy, monitor across sessions with quality and security enforcement.

Generates Vaadin UI views, jOOQ data access queries, Karibu server-side tests, and Playwright E2E tests for Java web apps, plus Flyway database migrations from entity models.

Automate CLI processing of YouTube videos and channels (transcribe, upload, schedule, annotate into Markdown blogs), Zoom meeting transcripts, Twitter/X data (fetch likes/posts/follows, screenshot), ConvertKit newsletters, and media analysis/image generation with Google Gemini.

Automates Git and GitHub PR workflows, debugs CI failures and production issues via Datadog and GitHub Actions, and enforces code quality through adversarial review, flaky test detection, and session analysis. Speeds up development with tools for package linking, test data seeding, and iterative PR fix-up.

Orchestrate a structured, gate-based product development workflow from idea to release, with formal spec, design, task, TDD implementation, multi-phase review, regression, and closeout stages enforced by automated routing and evidence verification.

Manage the full product lifecycle from concept to launch: brainstorm and design specs, implement features with TDD, audit SEO and security, run pentests and Lighthouse, deploy with canary monitoring, and track post-ship growth metrics. Includes currency guard for live documentation.

Write maintainable end-to-end tests with Playwright using fixtures for test state management, Page Object Model for scalable page abstractions, and configurable multi-browser project setups. Includes a hook that logs tool usage to track test session activity.

Drive a DDD-based full-stack workflow for Rust + React projects: scaffold projects, write PRDs and design docs, generate task plans, implement backend and frontend code, run tests, and finalize releases with automated CI, acceptance checks, and documentation sync.

Implement full cookie consent compliance workflows: design TCF v2/CNIL banners, integrate GPC/Google Consent Mode, audit trackers/lifetimes, automate Playwright/Selenium testing in CI/CD, deploy server-side tracking on GCP/AWS, and adopt cookieless Privacy Sandbox alternatives for global regs like ePrivacy/CCPA.

Automate E2E browser testing via CLI: explore pages and navigation goals, record interactions into YAML tests, initialize and run tests with AI self-healing and real-time monitoring, verify features or GitHub PR frontend changes with sequential sessions, screenshots, and Markdown reports.