Browser Automation

ui-demo helps you record polished web app demo videos with Playwright, visible cursor movement, and natural pacing. Use the ui-demo skill for walkthroughs, onboarding clips, feature tours, and tutorial-style recordings. Follow the discover, rehearse, then record workflow for reliable results, especially for prototypes and fast-changing UIs.

nuxt4-patterns is a Nuxt 4 skill for hydration safety, route rules, lazy loading, and SSR-safe data fetching. Use the nuxt4-patterns skill to make better Frontend Development decisions, reduce mismatches, and apply the right pattern for each page or component.

The deep-research skill turns broad questions into sourced web research with firecrawl and exa MCP tools. Use it to compare sources, synthesize findings, and produce cited reports for competitive analysis, technology evaluation, due diligence, and other decisions that need evidence.

Use the benchmark skill to measure performance baselines, detect regressions before and after PRs, and compare stack alternatives across pages, APIs, and builds for Performance Optimization.

The benchmark skill helps detect performance regressions in web and app workflows. Use it to establish a baseline, compare before and after changes, and track whether a PR made pages slower, heavier, or less stable. It is a practical benchmark guide for performance optimization, Core Web Vitals, Lighthouse checks, bundle size, and load time trends.

canary is a post-deploy monitoring skill that watches live apps for console errors, page failures, and performance regressions. It compares current behavior against a pre-deploy baseline so you can verify a release, catch broken pages, and spot visible anomalies with less guesswork than a generic prompt.

The qa skill systematically tests a web app, finds bugs, and verifies fixes with a staged workflow. Use it for regression testing, ship-readiness checks, or a structured QA guide when you need evidence, severity ratings, and atomic fix-and-retest loops instead of a generic bug-hunt prompt.

Documentation lookup for the browser-use Python library. The open-source skill helps with install, setup, Agent and Browser code, model env vars, tools, MCP integrations, monitoring, and legacy Actor API guidance.

gstack is a browser-driven AI skill for QA testing, dogfooding, release checks, and bug capture. It opens real pages, clicks through UI, verifies state, compares before and after, tests responsive layouts, and captures screenshot-backed evidence. It is especially useful for UI Design review and deployment validation when you need trustworthy browser results from the gstack skill.

diagnose is a structured debugging workflow for hard bugs, flaky tests, and performance regressions. It helps you reproduce the issue, minimise the failing case, form one hypothesis at a time, add instrumentation, fix the root cause, and lock it in with a regression test. Use the diagnose guide when “debug this” is not enough.

critique helps you review interfaces, features, pages, or components from a UX lens with structured scoring, persona-based testing, heuristic checks, and actionable feedback. Use the critique skill when you need a repeatable critique guide for UI/UX Design, not vague commentary. It is best for focused critique usage on a specific area with clear context.

figma-create-new-file creates a new blank Figma Design file or FigJam board in drafts. Use it when you need a fresh starting point before deeper Figma actions, including use_figma. It supports design or figjam, optional file naming, and can resolve plan access with whoami when needed.

baoyu-post-to-wechat is a WeChat Official Account publishing skill with browser and API flows for articles and image-text posts. It supports Markdown, HTML, and plain text input, frontmatter-based title and summary extraction, Markdown-to-WeChat conversion, image handling, and environment checks for Chrome profile automation.

baoyu-post-to-weibo lets agents publish Weibo posts and headline articles through a real Chrome session. It supports text, images, video, Markdown-to-HTML conversion, clipboard paste helpers, and bun or npx-based execution for reliable posting workflows.

Use transformers-js to run ML models in JavaScript and TypeScript across browser and server runtimes. The transformers-js skill covers install, model loading, caching, configuration, and practical transformers-js usage for text, vision, audio, multimodal tasks, and transformers-js for Code Generation with supported text-generation models.

seo-dataforseo connects Claude to live SEO data through the DataForSEO MCP server for SERP checks, keyword research, backlinks, on-page analysis, competitor research, business listings, and AI visibility tracking. It is best for data-backed workflows when you need real search evidence, clear install guidance, and practical seo-dataforseo usage.

seo-audit runs a full website SEO audit with parallel subagent delegation, crawling up to 500 pages and detecting business type. It covers technical, content, schema, performance, visual, local, and geo signals, then returns a health score and prioritized fixes for site-wide review and SEO Content analysis.

analyzing-browser-forensics-with-hindsight helps Digital Forensics teams analyze Chromium browser artifacts with Hindsight, including history, downloads, cookies, autofill, bookmarks, saved credentials metadata, cache, and extensions. Use it to reconstruct web activity, review timelines, and investigate Chrome, Edge, Brave, and Opera profiles.

website-to-hyperframes is a workflow skill for turning an existing website into a HyperFrames video. Use it when you have a URL and want a product tour, promo, social ad, or explainer grounded in the site’s real design, copy, and assets. The repo supports capture, design, script, storyboard, VO, build, and validation for Design Implementation work.

The wp-playground skill helps you create disposable, reproducible WordPress Playground environments for plugin and theme testing, version switching, blueprints, snapshots, and isolated debugging. It supports browser or CLI workflows via @wp-playground/cli and is especially useful for backend development, QA, and controlled issue reproduction.

web-perf analyzes web performance with Chrome DevTools MCP. It measures Core Web Vitals, trace-based load issues, render-blocking resources, layout shifts, caching problems, and accessibility gaps. Use the web-perf skill for Performance Optimization, debugging slow pages, and evidence-based web-perf guide workflows that rely on current docs and live traces.

agents-sdk helps you build Cloudflare Workers agents with stateful conversations, durable execution, WebSocket or streaming chat, MCP integration, scheduled tasks, and browser automation. This agents-sdk skill focuses on install decisions, configuration, and practical usage for existing or new Workers apps, with guidance for multi-agent systems only when they fit Cloudflare runtime constraints.

Use the network skill to create PlantUML network topology diagrams with mxGraph device icons, auto-layout, zone grouping, and clear link semantics. It fits LAN, WAN, enterprise, data center, wireless, security, and vendor-specific diagrams, with examples for network usage and guidance on when to use network versus uml or cloud.

Use the slack-messaging skill to send or read Slack messages, check channels, test Slack integrations, and interact with a Slack workspace from the command line with slackcli for workflow automation.