139 skills · sorted by relevance
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers hosted cloud browsers for AI agents: the browser-use Python library (Browser(use_cloud=True)), Playwright, Puppeteer or any CDP client.
The English summary is being prepared. Showing the original description.
Browser Use — direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers hosted cloud browsers for AI agents: the browser-use Python library (Browser(use_cloud=True)), Playwright, Puppeteer or any CDP client.
The English summary is being prepared. Showing the original description.
Target a specific Google Chrome user profile for browser automation via CDP. Discovers installed profiles from the Chrome Local State file, launches Chrome with the requested profile attached to a debug port, and connects agent-browser via `agent-browser connect <port>`. Use when "automate using my Work/Personal Chrome", "open site with my saved session", or "use Chrome profile named <name>". NOT for headless scraping without an existing user profile (use mk:agent-browser directly); NOT for importing cookies only (use agent-browser --auto-connect state save).
The English summary is being prepared. Showing the original description.
Expert patterns for Segment Customer Data Platform including Analytics.js, server-side tracking, tracking plans with Protocols, identity resolution, destinations configuration, and data governance best practices. Use when: segment, analytics.js, customer data platform, cdp, tracking plan.
The English summary is being prepared. Showing the original description.
Record a website's network traffic in a HAR file, a log of requests and responses, then derive an HTTP client from its JSON requests. Reuse captured request details to run searches or fetch data without repeated browser interaction.
Debug Node.js from the terminal by pausing execution, inspecting variables, and tracing function calls. Use interactive commands or scripts to investigate failing tests, collect runtime state, and capture CPU profiles or memory snapshots.
Helps you integrate hosted browser automation through Browser Use Cloud APIs and Python or TypeScript SDKs. Reference guides cover authentication, sessions, saved browser profiles, live views, and connections to existing agents or workflow services.
Capture an entire web page as a full-page screenshot using Chrome DevTools Protocol, Chrome's developer control interface. The workflow needs no additional dependencies and provides page images for portfolios, case studies, and audit reports.
Inspect and test web pages through a browser automation command-line tool. Navigate, click, enter text, capture screenshots, and extract page details, with a focus on checking local OpenDesign previews and reviewing web app quality.
Check web pages and components for accessibility issues against WCAG 2.2, web accessibility guidelines. Receive a report prioritized by user impact, or request targeted code fixes followed by verification of resolved and newly introduced issues.
Trace how a web page generates request signatures and encrypted parameters by inspecting network requests and JavaScript execution. Collect runtime evidence, then use it to reproduce the behavior locally in Node.js.
Analyze authorized browser extensions for Chrome, Edge, and Firefox. Inspect permissions, background scripts, storage, and network activity to reconstruct key data flows and explain credential handling, signing, encryption, or proxy behavior.
Analyze custom virtual machines written in JavaScript by extracting instruction tables, examining constants, and capturing runtime state. Use the findings to reconstruct how obfuscated code executes, including custom runtimes used in risk-control engines.
Capture an entire web page as a PNG, including content below the visible screen. Handle internal scrolling areas and images that load during scrolling, with tiled capture for very tall pages and support for already-open tabs.
Save web content as readable Markdown, a plain-text format for structured notes. Supports X posts, YouTube transcripts, Hacker News discussions, and general pages, with optional local downloads of images and videos.
Prepare text, image, and video posts for X, or turn Markdown drafts into long-form X Articles. The skill uses a real Chrome browser to compose content and supports review before publishing.
Prepare Weibo posts with text, images, or videos, and turn Markdown files into long articles with titles, summaries, and cover images. Scripts fill the browser editor so the user can review and publish manually.
Prepare article drafts for WeChat Official Account from Markdown, HTML, or plain text through its API or Chrome. Also create short image-and-text posts with up to nine images, and format article links as end references.
Reproduce model connection failures and interrupted responses in the desktop app using a local fault server and test providers. Check error messages and retry behavior for refused connections, DNS failures, HTTP errors, stalled requests, and cut streams.
Extract web page content as Markdown from a single URL or a site crawl. When access is blocked, progressively switch from basic fetching to Chrome and Bright Data proxy services, which route requests through other IP addresses.
Operate Chrome or Brave using signed-in browser sessions to verify deployed pages, reproduce bugs, inspect page structure, and examine errors or network traffic. An optional macOS bridge extends control to native applications and operating system input.
Troubleshoot browser automation when clicks, typing, scrolling, or page snapshots fail on complex websites. Inspect page structure and errors, apply waits or alternative interaction methods, and verify the fix on both problematic and simple pages.
Research websites, extract page content, and interact with sites using search tools or an existing browser session. Handles login-dependent and dynamically loaded pages, with browser controls for navigation, forms, screenshots, and media inspection.
Upload Kleros evidence, policies, or metadata to IPFS through a paid gateway. Receive a CID, a content-based file identifier, and a viewing URL. Each request uploads one file and costs $0.01 USDC on Base mainnet.