A window of browser pages and terminals Claude works in and you watch, with a pane for its tabs and your comments
Plugin llx-desk from marketplace llx-desk in rsaryev/llx-desk. Commands read from the repo's manifest — yesterday.
boardPlan and track work on a kanban board the person watches in the llx-desk window (Backlog, Todo, Doing, Review, Done, Discarded), and hand cards to subagents: for a task of several parts, work the person wants to follow or accept piece by piece, or parallel subagents that must not do the same thing t
windowOpen real browser pages and terminals in a window the person watches, and work in them with `llx-desk window` calls: check a page you build, play a UI flow, size it as a phone, screenshot, drive a REPL or an installer.
/llx-desk:endClose this project's tabs
/llx-desk:stopQuit LLX Desk, its window and its terminals
workerWorks one card of this project's llx-desk board: takes it, does it, hands it in for the person's review. Give it the card's id and its name on the board (\"take c3; your name on the board: cart-button\"), and the address of the app's server when one runs. Start several for cards that touch different
The diff pane as a plugin: /diff opens the session's uncommitted changes beside the transcript, file by file with their hunks, refreshed as Claude edits and runs commands; the first edit opens it where the terminal is wide enough, and a file's ask button rides its hunks on the next prompt.
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Agentic browser automation with Playwright for testing, scraping, and UI interaction
10 skills · 1 command · 1 agent
Skill: add headroom-ai compress() to a Python or TypeScript app to cut LLM input tokens (tool outputs, logs, JSON, chat history). No API key.
1 skill
Automates browser interactions for web testing, form filling, screenshots, and data extraction
12 skills
Web scraping, Google search, structured data extraction, and MCP server integration powered by Bright Data. Includes 7 skills: scrape any webpage as markdown (with bot detection/CAPTCHA bypass), search Google with structured JSON results, extract data from 40+ websites (Amazon, LinkedIn, Instagram, TikTok, YouTube, and more), orchestrate Bright Data's 60+ MCP tools, built-in best practices for Web Unlocker, SERP API, Web Scraper API, and Browser API, Python SDK best practices for the brightda...
21 skills
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.