Skill Detail

Extract data and complete workflows in your real logged-in browser

Use bb-browser when an agent needs to inspect pages, pull data, or complete form-driven tasks inside the user's actual logged-in Chrome session. It is for browser work where normal HTTP fetches fail because the important context lives behind auth, cookies, or internal web apps.

Browser AutomationMulti-Framework
Browser Automation Multi-Framework Published
Tool match: bb-browser ⬇ 2.9k/wk npm MIT license
INSTALL WITH ANY AGENT
npx skills add agentskillexchange/skills --skill extract-data-and-complete-workflows-in-your-real-logged-in-browser Copy
Works best when you want a reusable capability, not another fragile one-off prompt.
At a glance
Tools required
bb-browser, Chrome/Chromium
Install & setup
Install bb-browser from the official repository, then use the documented bb-browser CLI commands such as open, snapshot, click, and fill against a logged-in browser session.
Author
epiral
Publisher
Organization
Last updated
Apr 11, 2026
Quick brief

bb-browser is a browser-control tool and MCP/CLI workflow for agents that need access to the user’s real authenticated browser state. This skill is not a generic β€œbrowser tool” listing. The job here is specific: an agent opens a site in the user’s real browser session, inspects interactive elements, extracts data from pages that require login, and completes bounded browser actions such as search, clicking through internal dashboards, or filling routine forms.

How it works

What this skill actually does

Use this when a normal API call or public scraper is not enough. Typical cases include internal admin panels, SaaS dashboards, pages that depend on existing cookies, and account views that only exist after sign-in. The point of invoking the agent skill is that the agent can reuse the user’s logged-in context instead of asking the user to manually navigate every page.

The scope boundary matters. This entry is not a catalog card for bb-browser as a product, browser, or SDK. It is narrowly about authenticated browser retrieval and action-taking through the user’s existing session. If you just need a public web fetch, a generic browser automation library, or a development framework for building your own browser tool, use those directly instead.

Integration points are clear in the upstream docs: the agent can open URLs, snapshot interactive elements, click, fill, close tabs, and use bb-browser’s site adapters when a workflow already exists for a specific platform. That makes it useful for research, internal operations, support workflows, and other tasks where the browser itself is the only realistic integration surface.