Automate browser tasks like login flows, form submissions, and data extraction.
npx skills add https://github.com/nawwwal/dex --skill agent-browser-nawwwal
Please help me install this Agent Skill. Skill: agent-browser Source: https://github.com/nawwwal/dex/tree/main/plugins/tools/skills/agent-browser Command: npx skills add https://github.com/nawwwal/dex --skill agent-browser-nawwwal
Automate browser-based tasks to streamline repetitive web interactions such as login flows, form submissions, and data extraction, reducing manual effort and human error.
Open a URL with agent-browser, snapshot interactive elements to obtain refs, and interact using those refs to automate tasks.
High-intent search queries and answers about installing and using this skill.
Automate web form submission and login flows by opening a URL, snapshotting interactive elements to obtain stable refs, and interacting using those refs. This snapshot-based approach ensures deterministic browser automation across multiple web apps.
The best way to extract web data reliably is to use snapshot-based refs to capture interactive elements, then extract text, attributes, HTML, and page metadata. This deterministic automation creates stable data pipelines for verification and information gathering.
Yes, headless browser automation supports end-to-end workflows across multiple web apps. It includes configurable security defaults, session persistence, and provider flexibility, enabling repeatable automated interactions without manual intervention.
Snapshot refs work by capturing interactive elements on a web page and assigning them stable references. You use these refs in subsequent automation steps to click, fill, and type, ensuring deterministic element interaction that remains reliable across workflow reuse.
Yes, this browser automation tool supports OAuth, headless sign-in, and manual sign-in patterns. It includes session and state management with multiple providers, allowing you to maintain authenticated sessions across automated workflow runs.
Snapshot-based browser automation requires re-snapshotting if page elements change dynamically, which can interrupt workflows. It relies on stable interactive elements for deterministic refs, so highly dynamic or heavily obfuscated pages may reduce interaction reliability.
haxlysRun agent-browser sessions on AWS Bedrock with AWS credential resolution.
mkurmanParse FCS files to extract event data and metadata into NumPy arrays or DataFrames.
CygnusfearAutomate end-to-end agent development workflows with phase-driven coordination and issue extraction.
heyJordanParkerAutomate browser navigation, form filling, and data extraction via CLI commands.
