agent-browser
agent-browser enables programmatic control of web browsers and automated navigation workflows. Execute complex web interactions, form submissions, and page navigation through a unified interface designed for AI agents. Perfect for building autonomous web automation tasks that require intelligent browser control.
agent-browser enables programmatic control of web browsers and automated navigation workflows. It allows you to execute complex web interactions, form submissions, and page navigation through a unified interface designed for AI agents. Perfect for building autonomous web automation tasks that require intelligent browser control, agent-browser supports everything from simple navigation to sophisticated multi-step workflows.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-07-24
agent-browser enables programmatic control of web browsers and automated navigation workflows. It allows you to execute complex web interactions, form submissions, and page navigation through a unified interface designed for AI agents. Perfect for building autonomous web automation tasks that require intelligent browser control, agent-browser supports everything from simple navigation to sophisticated multi-step workflows.
Use it when
- Yes.
- agent-browser supports authentication and maintains browser sessions across multiple operations.
Verify before relying
Read SKILL.md below before installing (11 files). Open directory: indexed for reading, not audited.
Install
andreadellacorte/groove/agent-browser · repository language: Shell
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
What is agent-browser and what can it do?
agent-browser enables programmatic control of web browsers and automated navigation workflows. It allows you to execute complex web interactions, form submissions, and page navigation through a unified interface designed for AI agents. Perfect for building autonomous web automation tasks that require intelligent browser control, agent-browser supports everything from simple navigation to sophisticated multi-step workflows.
Can agent-browser automate clicking buttons and filling forms?
Yes. agent-browser is built to automate clicking buttons and filling forms as a core capability. You can programmatically interact with web page elements, submit forms, and navigate through multi-step workflows without manual intervention. This makes it ideal for automating repetitive web tasks and building intelligent agents that can handle complex form-based interactions.
How does agent-browser handle login to websites automatically?
agent-browser supports authentication and maintains browser sessions across multiple operations. You can automate login workflows by programmatically filling in credentials, submitting authentication forms, and preserving session state across subsequent requests. This capability enables you to build agents that can authenticate once and then perform multiple authenticated actions within the same session.
Can I extract data from web pages using agent-browser?
Absolutely. agent-browser is designed to extract data and content from websites at scale. You can programmatically navigate to pages, locate specific elements, and retrieve their content for processing. This makes agent-browser suitable for web scraping tasks, data collection workflows, and building intelligent agents that need to gather information from multiple web sources.
Does agent-browser support taking screenshots of websites programmatically?
Yes. agent-browser can capture visual evidence and snapshots of web pages for documentation or monitoring purposes. You can take screenshots programmatically at any point in your automation workflow, which is useful for visual verification, creating documentation, monitoring page state changes, or building audit trails of web interactions.
What license does agent-browser use?
agent-browser is released under the MIT license, which is a permissive open-source license. This means you can freely use, modify, and distribute agent-browser in both personal and commercial projects, provided you include the original license notice in your distribution.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
Browser Automation with agent-browser
Core Workflow
Every browser automation follows this pattern:
- Navigate:
agent-browser open <url> - Snapshot:
agent-browser snapshot -i(get element refs like@e1,@e2) - Interact: Use refs to click, fill, select
- Re-snapshot: After navigation or DOM changes, get fresh refs
```bash agent-browser open https://example.com/form agent-browser snapshot -i
Output: @e1 [input type="email"], @e2 [input type="password"], @e3 [button] "Submit"
agent-browser fill @e1 "user@example.com" agent-browser fill @e2
(truncated - see the full file via the links below)
File tree — 11 files
.agents/skills/agent-browser/SKILL.md
.agents/skills/agent-browser/references/authentication.md
.agents/skills/agent-browser/references/commands.md
.agents/skills/agent-browser/references/profiling.md
.agents/skills/agent-browser/references/proxy-support.md
.agents/skills/agent-browser/references/session-management.md
.agents/skills/agent-browser/references/snapshot-refs.md
.agents/skills/agent-browser/references/video-recording.md
.agents/skills/agent-browser/templates/authenticated-session.sh
.agents/skills/agent-browser/templates/capture-workflow.sh
.agents/skills/agent-browser/templates/form-automation.sh
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Automate browser interactions and web navigation tasks programmatically”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
Agent Browser equips your AI agents with full web navigation and interaction abilities. Browse websites, click links, fill forms, and extract live content—all programmatically integrated into your agent's workflow. Perfect for research, data gathering, and dynamic web-based tasks.
agent-browser lets you script repetitive web interactions—form submissions, element clicks, page navigation—directly through Claude Code. Built for end-to-end encrypted access, it brings browser automation to your workflow without leaving SkillFed's environment.
agent-browser is a skill for automating browser-based workflows and web interactions through programmatic control. Built as part of an open-source AI agent framework, it enables you to orchestrate web tasks, integrate with large language models, and connect external tools into executable automation chains. Perfect for developers building intelligent agents that need to interact with web applications and handle complex browser operations at scale.
Agent Browser equips AI systems with autonomous web navigation capabilities, allowing them to visit URLs, extract information, and perform interactions on live websites without manual intervention. This skill transforms agents into independent web explorers capable of handling real-time browsing workflows and data collection tasks.
Agent Browser equips your AI agent with full web browsing capabilities, allowing it to navigate pages, interact with elements, and retrieve information from live websites. Perfect for agents that need to research, gather data, or complete tasks across the open web.
Agent Browser equips AI systems with web navigation capabilities, allowing them to fetch and interact with online content in real time. This skill bridges the gap between isolated language models and the live web, enabling agents to research, gather data, and respond to queries with current information.
More skills Agent Browser (NOASSERTION) · agent-browser (Apache-2.0) · agent-browser (Apache-2.0) · Agent Browser (NOASSERTION)