How do I install the Browse skill?

Run npx skillmds@latest add topshark-jim/browse in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Browse safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Browse?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Browse free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Browse?

topshark-jim (@topshark-jim) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Browse by topshark-jim — Agent Skill

Name: Browse
Author: topshark-jim

Browse

Browser automation workflow built on the `agent-browser` CLI. Use when you need to open pages, inspect content, click through flows, fill forms, capture screenshots, inspect console or network activity, or compare pages.

topshark-jim 1657e6d 2.3 KB Updated Sep 17, 2026

File contents

browse

Use agent-browser directly for browser automation. Keep commands explicit and prefer the built-in session model instead of adding a second wrapper layer.

Requirements

agent-browser must be available on PATH.
If browser binaries are missing, run agent-browser install.
Reuse the default session unless isolation matters; close it with agent-browser close when the workflow is finished.

Default Flow

agent-browser open https://example.com
agent-browser wait --load networkidle
agent-browser snapshot -i

Use snapshot -i when selectors are unclear, then interact with @ref targets from the snapshot output.

Command Map

# Open or navigate
agent-browser open https://example.com
agent-browser back
agent-browser forward
agent-browser reload

# Inspect content
agent-browser get title
agent-browser get url
agent-browser get text body
agent-browser get html main
agent-browser snapshot -i

# Interact
agent-browser click @e3
agent-browser fill @e4 "test@example.com"
agent-browser type @e5 "hello"
agent-browser press Enter
agent-browser select @e6 option-a
agent-browser upload @e7 /tmp/file.png
agent-browser wait @e8

# Visual checks
agent-browser screenshot /tmp/page.png
agent-browser screenshot --full /tmp/page-full.png
agent-browser pdf /tmp/page.pdf

# Debugging
agent-browser console
agent-browser errors
agent-browser network requests
agent-browser eval "document.title"

# State and tabs
agent-browser cookies get
agent-browser storage local get
agent-browser tab new
agent-browser tab list
agent-browser tab 2
agent-browser close

Working Rules

Prefer wait --load networkidle after navigation-heavy steps.
Prefer snapshot -i before click, fill, or select when the page is not stable enough for CSS selectors.
Use console, errors, and network requests before concluding that a page is broken.
Use --profile <path> when a persistent login or browser profile matters.
Use --session <name> when separate browser contexts are required in the same task.
If agent-browser is missing, tell the user exactly how to install it before continuing.

---name: browsedescription: Browser automation workflow built on the `agent-browser` CLI. Use when you need to open pages, inspect content, click through flows, fill forms, capture screenshots, inspect console or network activity, or compare pages.---# browseUse `agent-browser` directly for browser automation. Keep commands explicit and prefer the built-in session model instead of adding a second wrapper layer.## Requirements- `agent-browser` must be available on `PATH`.- If browser binaries are missing, run `agent-browser install`.- Reuse the default session unless isolation matters; close it with `agent-browser close` when the workflow is finished.## Default Flow```bashagent-browser open https://example.comagent-browser wait --load networkidleagent-browser snapshot -i```Use `snapshot -i` when selectors are unclear, then interact with `@ref` targets from the snapshot output.## Command Map```bash# Open or navigateagent-browser open https://example.comagent-browser backagent-browser forwardagent-browser reload# Inspect contentagent-browser get titleagent-browser get urlagent-browser get text bodyagent-browser get html mainagent-browser snapshot -i# Interactagent-browser click @e3agent-browser fill @e4 "test@example.com"agent-browser type @e5 "hello"agent-browser press Enteragent-browser select @e6 option-aagent-browser upload @e7 /tmp/file.pngagent-browser wait @e8# Visual checksagent-browser screenshot /tmp/page.pngagent-browser screenshot --full /tmp/page-full.pngagent-browser pdf /tmp/page.pdf# Debuggingagent-browser consoleagent-browser errorsagent-browser network requestsagent-browser eval "document.title"# State and tabsagent-browser cookies getagent-browser storage local getagent-browser tab newagent-browser tab listagent-browser tab 2agent-browser close```## Working Rules- Prefer `wait --load networkidle` after navigation-heavy steps.- Prefer `snapshot -i` before `click`, `fill`, or `select` when the page is not stable enough for CSS selectors.- Use `console`, `errors`, and `network requests` before concluding that a page is broken.- Use `--profile <path>` when a persistent login or browser profile matters.- Use `--session <name>` when separate browser contexts are required in the same task.- If `agent-browser` is missing, tell the user exactly how to install it before continuing.

Frequently asked questions