agent-browser

Browser automation using Vercel's agent-browser CLI. This skill should be used when the user says "browse a website", "fill a form", "take a screenshot", or "test a web page". Uses ref-based element selection.

Jump to install

Repository: tmchow/tmc-marketplace
Last source activity: February 8, 2026 at 23:12
Detected SKILL.md language: English
Stars: 22
Forks: 2

Install options

The review-first prompt is selected by default. You can switch to a direct command or download a local copy.

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

A direct command skips the review prompt. Inspect the source before running it.

npx skills add https://github.com/tmchow/tmc-marketplace --skill agent-browser

The command stays on one line. Scroll horizontally to inspect it before copying.

Prefer a local copy? Download the files currently available to SkillsMP.

Review the source files

Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.

SKILL.md

Source instructions · Read-only preview

Back to search Back to installation

iterativedesign-exploration

Explore radically different design approaches for any page, component, or feature. Use when the user wants to compare multiple distinct visual directions side by side — not build one specific thing, but see several fundamentally different takes on the same UI. Signals: "explore designs for", "show me different ways to design", "radically different approaches", "what could this look like", "design exploration", "let's see some options before we commit", "different layout approaches", "different visual identities for the same content", wanting to see multiple families or variations before choosing a direction. Also triggers when the user pastes design exploration feedback (starts with "## Design Exploration Feedback") to iterate on a previous round, or pastes a design direction ("## Design Direction") to finalize. Do NOT trigger for building one specific design, visual refreshes, design critiques, brainstorming without visual output, single widget prototypes, or comparing CSS frameworks.

2026-03-07

plan-review

Review PRDs, brainstorm docs, tech plans, design docs, specs, or any planning document for issues. This skill should be used whenever the user wants feedback, critique, or a quality check on an existing planning or requirements document — even if they don't use the word "review." Common triggers include: "review the plan", "check the PRD", "critique my tech plan", "what's wrong with this plan", "poke holes in the requirements", "is this plan solid", "take a look at this spec", "give feedback on the brainstorm", or pointing to a doc file and asking if anything is off. Also triggers after writing a PRD or tech plan (to review what was just created), or when invoked by brainstorming or tech-planning skills. Do NOT trigger for code review (PRs, diffs, source files), writing/creating new plans, debugging, or reviewing non-planning documents (READMEs, CLAUDE.md, test coverage).

2026-03-05

code-review

This skill should be used when the user says "review my code", "check these changes", or wants feedback on code before creating a PR. Also used after completing a task during iterative implementation.

2026-03-04

View all from this repository

name	agent-browser
description	Browser automation using Vercel's agent-browser CLI. This skill should be used when the user says "browse a website", "fill a form", "take a screenshot", or "test a web page". Uses ref-based element selection.
user-invocable	true

agent-browser: CLI Browser Automation

Vercel's headless browser CLI designed for AI agents. Uses ref-based selection (@e1, @e2) from accessibility snapshots.

Setup Check

command -v agent-browser >/dev/null 2>&1 && echo "Installed" || echo "NOT INSTALLED"

Install if needed

npm install -g agent-browser
agent-browser install  # Downloads Chromium

Core Workflow

The snapshot + ref pattern is optimal for LLMs:

Navigate to URL
Snapshot to get interactive elements with refs
Interact using refs (@e1, @e2, etc.)
Re-snapshot after navigation or DOM changes

# Step 1: Open URL
agent-browser open https://example.com

# Step 2: Get interactive elements with refs
agent-browser snapshot -i

# Step 3: Interact using refs
agent-browser click @e1
agent-browser fill @e2 "search query"


agent-browser snapshot -i

Feature	agent-browser (CLI)	Playwright MCP
Interface	Bash commands	MCP tools
Selection	Refs (@e1)	Refs (e1)
Output	Text/JSON	Tool responses
Parallel	Sessions	Tabs
Best for	Quick automation	Tool integration

agent-browser

Install options

Review the source files

agent-browser: CLI Browser Automation

Setup Check

Install if needed

Core Workflow

agent-browser: CLI Browser Automation

Setup Check

Install if needed

Core Workflow

Key Commands

Navigation

Snapshots (Essential for AI)

Interactions

Get Information

Screenshots & PDFs

Wait

Semantic Locators (Alternative to Refs)

Sessions & Profiles

Sessions (Parallel Isolated Browsers)

Profiles (Persistent State Across Restarts)

Authentication

Skip UI Login with Headers

Save/Load Auth State

Debug Mode

Examples

Login Flow

Search and Extract

Form Filling

JSON Output

vs Playwright MCP

agent-browser

Source facts

Install options

Review the source files

More from this repository

More from this repository

agent-browser: CLI Browser Automation

Setup Check

Install if needed

Core Workflow

agent-browser: CLI Browser Automation

Setup Check

Install if needed

Core Workflow

Key Commands

Navigation

Snapshots (Essential for AI)

Interactions

Get Information

Screenshots & PDFs

Wait

Semantic Locators (Alternative to Refs)

Sessions & Profiles

Sessions (Parallel Isolated Browsers)

Profiles (Persistent State Across Restarts)

Authentication

Skip UI Login with Headers

Save/Load Auth State

Debug Mode

Examples

Login Flow

Search and Extract

Form Filling

JSON Output

vs Playwright MCP