Ejecuta cualquier Skill en Manus
con un clic

Ejecuta cualquier Skill en Manus con un clic

browser-use

Estrellas5

Forks0

Actualizado7 de febrero de 2026 a las 00:25

Fast, persistent browser automation via `browser-use` CLI (sessions persist across commands). Use for multi-step web workflows (open -> state -> click/input -> verify -> repeat). Supports chromium/headed, real Chrome (logged-in), and remote browser.

Instalación

Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.

Ejecutar en Manus

Fuente

marchatton

marchatton/agent-skills

Abrir repositorio de GitHub Ver repositorios del creador

Descarga

Ejecutar en Manus

Ocupaciones relacionadasSOC

Basado en la clasificación ocupacional SOC

Desarrolladores de softwareOcupaciones informáticas y matemáticas·SOC 15-1252

SKILL.md

readonly

name	browser-use
description	Fast, persistent browser automation via `browser-use` CLI (sessions persist across commands). Use for multi-step web workflows (open -> state -> click/input -> verify -> repeat). Supports chromium/headed, real Chrome (logged-in), and remote browser.

browser-use

Purpose

Persistent browser session across commands.
Element index workflow: state -> act by index.

When

Need quick multi-step browser automation without writing Playwright.
Need reuse logged-in Chrome session (real browser mode).
Need parallel sessions (--session).

Install

# one-off
uvx "browser-use[cli]" open https://example.com

# permanent
uv pip install "browser-use[cli]"
browser-use install  # downloads Chromium/deps

Core Loop

browser-use open https://example.com
browser-use state                 # list elements w/ indices
browser-use click 5
browser-use input 3 "hello"
browser-use screenshot
browser-use state                 # verify + get next indices
browser-use close

Modes

browser-use --browser chromium open <url>              # default (headless)
browser-use --browser chromium --headed open <url>     # visible window
browser-use --browser real open <url>                  # your Chrome (cookies/login)
browser-use --browser remote open <url>                # cloud browser (API key)

Common Commands

browser-use open <url>
browser-use state [--json]
browser-use click <idx> | dblclick <idx> | rightclick <idx> | hover <idx>
browser-use input <idx> "text" | type "text"
browser-use scroll up|down [n]
browser-use screenshot
browser-use get <what>                                # read page/element info
browser-use back | switch | close-tab
browser-use cookies export <path> | cookies import <path>
browser-use profile list|create|update|delete
browser-use sessions
browser-use server status|logs|stop
browser-use close [--all]

Sessions

browser-use --session work open https://work.example.com
browser-use --session personal open https://personal.example.com
browser-use --session work state
browser-use close --all

Rules (agent-friendly)

Always run browser-use state before acting; indices change after navigation.
After each navigation/submit: re-run state (don’t reuse stale indices).
Prefer --headed while debugging.
Cleanup: browser-use close (or close --all) when done.

Remote Mode

Env: BROWSER_USE_API_KEY (or --api-key).

Más de este repositorio

mismo repositorio

precoil-emt

marchatton/agent-skills

Use this skill when the user wants to test a business idea, strategy, or initiative against real-world risk. Triggers include: 'test my idea', 'what are the riskiest assumptions', 'help me validate this', 'run EMT on this', 'extract assumptions', 'assumption mapping', 'what could go wrong with this plan', 'pressure test this', 'validate this plan', 'what could go wrong with this strategy', 'identify hidden risk in this idea', or any request to pressure-test a business decision before committing resources. Runs a guided Extract → Map → Test system based on David J. Bland's Precoil methodology.

2026-03-105

validate-evaluator

marchatton/agent-skills

Calibrate an LLM judge against human labels using data splits, TPR/TNR, and bias correction. Use after writing a judge prompt (write-judge-prompt) when you need to verify alignment before trusting its outputs. Do NOT use for code-based evaluators (those are deterministic; test with standard unit tests).

2026-03-105

visual-explainer

marchatton/agent-skills

Generate beautiful, self-contained HTML pages that visually explain systems, code changes, plans, and data. Use when the user asks for a diagram, architecture overview, diff review, plan review, project recap, comparison table, or any visual explanation of technical concepts. Also use proactively when you are about to render a complex ASCII table (4+ rows or 3+ columns) — present it as a styled HTML page instead.

2026-03-025

breadboarding

marchatton/agent-skills

This skill should be used when shaping a software change and needing to breadboard the solution at the right level of abstraction (places, affordances, connections), including mapping an existing system via UI + code affordances, producing a wiring diagram, a parts/BOM plan, a fit check, and (when relevant) an extract-vs-duplicate analysis.

2026-02-115

ask-questions-if-underspecified

marchatton/agent-skills

Clarify requirements before implementing. Do not use automatically, only when invoked explicitly.

2026-02-105

demo-runbook

marchatton/agent-skills

This skill should be used when a user needs a demo package that starts with a live demo (not slides) and produces both a demo script and a navigable single-file HTML runbook, including caveats, respectful competitive comparison, and LLM architecture details (RAG, evals, observability).

2026-02-085

browser-use

Purpose

Persistent browser session across commands.

Element index workflow: state -> act by index.

When

Need quick multi-step browser automation without writing Playwright.

Need reuse logged-in Chrome session (real browser mode).

Need parallel sessions (--session).

Install

# one-off uvx "browser-use[cli]" open https://example.com # permanent uv pip install "browser-use[cli]" browser-use install # downloads Chromium/deps

Core Loop

browser-use open https://example.com browser-use state # list elements w/ indices browser-use click 5 browser-use input 3 "hello" browser-use screenshot browser-use state # verify + get next indices browser-use close

Modes

browser-use --browser chromium open <url> # default (headless) browser-use --browser chromium --headed open <url> # visible window browser-use --browser real open <url> # your Chrome (cookies/login) browser-use --browser remote open <url> # cloud browser (API key)

Common Commands

Sessions

browser-use --session work open https://work.example.com browser-use --session personal open https://personal.example.com browser-use --session work state browser-use close --all

Rules (agent-friendly)

Always run browser-use state before acting; indices change after navigation.

After each navigation/submit: re-run state (don’t reuse stale indices).

Prefer --headed while debugging.

Cleanup: browser-use close (or close --all) when done.

Remote Mode

Env: BROWSER_USE_API_KEY (or --api-key).