信頼 32/100中リスクスキル 1件

パッケージ

browser-use/browser-use

🌐 Make websites accessible for AI agents. Automate tasks online with ease.

Trust means

Trust score is a heuristic blend of popularity, freshness, structure quality, and safety penalties. Useful for ranking, not a guarantee.

Risk means

Risk is generated by automated scans of skills, files, and allowed tools. It is not the same thing as a human security review.

Review status

Auto-scanned only. High-risk signals exist, so manual review is strongly recommended before install.

リスク: 中（auto-imported from GitHub; risk not assessed）

スター

84,805

フォーク

9,818

スキル

ファイル

Suitable for

Teams or solo users who want to inspect a workflow package before installing it, instead of trusting a random repo at face value.

Not suitable for

Anyone looking for a zero-review one-click install, or teams that are not willing to read the starter skill and allowed tools first.

Install prerequisites

What to verify before touching install

Read the starter skill and confirm the workflow matches your actual job-to-be-done.
Check allowed tools, scripts, and file count so you know what the package can touch.
Make sure your agent runtime supports the install path you plan to use.
Tooling check: this package references Read, Bash(browser-use:*) as part of its skills.

open-source

Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browser_use, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle hooks, MCP server setup, or monitoring/observability with Laminar or OpenLIT. Also trigger for questions about browser-use installation, prompting strategies, or sensitive data handling. Do NOT use this for Cloud API/SDK usage or pricing — use the cloud skill instead. Do NOT use this for directly automating a browser via CLI commands — use the browser-use skill instead.

パス: skills/open-source

Allowed tools: Read

Risk level: 高

After install

How to verify it actually works

Open the starter skill after install and confirm the expected files are present.

Run the package only in a safe test context first, not directly in a sensitive workspace.

Verify the workflow outcome matches the package description before wider rollout.

Pay extra attention to any skill that can execute scripts, access the network, or ask for elevated actions.

Core skills

What this package actually helps you do

open-source

skills/open-source · 10 files

高

許可ツール: Read

cloud

Documentation reference for using Browser Use Cloud — the hosted API and SDK for browser automation. Use this skill whenever the user needs help with the Cloud REST API (v2 or v3), browser-use-sdk (Python or TypeScript), X-Browser-Use-API-Key authentication, cloud sessions, browser profiles, profile sync, CDP WebSocket connections, stealth browsers, residential proxies, CAPTCHA handling, webhooks, workspaces, skills marketplace, liveUrl streaming, pricing, or integration patterns (chat UI, subagent, adding browser tools to existing agents). Also trigger for questions about n8n/Make/Zapier integration, Playwright/ Puppeteer/Selenium on cloud infrastructure, or 1Password vault integration. Do NOT use this for the open-source Python library (Agent, Browser, Tools config) — use the open-source skill instead.

skills/cloud · 11 files

中

許可ツール: Read

browser-use

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, or extract information from web pages.

skills/browser-use · 1 file

中

許可ツール: Bash(browser-use:*)

remote-browser

Controls a local browser from a sandboxed remote machine. Use when the agent is running in a sandbox (no GUI) and needs to navigate websites, interact with web pages, fill forms, take screenshots, or expose local dev servers via tunnels.

skills/remote-browser · 1 file

中

許可ツール: Bash(browser-use:*)

Package contents

Folders and files

open-source

skills/open-source

10 ファイル

SKILL.md.md
references/actor.md.md
references/agent.md.md
references/browser.md.md
references/examples.md.md
references/integrations.md.md
references/models.md.md
references/monitoring.md.md
references/quickstart.md.md
references/tools.md.md

cloud

skills/cloud

11 ファイル

SKILL.md.md
references/api-v2.md.md
references/api-v3.md.md
references/browser-api.md.md
references/features.md.md
references/guides/chat-ui.md.md
references/guides/subagent.md.md
references/guides/tools-integration.md.md
references/patterns.md.md
references/quickstart.md.md
references/sessions.md.md

browser-use

skills/browser-use

1 ファイル

SKILL.md.md

remote-browser

skills/remote-browser

1 ファイル

SKILL.md.md

Last step

Install only after the checks above

If the package fits your workflow, the starter skill makes sense, and the auto-scan signals are acceptable for your environment, then use the exact install command below.

Install command

npx skills add browser-use/browser-use

Claude Code

Copy to .claude/skills/

GitHub Copilot

Copy to .github/skills/

Codex CLI

Copy to .agents/skills/

Gemini CLI

Copy to .gemini/skills/

Community Signals

What users think

🟡 Moderate

Similar packages worth comparing

関連パッケージはありません。