← 返回 Skills 市场
makforce

Browser Use 1.0.0

作者 Makforce · GitHub ↗ · v1.0.0
cross-platform ⚠ suspicious
810
总下载
0
收藏
4
当前安装
1
版本数
在 OpenClaw 中安装
/install browser-use-1-0-0
功能描述
Use Browser Use cloud API to spin up cloud browsers for Clawdbot and run autonomous browser tasks. Primary use is creating browser sessions with profiles (pe...
使用说明 (SKILL.md)

Browser Use

Browser Use provides cloud browsers and autonomous browser automation via API.

Docs:

Setup

API Key is read from clawdbot config at skills.entries.browser-use.apiKey.

If not configured, tell the user:

To use Browser Use, you need an API key. Get one at https://cloud.browser-use.com (new signups get $10 free credit). Then configure it:

clawdbot config set skills.entries.browser-use.apiKey "bu_your_key_here"

Base URL: https://api.browser-use.com/api/v2

All requests need header: X-Browser-Use-API-Key: \x3CapiKey>


1. Browser Sessions (Primary)

Spin up cloud browsers for Clawdbot to control directly. Use profiles to persist logins and cookies.

Create browser session

# With profile (recommended - keeps you logged in)
curl -X POST "https://api.browser-use.com/api/v2/browsers" \
  -H "X-Browser-Use-API-Key: $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"profileId": "\x3Cprofile-uuid>", "timeout": 60}'

# Without profile (fresh browser)
curl -X POST "https://api.browser-use.com/api/v2/browsers" \
  -H "X-Browser-Use-API-Key: $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"timeout": 60}'

Response:

{
  "id": "session-uuid",
  "cdpUrl": "https://\x3Cid>.cdp2.browser-use.com",
  "liveUrl": "https://...",
  "status": "active"
}

Connect Clawdbot to the browser

gateway config.patch '{"browser":{"profiles":{"browseruse":{"cdpUrl":"\x3CcdpUrl-from-response>"}}}}'

Now use the browser tool with profile=browseruse to control it.

List/stop browser sessions

# List active sessions
curl "https://api.browser-use.com/api/v2/browsers" -H "X-Browser-Use-API-Key: $API_KEY"

# Get session status
curl "https://api.browser-use.com/api/v2/browsers/\x3Csession-id>" -H "X-Browser-Use-API-Key: $API_KEY"

# Stop session (unused time is refunded)
curl -X PATCH "https://api.browser-use.com/api/v2/browsers/\x3Csession-id>" \
  -H "X-Browser-Use-API-Key: $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"status": "stopped"}'

Pricing: $0.06/hour (Pay As You Go) or $0.03/hour (Business). Max 4 hours per session. Billed per minute, refunded for unused time.


2. Profiles

Profiles persist cookies and login state across browser sessions. Create one, log into your accounts in the browser, and reuse it.

# List profiles
curl "https://api.browser-use.com/api/v2/profiles" -H "X-Browser-Use-API-Key: $API_KEY"

# Create profile
curl -X POST "https://api.browser-use.com/api/v2/profiles" \
  -H "X-Browser-Use-API-Key: $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"name": "My Profile"}'

# Delete profile
curl -X DELETE "https://api.browser-use.com/api/v2/profiles/\x3Cprofile-id>" \
  -H "X-Browser-Use-API-Key: $API_KEY"

Tip: You can also sync cookies from your local Chrome using the Browser Use Chrome extension.


3. Tasks (Subagent)

Run autonomous browser tasks - like a subagent that handles browser interactions for you. Give it a prompt and it completes the task.

Always use browser-use-llm - optimized for browser tasks, 3-5x faster than other models.

curl -X POST "https://api.browser-use.com/api/v2/tasks" \
  -H "X-Browser-Use-API-Key: $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "task": "Go to amazon.com and find the price of the MacBook Air M3",
    "llm": "browser-use-llm"
  }'

Poll for completion

curl "https://api.browser-use.com/api/v2/tasks/\x3Ctask-id>" -H "X-Browser-Use-API-Key: $API_KEY"

Response:

{
  "status": "finished",
  "output": "The MacBook Air M3 is priced at $1,099",
  "isSuccess": true,
  "cost": "0.02"
}

Status values: pending, running, finished, failed, stopped

Task options

Option Description
task Your prompt (required)
llm Always use browser-use-llm
startUrl Starting page
maxSteps Max actions (default 100)
sessionId Reuse existing session
profileId Use a profile for auth
flashMode Even faster execution
vision Visual understanding

Full API Reference

See references/api.md for all endpoints including Sessions, Files, Skills, and Skills Marketplace.

安全使用建议
Before installing, verify the following: (1) Confirm you trust the domains docs.browser-use.com and api.browser-use.com and that they belong to the service you expect — check official ownership and privacy policy. (2) Understand that the skill expects you to store an API key in your Clawdbot config (skills.entries.browser-use.apiKey) even though the registry metadata lists no required credentials — ask the publisher to declare the credential formally. (3) Be aware that 'profiles' persist cookies/logins and the 'tasks' feature will drive browsers and can send page content (including authenticated content) to Browser Use's servers and their 'browser-use-llm' — do not use with sensitive accounts unless you accept that risk. (4) Confirm you are comfortable with the skill running gateway config.patch and modifying global config; if not, refuse or run in a sandbox/isolated agent. (5) Ask the publisher to resolve the ownerId mismatch, include the missing referenced files (references/api.md), and clarify whether examples using $API_KEY are meant to be env vars or the stored clawdbot config value. If you proceed, create a dedicated, limited-privilege API key/account for this integration and avoid syncing sensitive account cookies.
功能分析
Type: OpenClaw Skill Name: browser-use-1-0-0 Version: 1.0.0 The skill bundle is designed to interact with the 'Browser Use' cloud API for browser automation. All network calls (`curl`) are directed to `https://api.browser-use.com` for legitimate API interactions (creating sessions, profiles, tasks) and require an API key read from `clawdbot config`. The `SKILL.md` instructions include a `gateway config.patch` command to configure the Clawdbot's browser tool with a CDP URL from the 'Browser Use' service, which is a functional requirement for the skill's purpose. There is no evidence of prompt injection against the local agent, data exfiltration beyond necessary API key usage, malicious execution, persistence mechanisms, or obfuscation within the provided files. The actions are transparently aligned with the stated goal of using a remote browser service.
能力评估
Purpose & Capability
The SKILL.md describes a cloud-browser API and how to create sessions, profiles, and tasks — these map to the stated purpose. However, the skill metadata declares no required credential or env vars while the runtime instructions clearly rely on an API key. Also _meta.json ownerId differs from the registry owner ID in the provided metadata, and the SKILL.md references a local file (references/api.md) that is not included.
Instruction Scope
Instructions tell the agent to write an API key into the global Clawdbot config (skills.entries.browser-use.apiKey) and to run gateway config.patch to inject a cdpUrl into gateway configuration — both actions modify agent/global configuration. The 'Tasks (Subagent)' feature will run autonomous browser tasks and instructs to 'always use browser-use-llm', implying potentially sending page content (including content from authenticated sessions tied to profiles/cookies) to an external LLM/service. There is no warning about sensitive data exfiltration.
Install Mechanism
Instruction-only skill with no install spec or code files — nothing is written to disk by an installer. This is the lowest-risk install mechanism.
Credentials
The skill requires an API key at runtime but the registry metadata declares no required env vars or primary credential. Examples in the doc use $API_KEY, while the setup text says the API key lives in clawdbot config — inconsistent. The feature set (profiles that persist cookies and an LLM for tasks) justifies an API key, but the skill should declare that credential and clarify storage/access. Persisting cookies/profiles and running autonomous tasks increases the sensitivity of the credential and the data the service will see.
Persistence & Privilege
always is false (normal). However, the instructions explicitly modify global Clawdbot/gateway configuration (clawdbot config set and gateway config.patch). Writing to global agent config is functionally expected for integration but is a privilege: it can change runtime behavior and expose stored credentials to the service if misconfigured. This cross-config modification should be confirmed acceptable.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install browser-use-1-0-0
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /browser-use-1-0-0 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
Initial release of the browser-use skill. - Provides cloud browser automation and persistent browser sessions for Clawdbot via Browser Use API. - Supports creation and management of browser sessions with optional profile support for persisted logins. - Enables subagent browser task execution using a fast, specialized language model. - Includes setup instructions, API key configuration guidance, and pricing overview. - Detailed usage documentation for sessions, profiles, and task subagents.
元数据
Slug browser-use-1-0-0
版本 1.0.0
许可证
累计安装 4
当前安装数 4
历史版本数 1
常见问题

Browser Use 1.0.0 是什么?

Use Browser Use cloud API to spin up cloud browsers for Clawdbot and run autonomous browser tasks. Primary use is creating browser sessions with profiles (pe... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 810 次。

如何安装 Browser Use 1.0.0?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install browser-use-1-0-0」即可一键安装,无需额外配置。

Browser Use 1.0.0 是免费的吗?

是的,Browser Use 1.0.0 完全免费(开源免费),可自由下载、安装和使用。

Browser Use 1.0.0 支持哪些平台?

Browser Use 1.0.0 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Browser Use 1.0.0?

由 Makforce(@makforce)开发并维护,当前版本 v1.0.0。

💬 留言讨论