← 返回 Skills 市场
tielei

Browser Automation

作者 Charles Zhang · GitHub ↗ · v0.0.5 · MIT-0
cross-platform ✓ 安全检测通过
101
总下载
2
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install bridgic-browser
功能描述
Use for any task requiring a real browser: viewing web pages, accessing login-gated sites, operating web UIs, scraping social media (Xiaohongshu/Weibo/Twitte...
使用说明 (SKILL.md)

Dependencies

A bridgic-browser project requires the following packages:

Package Description
bridgic-browser Browser automation CLI + Python SDK (installing one installs both)

Additionally, browser binaries must be installed once: uv run playwright install chromium.

Installation: Run the install script to set up all dependencies:

bash "skills/bridgic-browser/scripts/install-deps.sh" "$PWD"

The script checks uv availability, initializes a uv project if needed, installs missing packages, and ensures Playwright chromium is available.

Strategies & Guidelines (Important!!)

Notes:

  • Whenever invoking the bridgic-browser CLI, you must call it using uv run.
  • If the user clearly specifies exact steps that must be followed, try to perform the exploration according to those steps. If loops or branches appear during exploration, decide the best exploration path autonomously.
  • If you think you may need to return to the original page after clicking into a new page, try opening the new page in a new browser tab instead of using a “click then go back” approach. This is especially important when the original page already has interaction state (such as filled forms or applied filters); otherwise, that state may be lost after navigating back. Be sure to close the new tab promptly after finishing the related actions.
  • If exploration involves repeatedly clicking items in a list, you do not need to traverse every item (especially when the list is large).
  • If login, verification, or authorization is required during exploration, pause and ask the user to complete it manually, unless the user explicitly provides instructions in the task.
  • To avoid operating on websites too frequently, maintain human-like access intervals during both exploration and coding. You may simulate random wait times to reduce the risk of being blocked. Note: the bridgic-browser wait command parameter is in seconds, not milliseconds; for example, bridgic-browser wait 2 or bridgic-browser wait 3.2.
  • After finishing exploration and code writing, automatically run testing/validation.
  • CDP mode tab visibility: when attached via --cdp to a user's running Chrome, tabs / switch-tab / close-tab only see pages bridgic itself opened (the initial blank tab plus anything spawned from it via new-tab or a click on a target="_blank" link). The user's other tabs are deliberately invisible to bridgic — never assume you can switch-tab into them. To work with such a tab, ask the user to navigate to it through bridgic, or use new-tab \x3Curl>.

Reference Files

Reference files cover all use cases. Load only the one(s) relevant to the task:

Scenario Interface Load
Directly control browser from terminal CLI cli-guide.md
Write Python code about browser automation Python sdk-guide.md
Write shell script about browser automation CLI cli-guide.md
Explore via CLI, then generate Python code CLI → Python cli-sdk-api-mapping.md + sdk-guide.md
Migrate / compare / explain CLI ↔ SDK Both cli-sdk-api-mapping.md
Configure env vars or login state persistence Either env-vars.md
Connect to an existing Chrome (chrome://inspect, --remote-debugging-port, cloud browser, Electron) CLI / SDK cdp-mode.md

Interface Decision Rules

  1. Output requested as shell commands or scripts → use CLI guide first (references/cli-guide.md).
  2. Output requested as runnable Python code (async, Browser, tool builder) → use SDK guide first (references/sdk-guide.md).
  3. Input is CLI outputs or actions but output needs to be Python code → use mapping guide first (references/cli-sdk-api-mapping.md), then SDK guide for final code generation (references/sdk-guide.md).
  4. If intent is ambiguous, infer from requested artifacts (.sh / terminal session vs .py script).

Common Usage (CLI + SDK)

  • Ref-based actions depend on the latest snapshot.
  • After navigation or major DOM updates, refs can become stale; refresh snapshot before ref actions.
  • CLI keeps state in a daemon session across invocations. Set BRIDGIC_HOME env var to run multiple independent daemon instances (each with its own socket, logs, and user data).
  • SDK keeps state in the Python process/context. By default, browser profile (cookies, session) is persisted to $BRIDGIC_HOME/bridgic-browser/user_data/ (default ~/.bridgic/...); pass clear_user_data=True to Browser() for an ephemeral session.
  • Use exact command/method names from references; do not invent aliases.

Bridge Workflow: CLI Actions -> Python Code

  1. Parse CLI steps in order.
  2. Map each step using references/cli-sdk-api-mapping.md.
  3. Preserve behavior details: refs, options, arguments, configuration, etc.
  4. Emit runnable async Python code with explicit browser lifecycle (async with Browser(...) preferred).
  5. Call out any behavior differences that cannot be represented 1:1.

Minimal Quality Checklist

  • CLI request: return valid CLI commands/options only.
  • SDK request: return executable async Python with correct imports.
  • Bridge request: include mapping rationale plus final SDK code.
安全使用建议
This review is low confidence because the workspace inspection commands failed before reading metadata.json or artifact files; rerun the scan in an environment where the artifacts are readable before relying on this result.
能力标签
cryptorequires-oauth-tokenrequires-sensitive-credentials
能力评估
Purpose & Capability
Not enough readable artifact evidence to identify a purpose/capability mismatch.
Instruction Scope
Not enough readable artifact evidence to identify unsafe or deceptive instruction scope.
Install Mechanism
Not enough readable artifact evidence to identify a risky install mechanism.
Credentials
Not enough readable artifact evidence to identify disproportionate environment access.
Persistence & Privilege
Not enough readable artifact evidence to identify persistence or privilege abuse.
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 bridgic-browser
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /bridgic-browser 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
v0.0.5
bridgic-browser 0.0.5 - Provides robust browser automation via both CLI (`bridgic-browser ...`) and Python SDK interfaces. - Reuse the browser you already have open. New "--cdp" flag. - Supports complex web tasks: JS-rendered/dynamic pages, login-gated sites, social media scraping, bot detection evasion, and general web UI interaction. - Integrates guidelines and strategies for reliable automation, session management, and human-like behavior to reduce blocking. - Stealth that holds up in production. 24+ fingerprint vectors hardened. - Includes mapping documentation to bridge CLI steps and Python SDK code. - Covers best practices for tab handling, authentication pause, state persistence, and reference file usage for different automation scenarios. - Tab-level privacy. The agent only sees tabs it spawned. - CDP screencast video recorder + silent downloads with real filenames.
元数据
Slug bridgic-browser
版本 0.0.5
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Browser Automation 是什么?

Use for any task requiring a real browser: viewing web pages, accessing login-gated sites, operating web UIs, scraping social media (Xiaohongshu/Weibo/Twitte... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 101 次。

如何安装 Browser Automation?

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

Browser Automation 是免费的吗?

是的,Browser Automation 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Browser Automation 支持哪些平台?

Browser Automation 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 Automation?

由 Charles Zhang(@tielei)开发并维护,当前版本 v0.0.5。

💬 留言讨论