← Back to Skills Marketplace
Brave Loggedin Tag Browsing
by
https://github.com/account/ssh
· GitHub ↗
· v2.0.1
· MIT-0
235
Downloads
0
Stars
1
Active Installs
2
Versions
Install in OpenClaw
/install brave-loggedin-tag-browsing
Description
使用 Brave 瀏覽器（已登入狀態）瀏覽 X/Twitter、Facebook 用戶頁面並提取最新帖子。 自動化社交媒體監控，支援登入狀態檢查、帖子提取、互動數據抓取。
README (SKILL.md)
brave-loggedin-tag-browsing
自動化瀏覽器技能 - 使用已登入的 Brave 瀏覽器查看 X/Twitter、Facebook 用戶帖子
⚠️ 平台支援
目前僅支援：
x/twitter- X/Twitter（完整功能）facebook/fb- Facebook（基本功能）
暫不支援：Instagram、LinkedIn、YouTube 等
🎯 核心功能
- 登入狀態检测：自動檢查瀏覽器是否已登入目標平台
- 帖子提取：抓取最新 N 篇帖子（文字、時間）
- 互動數據：可選提取轉推/喜歡/分享 或 留言/分享/讚數
- 用戶資料：抓取姓名、bio、粉絲/追蹤數
- 彈性連接：優先連接 OpenClaw browser 實例
📥 輸入參數
| 參數 | 類型 | 必填 | 預設 | 說明 |
|---|---|---|---|---|
username |
string | ✅ | - | 帳號名稱（不需 @） |
platform |
string | ❌ | x |
x、twitter、facebook、fb |
maxPosts |
number | ❌ | 5 | 最大帖子數（建議 ≤ 20） |
includeStats |
boolean | ❌ | true | 是否包含互動數據 |
🚀 使用方式
CLI
node index.js realDonaldTrump x 5 true
node index.js markzuckerberg facebook 3 false
OpenClaw (sessions_spawn)
await sessions_spawn({
runtime: "subagent",
task: JSON.stringify({
skill: "brave-loggedin-tag-browsing",
params: { username: "elonmusk", platform: "x", maxPosts: 5, includeStats: true }
})
});
📤 輸出格式
{
"username": "realDonaldTrump",
"platform": "x",
"loginStatus": "💰 錢錢AI (@MVenusean67544)",
"profile": { "name": "...", "bio": "...", "followers": "110.8M" },
"posts": [
{ "time": "2026-03-02T16:20:05.000Z", "text": "...", "stats": { "likes": "459K" } }
],
"metadata": { "maxPosts": 5, "timestamp": "...", "connectionMode": "opencdl" }
}
⚙️ 技術實現
- 依賴：playwright（chromium）
- 連接策略：
- OpenClaw CDP (port 18800)
- Chrome CDP (port 9222)
- 啟動新 Brave 實例（userDataDir）
🔧 故障排除
| 問題 | 解決方案 |
|---|---|
| 連接 OpenClaw Brave 失敗 | 先執行 /browser start |
| 提示安裝瀏覽器 | npx playwright install chromium |
| 未檢測到登入 | 在 Brave 中手動登入目標平台 |
| 提取不到帖子 | 增加等待時間或檢查 DOM 選擇器 |
📊 效能指標
- 首次執行：8-12 秒
- 後續執行：3-5 秒
- 記憶體：~150MB
- 建議 maxPosts ≤ 20
📝 License
CC BY-NC 4.0
Usage Guidance
This skill appears to do what it says, but it requires access to your Brave/Chrome profile (cookies and logged-in sessions) to read private or authenticated content. Before installing: (1) only run it on a machine/profile you control; consider creating a dedicated browser profile for automation so your personal accounts are not exposed; (2) be aware it connects to localhost CDP (http://localhost:18800) — if a malicious CDP server were running locally it could be used; (3) installing will pull Playwright and its browser components from npm (normal but moderately privileged); (4) review/modify hardcoded paths (e.g., ~/.config/google-chrome, /usr/bin/brave-browser) if they don't match your environment. If you need stronger guarantees, run the skill in an isolated environment or ephemeral profile.
Capability Analysis
Type: OpenClaw Skill
Name: brave-loggedin-tag-browsing
Version: 2.0.1
The skill is designed to scrape data from X/Twitter and Facebook by accessing the user's authenticated browser sessions, which involves reading sensitive browser profile data from hardcoded paths like `/home/shuttle/.config/google-chrome` (found in `dist/index.js` and `index.ts`). While this behavior is consistent with the stated purpose of 'social media monitoring,' the ability to programmatically access and extract data from logged-in accounts is a high-risk capability. The implementation also disables security features such as the Chromium sandbox and `AutomationControlled` flags to evade bot detection, which is a common technique in scraping tools but increases the attack surface.
Capability Assessment
Purpose & Capability
The name/description (logged-in Brave browsing of X/Facebook) aligns with the implementation: files use Playwright to connect to a local CDP (port 18800) or launch Brave with a persistent userDataDir. Playwright is a reasonable dependency for this task. No unrelated credentials or external services are required.
Instruction Scope
SKILL.md and the code are focused on browsing user pages, checking login state, extracting posts/profile/stats, and prefer connecting to an OpenClaw browser instance. The README and troubleshooting mention cookie files and starting the OpenClaw browser tool; these are within the skill's stated scope but do mean the skill will read and use whatever is present in the browser profile (cookies/sessions).
Install Mechanism
This is instruction- and code-based (no declarative installer). Dependencies come from npm (playwright) as declared in package.json/package-lock.json — a standard, traceable source. There are no downloads from personal servers or URL shorteners. Installing Playwright will pull browser binaries via its normal mechanism (expected but moderately privileged).
Credentials
The skill requests no env vars or external credentials, which is appropriate. However, it intentionally accesses a persistent browser profile (userDataDir like ~/.config/google-chrome or /home/shuttle/.config/google-chrome) and connects to local CDP. Access to that directory gives the skill cookies/session tokens and therefore access to logged-in content — this is necessary for the feature but is sensitive and worth user caution.
Persistence & Privilege
The skill is not always-enabled and does not request elevated platform privileges. It intentionally keeps the browser session alive (does not close the browser) to preserve login state, which is reasonable for the use case but means sessions remain accessible after a run.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install brave-loggedin-tag-browsing - After installation, invoke the skill by name or use
/brave-loggedin-tag-browsing - Provide required inputs per the skill's parameter spec and get structured output
Version History
v2.0.1
- Minor maintenance update; no user-facing changes.
- Internal files updated (cli.js, package.json, skill.json).
- Documentation and features remain unchanged.
v2.0.0
**Major update with expanded documentation and technical details**
- Comprehensive SKILL.md added, detailing supported platforms, features, input parameters, and usage instructions.
- Now supports browsing and extracting recent posts from X/Twitter and Facebook via a logged-in Brave browser.
- Includes auto login-state checking, post extraction, interaction stats, and user profile grabbing.
- Details robust connection strategy (OpenClaw, Chrome CDP, or standalone Brave).
- Provides troubleshooting steps and performance benchmarks.
- Clarifies input/output formats for both CLI and programmable use.
Metadata
Frequently Asked Questions
What is Brave Loggedin Tag Browsing?
使用 Brave 瀏覽器（已登入狀態）瀏覽 X/Twitter、Facebook 用戶頁面並提取最新帖子。 自動化社交媒體監控，支援登入狀態檢查、帖子提取、互動數據抓取。 It is an AI Agent Skill for Claude Code / OpenClaw, with 235 downloads so far.
How do I install Brave Loggedin Tag Browsing?
Run "/install brave-loggedin-tag-browsing" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Brave Loggedin Tag Browsing free?
Yes, Brave Loggedin Tag Browsing is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Brave Loggedin Tag Browsing support?
Brave Loggedin Tag Browsing is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Brave Loggedin Tag Browsing?
It is built and maintained by https://github.com/account/ssh (@sean810720); the current version is v2.0.1.
More Skills