Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Browser Auto Tweet To X

ASecurity

Automate X posts via browser control - bypass $200/month API costs.

19 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentsgobashapi

Works with

api

Security Analysis

A96/100
mediumInstalls packages at runtime which could introduce malicious dependencies

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add rondoflow/rondoflow --skill browser-auto-tweet-to-x --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Browser Auto Tweet To X?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Browser Auto Tweet To X
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/rondoflow-browser-auto-tweet-to-x/badge)](https://www.skillsdirectory.com/skills/rondoflow-browser-auto-tweet-to-x)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: browser-auto-tweet-to-x
description: "Automate X posts via browser control - bypass $200/month API costs."
category: "Web & Scraping"
author: community
version: "1.0.0"
icon: globe
---

# X (Twitter) Automation Skill

Automate X posts via browser control - bypass $200/month API costs.

## What It Does

- **Scrape trending topics** from your personalized "For You" feed
- **Generate tweet ideas** based on trends (crypto/Web3/tech focused)
- **Schedule tweets** throughout the day for natural posting
- **Post via browser automation** - no API keys needed
- **Queue management** for approval workflows

## Why This Exists

X API pricing is insane:
- Free tier: Write-only, can't read anything
- Basic: $200/month for 15k tweets read
- Pro: $5,000/month

This skill uses browser automation instead. Zero API costs.

## Features

✅ **Trend Scraping**
- Navigates to X.com/explore
- Extracts trending topics from "For You" tab
- Saves to JSON for AI processing

✅ **Tweet Generation**
- AI generates 3-5 tweet ideas based on trends
- Customizable tone/voice
- Length optimization (150-250 chars for engagement)

✅ **Scheduled Posting**
- Space tweets throughout the day
- Human-like delays between posts
- Approval queue workflow

✅ **Browser Automation**
- Uses OpenClaw browser control
- Requires one-time login
- Session persists across runs

## Installation

```bash
cd ~/.openclaw/workspace/skills/x-automation
npm install
```

## Usage

### 1. Manual Tweet Generation

Ask your agent:
```
"Check X trends and generate 3 tweet ideas"
```

The agent will:
1. Navigate to X.com/explore
2. Scrape trending topics
3. Generate tweet ideas
4. Send to you for approval
5. Post approved tweets

### 2. Automated Posting (Cron)

Set up a cron job to run every 4 hours:

```json
{
  "schedule": { "kind": "every", "everyMs": 14400000 },
  "payload": {
    "kind": "agentTurn",
    "message": "Check X trends, generate 2-3 tweet ideas, send to Telegram for approval"
  },
  "sessionTarget": "isolated"
}
```

### 3. Direct Posting

```
"Post this tweet: <your text>"
```

## Configuration

No API keys needed! Just:

1. **Log in to X.com** in OpenClaw browser
2. **Keep browser session active** (or re-login when needed)
3. **Customize tweet voice** in your SOUL.md or prompt

## Tweet Generation Guidelines

Default focus areas (customize in your prompts):
- Crypto trends (ETH, Base L2, DeFi)
- Web3 development
- Tech commentary
- Product updates (if applicable)

Default tone:
- Direct, opinionated
- No corporate speak
- Short & punchy (150-250 chars)
- Engagement-focused

## File Structure

```
x-automation/
├── scripts/
│   ├── auto-tweet.js       # Main automation
│   ├── post.js             # Single tweet posting
│   ├── post-approved.js    # Post from queue
│   └── check-trends.js     # View current trends
├── data/                   # Created on first run
│   ├── latest-trends.json
│   ├── approved-queue.json
│   └── tweet-history.json
├── SKILL.md
├── README.md
└── package.json
```

## Safety Features

- **No auto-posting without approval** (unless you configure it)
- **Human-like delays** (30-60s between tweets)
- **Daily limits** (configurable, default 10/day)
- **Queue review** before posting

## Anti-Detection

- Uses real browser session (not headless)
- Random delays between actions
- Natural posting schedule
- Human-like mouse movements (Playwright)

## Limitations

- Requires browser to stay logged in
- Can be detected if too aggressive
- Manual login required (can't automate 2FA)

## Legal Note

This automates YOUR account via YOUR browser. You're not violating X ToS any more than using the website normally. Just don't spam.

## Pro Tips

**Optimal posting times (adjust for your timezone):**
- Morning: 9-10 AM (commute browsing)
- Lunch: 1-2 PM (break time)
- Evening: 7-9 PM (peak Twitter hours)
- Late: 11 PM-12 AM (night crew)

**Posting frequency:**
- 2-4 tweets/day is natural
- Space out by 3-4 hours minimum
- Don't post all at once

**Content strategy:**
- Comment on trends (show you're plugged in)
- Share insights (demonstrate expertise)
- Mention your product (subtle, 1 in 5 tweets)
- Engage with replies (build community)

## Examples

See `WORKFLOW.md` for detailed examples of:
- Trend scraping output
- Generated tweet samples
- Approval workflows
- Scheduling strategies

## Support

This skill is credential-free and safe to share. No API keys, no passwords, no private data.

Issues? Check:
1. Is browser logged into X?
2. Is OpenClaw browser control running?
3. Are cron jobs properly configured?

---

Built for crypto devs who refuse to pay $200/month for an API that should be free.

Attribution

rondoflowrondoflow
View sourceMore from rondoflow →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1066601 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →