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

Realtime Twitter Search With Citations

ASecurity

Search X/Twitter in real-time using Grok or X API. Find tweets, trends, and discussions with citations.

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

Works with

claude codeapi

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add rondoflow/rondoflow --skill realtime-twitter-search-with-citations --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Realtime Twitter Search With Citations?

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

Security grade badge for Realtime Twitter Search With Citations
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/rondoflow-realtime-twitter-search-with-citations/badge)](https://www.skillsdirectory.com/skills/rondoflow-realtime-twitter-search-with-citations)

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

Download with Pro
Files
SKILL.md
---
name: realtime-twitter-search-with-citations
description: "Search X/Twitter in real-time using Grok or X API. Find tweets, trends, and discussions with citations."
category: "Communication"
author: community
version: "1.0.1"
icon: message-circle
---

# Search X

Real-time X/Twitter search with two modes:
1. **xAI Grok** (default) — AI-powered search with x_search tool, up to 30 days
2. **X API** (`--x-api`) — Native X search, up to 7 days, pay-per-use

## Setup

### Option 1: xAI API (default)

```bash
export XAI_API_KEY="xai-YOUR-KEY"
```
Get your key at: https://console.x.ai

### Option 2: X API (native)

```bash
export X_BEARER_TOKEN="YOUR-BEARER-TOKEN"
```
Get your token at: https://console.x.com

**Note:** X API uses pay-per-usage pricing. No subscription needed.

## Commands

### Basic Search (xAI Grok)
```bash
node {baseDir}/scripts/search.js "AI video editing"
```

### Native X API Search
```bash
node {baseDir}/scripts/search.js --x-api "AI video editing"
node {baseDir}/scripts/search.js --x-api --max 50 "trending topic"  # More results
```

### Filter by Time
```bash
node {baseDir}/scripts/search.js --days 7 "breaking news"
node {baseDir}/scripts/search.js --days 1 "trending today"
node {baseDir}/scripts/search.js --x-api --days 7 "news"  # X API max is 7 days
```

### Filter by Handles
```bash
node {baseDir}/scripts/search.js --handles @elonmusk,@OpenAI "AI announcements"
node {baseDir}/scripts/search.js --exclude @bots "real discussions"
```

### Output Options
```bash
node {baseDir}/scripts/search.js --json "topic"        # Full JSON response
node {baseDir}/scripts/search.js --compact "topic"     # Just tweets, no fluff
node {baseDir}/scripts/search.js --links-only "topic"  # Just X links
```

## Example Usage in Chat

**User:** "Search X for what people are saying about Claude Code"
**Action:** Run search with query "Claude Code"

**User:** "Find tweets from @remotion_dev in the last week"
**Action:** Run search with --handles @remotion_dev --days 7

**User:** "What's trending about AI on Twitter today?"
**Action:** Run search with --days 1 "AI trending"

**User:** "Search X for Remotion best practices, last 30 days"
**Action:** Run search with --days 30 "Remotion best practices"

## How It Works

### xAI Grok Mode (default)
Uses xAI's Responses API (`/v1/responses`) with the `x_search` tool:
- Model: `grok-4-1-fast` (optimized for agentic search)
- Up to 30 days of history
- AI-powered result formatting with citations
- Returns real tweets with URLs

### X API Mode (--x-api)
Uses X's native search API (`/2/tweets/search/recent`):
- Up to 7 days of history
- Pay-per-usage pricing (no subscription)
- Raw tweet data with metrics
- Up to 100 results per query

## Response Format

Each result includes:
- **@username** (display name)
- Tweet content
- Date/time
- Engagement metrics (X API mode)
- Direct link to tweet

## Environment Variables

**xAI Mode:**
- `XAI_API_KEY` - Your xAI API key (required for default mode)
- `SEARCH_X_MODEL` - Model override (default: grok-4-1-fast)
- `SEARCH_X_DAYS` - Default days to search (default: 30)

**X API Mode:**
- `X_BEARER_TOKEN` - Your X API Bearer Token
- `TWITTER_BEARER_TOKEN` - Alternative env var name

## Security & Permissions

**What this skill does:**
- Calls xAI's `/v1/responses` endpoint (Grok mode) or X's `/2/tweets/search/recent` endpoint (X API mode)
- Returns public tweet data with URLs and citations
- All requests go only to `api.x.ai` or `api.x.com`

**What this skill does NOT do:**
- Does not post, like, retweet, or modify any X/Twitter content
- Does not access your X/Twitter account or DMs
- Does not read config files or access the local filesystem
- Does not send credentials to any third-party endpoint
- Cannot be invoked autonomously by the agent (`disable-model-invocation: true`)

Review `scripts/search.js` before first use to verify behavior.

Attribution

rondoflowrondoflow
View sourceMore from rondoflow →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

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

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

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".

1074701 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', ...

693621 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.

691 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 →