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

Monitor X Accounts Noteworthy Tweets

ASecurity

Monitor specific X/Twitter accounts and surface noteworthy tweets on a configurable schedule. Filters for high-value content about technology and trends, excluding political rage bait. Use when user wants to manage their X account list, run a manual check, or update filtering cr…

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

Works with

api

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add rondoflow/rondoflow --skill monitor-x-accounts-noteworthy-tweets --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Monitor X Accounts Noteworthy Tweets?

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

Security grade badge for Monitor X Accounts Noteworthy Tweets
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/rondoflow-monitor-x-accounts-noteworthy-tweets/badge)](https://www.skillsdirectory.com/skills/rondoflow-monitor-x-accounts-noteworthy-tweets)

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

Download with Pro
Files
SKILL.md
---
name: monitor-x-accounts-noteworthy-tweets
description: "Monitor specific X/Twitter accounts and surface noteworthy tweets on a configurable schedule. Filters for high-value content about technology and trends, excluding political rage bait. Use when user wants to manage their X account list, run a manual check, or update filtering cr…"
category: "DevOps & Infra"
author: community
version: "1.0.0"
icon: server
---

# X Monitor

Automated Twitter/X monitoring with intelligent filtering for high-value content.

## Setup

### 1. X API Credentials

Save your X API credentials to `~/.openclaw/workspace/x-monitor/credentials.json`:

```json
{
  "bearer_token": "YOUR_BEARER_TOKEN_HERE"
}
```

### 2. Handles to Monitor

Configure accounts in `~/.openclaw/workspace/x-monitor/handles.json`:

```json
{
  "handles": [
    "naval",
    "paul_graham",
    "balajis",
    "vitalikbuterin"
  ]
}
```

**Limit:** 10-20 handles recommended for API quota management.

### 3. Schedule Configuration

Configure check frequency in `~/.openclaw/workspace/skills/x-monitor/config/schedule.json`:

```json
{
  "timezone": "America/Los_Angeles",
  "check_times": ["08:00", "12:00", "16:00", "20:00"],
  "enabled": true
}
```

**Options:**
- `timezone`: IANA timezone string (e.g., "America/New_York", "Europe/London", "Asia/Tokyo")
- `check_times`: Array of 24-hour times for daily checks (e.g., ["09:00", "18:00"] for twice daily)
- `enabled`: Set to false to pause scheduled checks

**Common schedules:**
- 4x daily (default): `["08:00", "12:00", "16:00", "20:00"]`
- 3x daily: `["09:00", "14:00", "20:00"]`
- 2x daily: `["09:00", "18:00"]`
- 1x daily: `["09:00"]`

### 4. Setup Cron Jobs

After configuring your schedule, ask the agent to set up the cron jobs:
- "set up x monitor cron jobs" — creates cron jobs based on your schedule.json
- "update x monitor schedule" — updates cron jobs after changing schedule.json

### 5. Noteworthy Criteria

Edit `~/.openclaw/workspace/x-monitor/noteworthy-criteria.md` to customize what gets surfaced.

## Scheduled Reports

Reports run at the times specified in `config/schedule.json`. Each report includes:
1. **Executive summary** — high-level overview of noteworthy items
2. **Filtered tweets** — chronological list with author, content, metrics

## Commands

**Manage handles:**
- "add @username to x monitor" — add a new handle
- "remove @username from x monitor" — remove a handle
- "show x monitor handles" — list current handles

**Manual check:**
- "check x now" — run immediate report

**Schedule management:**
- "show x monitor schedule" — display current schedule config
- "set x monitor to check at 9am and 6pm" — update check times
- "set x monitor timezone to America/New_York" — update timezone
- "set up x monitor cron jobs" — create/update cron jobs from schedule.json

**Update criteria:**
- "show noteworthy criteria" — display current filter rules
- "update noteworthy criteria" — help edit the criteria

## What Counts as Noteworthy (Default)

**Include:**
- Insights on technology trends, AI, crypto, product design
- First-person experiences building/shipping
- Novel frameworks, metaphors, or mental models
- Data-driven observations with concrete examples
- Contrarian but well-argued takes

**Exclude:**
- Political rage bait or partisan content
- Generic motivational quotes
- Pure engagement farming

## API Details

Uses X API v2 `tweets/search/recent` endpoint:
- Max results: 10 per handle per check
- Fields: `created_at`, `public_metrics`, `author_id`, `lang`
- Expansions: `author_id` for full user info
- Query pattern: `from:{handle}`

## Storage

- **Credentials:** `~/.openclaw/workspace/x-monitor/credentials.json`
- **Handles:** `~/.openclaw/workspace/x-monitor/handles.json`
- **Schedule:** `~/.openclaw/workspace/skills/x-monitor/config/schedule.json`
- **Criteria:** `~/.openclaw/workspace/x-monitor/noteworthy-criteria.md`
- **Last check:** `~/.openclaw/workspace/x-monitor/last-check.json` (timestamp tracking)

## Cron Job Setup

When setting up cron jobs, the agent will:
1. Read `config/schedule.json` for timezone and times
2. Create isolated cron jobs using `agentTurn` payloads
3. Each job runs: fetch tweets → filter for noteworthy → deliver summary

Example cron expression for 8am in America/Los_Angeles:
```json
{
  "schedule": { "kind": "cron", "expr": "0 8 * * *", "tz": "America/Los_Angeles" },
  "payload": { "kind": "agentTurn", "message": "Run x-monitor check and report noteworthy tweets" }
}
```

## Error Handling

- Rate limits: Backs off and logs warning
- Invalid handles: Skips and reports
- API errors: Logs and continues with remaining handles

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 →