Skip to content
TrustedSkillsbeta
Back to all skills

X Intelligence (xint)

Listed
0xNyk·v1.0.0·agents·MIT

X Intelligence CLI — search, analyze, monitor, and engage on X/Twitter. Real-time search, AI-powered analysis, sentiment reports, bookmarks, trending topics, and following management.

Repository

Install on your platform

Showing OpenClaw.

  1. 1

    Run this in your terminal

    terminal
    $ openclaw skills install xint

What we know about this skill

Publisher

0xNyk

Taken from the source listing. We haven't verified who controls this account.

Install target

Pinned to c8ddaf14

Installs fetch a stored snapshot of that commit, so the code can't change after the fact.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill failed 2 of 6 checks. A failure is not proof of bad intent; it means something in the code needs a human to look at it before you run it.

  • No undeclared network calls: failed

    Contacts 11 hosts that are neither well-known infrastructure nor declared in the skill's frontmatter: api.x.ai, api.x.com, console.x.ai, grok.com, management-api.x.ai….

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

    Hosts contacted

    api.github.comsource hostgithub.comsource hostx.comundeclaredapi.x.comundeclarednews.ycombinator.comundeclaredapi.x.aiundeclaredmanagement-api.x.aiundeclaredconsole.x.aiundeclaredgrok.comundeclared127.0.0.1localxint.devundeclaredtwitter.comundeclaredpbs.twimg.comundeclaredvideo.twimg.comundeclared

    What it found (3 of 40)

    • lib/actions.ts:78contacts x.com
      example: "xint thread https://x.com/.../status/...",
    • lib/actions.ts:87contacts x.com
      example: "xint article https://x.com/.../status/...",
    • lib/api.ts:153contacts x.com
      tweet_url: `https://x.com/${u.username || "?"}/status/${t.id}`,

  • No pipe-to-shell installers: failed

    Runs code fetched at install time in 2 places.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

    What it found

    • install.sh:28remote script piped into an interpreter
      tag="$(curl -fsSL "$api_url" | python3 -c 'import json,sys; print(json.load(sys.stdin)["tag_name"])')"
    • SKILL.md:88tells the user to run: remote script piped into a shell(in the instructions, not code)
      - For Bun: prefer OS package managers over `curl | bash` when possible

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • Pinned to a commit: passed

    Scanned 0xnyk/xint at a33dcc9615.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
a33dcc9615
Manifest
SKILL.md
Scanned
60 files, 12,810 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

xint is a command-line interface (CLI) tool designed for searching, monitoring, analyzing, and engaging on X/Twitter. It enables full-text search capabilities, real-time monitoring of specific terms, follower tracking, and AI sentiment analysis – all accessible directly from the terminal. The tool also supports structured export of data in JSONL or CSV formats.

When to use it

  • Market Research: Track trending topics and analyze public sentiment related to a new product launch.
  • Competitive Analysis: Monitor competitor activity on X/Twitter, including mentions and follower changes.
  • OSINT Investigations: Search for specific keywords or phrases within X/Twitter data for investigative purposes.
  • AI Agent Skill Integration: Integrate xint's capabilities into AI agents like Claude Code or OpenClaw to automate tasks related to X/Twitter interaction.

Key capabilities

  • Full-text search of X/Twitter content
  • Real-time monitoring of keywords and hashtags
  • Follower tracking for specific accounts
  • AI sentiment analysis of tweets
  • Structured export in JSONL or CSV formats
  • Unix pipeline integration
  • MCP server for AI agent tools

Example prompts

  • "Search X/Twitter for posts mentioning 'large language models' and save the results to a file."
  • "Monitor the hashtag '#AI' every 15 minutes and alert me to any significant changes in volume or sentiment."
  • “Find all tweets from users who follow @elonmusk containing the word ‘dogecoin’.”

Tips & gotchas

  • Requires an X API access token with prepaid credits. You can obtain this through the X Developer Portal.
  • The tool is built on Bun, so ensure you have it installed before attempting to use xint.

Tags

twitterxsocial-mediamonitoringclisearchsentiment