Token导航 LogoToken导航TokenDH.com
研究检索操作浏览器github未标认证来源可访问许可证需确认审计异常

xX 搜索

Agent Skill

该 Skill 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

294

周安装

12

GitHub Stars

6

下载量

94
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:x(X 搜索)
来源仓库:https://github.com/zuttam/business-growth-mp
仓库路径:skills/x
安装命令:
npx skills add https://github.com/zuttam/business-growth-mp --skill x
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/zuttam/business-growth-mp --skill x

简介

该 Skill 用于查找、检索和筛选相关信息。

  • 适合在 Codex、Claude、Cursor、Gemini CLI 中根据关键词或任务场景快速定位候选结果。
  • 通过 npx skills add 命令从指定 GitHub 仓库安装使用。
  • 安装前需确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。
  • 建议结合原始 README 核验具体用法和功能边界。

SKILL.md

X Community Engagement Skill

Overview

This skill enables authentic X engagement by discovering relevant tweets and threads, identifying thought leaders to follow, crafting concise replies and posts, and tracking engagement history.

Actions

ActionFileWhen to Use
Loginreferences/login.mdAuthenticate with X before engaging
Researchreferences/research.mdFind tweets, discover people, build content database
Engagereferences/engage.mdReply to tweets, create new tweets, or quote tweet

Data Files

FilePurpose
.business_growth/marketing/social/BUSINESS.mdShared business context (required)
.business_growth/marketing/social/x/strategy.mdX engagement strategy (overall approach, accounts to monitor, content themes)
.business_growth/marketing/social/x/{YYYY-MM}/{YYYY-MM-DD}.mdDaily tweets, people, and engagement log
community-pulse/skills/x/.env.profiles.localX credentials (gitignored)

Quick Start

  1. First time? → Run Login to authenticate, then Research to find tweets and people
  2. Have tweets? → Run Engage to reply, post, or quote tweet
  3. Before any Research or Engagement → The strategy file at .business_growth/marketing/social/x/strategy.md is loaded automatically. If it doesn't exist, you'll be asked if you want to create one.

Decision Flow

User Request
    │
    ├─► "Login" / "Sign in" / "Authenticate"
    │       └─► Load references/login.md
    │
    ├─► "Find tweets" / "Research" / "Discover" / "Find people"
    │       └─► Load references/research.md
    │
    ├─► "Reply" / "Tweet" / "Post" / "Engage" / "Quote"
    │       └─► Load references/engage.md
    │
    └─► Unclear
            └─► Ask: "Would you like me to research X posts/people or engage with existing content?"

Browser MCP Quick Reference

Get Browser Context

tabs_context_mcp (get available tabs)
tabs_create_mcp (create new tab if needed)

Navigation

navigate (url, tabId)

Reading Page

read_page (tabId) - Get page structure
get_page_text (tabId) - Get text content
screenshot - Visual verification

Finding Elements

find (query, tabId) - Natural language element search

Interaction

form_input (ref, value, tabId) - Fill form fields
computer (action: "left_click", coordinate, tabId) - Click elements
computer (action: "scroll", scroll_direction, tabId) - Scroll page
computer (action: "type", text, tabId) - Type text

Important Notes

  1. Authentication: Use login skill or ensure manual login before engaging
  2. Rate Limits: X limits tweet frequency and API access - wait between actions
  3. Character Limit: Tweets are limited to 280 characters (threads for longer content)
  4. Shadowbans: Aggressive tweeting or follow/unfollow can trigger restrictions
  5. Algorithm: X algorithm favors engagement (replies, quotes) over plain tweets
  6. User Approval: ALL engagement actions require explicit user confirmation

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

36.76%
按下载量换算35

Claude

29.65%
按下载量换算28

Cursor

18.78%
按下载量换算18

Gemini CLI

9.06%
按下载量换算9

安全审计

Gen Agent Trust Hub

未通过

Socket

通过

Snyk

未通过

权限和风险

操作浏览器

该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills