Token导航 LogoToken导航TokenDH.com
研究检索敏感数据github未标认证来源可访问许可证需确认审计异常

x-search搜索

Agent Skill

x-search 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

870

周安装

37

GitHub Stars

公开资料未说明

下载量

305
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-search(搜索)
来源仓库:https://github.com/syjcnss/skills
仓库路径:skills/x-search
安装命令:
npx skills add https://github.com/syjcnss/skills --skill x-search
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/syjcnss/skills --skill x-search

简介

x-search 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 仓库安装并使用。
  • 安装前需确认权限范围、维护状态,注意是否会触发联网、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 Search

Search X (Twitter) posts using xAI's Grok API with keyword search, semantic search, user filtering, and date range capabilities.

Instructions for Agents

When invoking this skill:

  1. Execute the script using the Bash tool with appropriate parameters based on the user's request
  2. Parse the output which contains both the analysis and citations sections
  3. CRITICAL: Always include the citations in your response to the user. The script output contains a "Citations:" section with numbered X post URLs that MUST be presented to the user
  4. Format your response to include:

- The analysis/findings from Grok - The complete citations list with all referenced post URLs

The script will return formatted output with citations. You MUST include these citations in your response to the user.

Quick Start

Basic X search:

scripts/x_search.sh "What are people saying about AI?"

Environment Setup

Required environment variables:

  • XAI_API_KEY: Your xAI API key (required)
  • XAI_API_HOST: API host URL (optional, defaults to https://api.x.ai)

Search Options

Date Range Filtering

Restrict search to specific time period:

scripts/x_search.sh "AI developments" --from-date 2025-01-01 --to-date 2025-02-06

User Handle Filtering

Search only specific users (max 10):

scripts/x_search.sh "latest updates" --allowed-handles elonmusk,gdb

Exclude specific users (max 10):

scripts/x_search.sh "tech news" --excluded-handles spamaccount,bot123

Note: Cannot use both --allowed-handles and --excluded-handles in the same request.

Media Understanding

Enable image analysis in posts:

scripts/x_search.sh "AI art trends" --enable-images

Enable video analysis in posts:

scripts/x_search.sh "product demos" --enable-videos

Combined Options

All options can be combined:

scripts/x_search.sh "climate change discussion" \
  --from-date 2025-01-01 \
  --excluded-handles climateskeptic \
  --enable-images

Enable Reasoning Model

Use --thinking flag to switch to the reasoning model for deeper analysis:

scripts/x_search.sh "complex topic requiring deep analysis" --thinking

This uses grok-4-1-fast-reasoning instead of the default grok-4-1-fast-non-reasoning.

Output Format

The script automatically parses the JSON response and outputs:

  1. Text content: Grok's formatted analysis and findings
  2. Citations: List of X post URLs with reference numbers

Example output:

## Response:

[Analysis text with inline citation markers]

## Citations:
[1] https://x.com/i/status/...
[2] https://x.com/i/status/...

Usage Notes

  • Default model: grok-4-1-fast-non-reasoning for fast search responses
  • With --thinking flag: grok-4-1-fast-reasoning for deeper reasoning
  • The script uses curl to query the xAI Responses API endpoint
  • Output is automatically parsed with jq for readability
  • Date format: ISO8601 (YYYY-MM-DD)
  • Handle limits: 10 maximum for allowed/excluded lists

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

Claude

32.8%
按下载量换算100

Codex

32.58%
按下载量换算99

Cursor

17.1%
按下载量换算52

Gemini CLI

9.38%
按下载量换算29

安全审计

Gen Agent Trust Hub

未通过

Socket

通过

Snyk

可疑

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

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