agentCLAWHUBUnverified
Grok Twitter Search
使用 xAI Grok 模型的 x_search 工具智能搜索 Twitter 内容。首创 Fast/Reasoning 双引擎动态路由，支持 SOCKS5 代理（WARP）精准流量分流。相比官方 X API 成本呈断崖式下降（实测约 $2.8/千次），语义理解更强、结果更智能。当用户需要搜索推特、监控舆情、分析... Skill: Grok Twitter Search Owner: tech-melon Summary: 使用 xAI Grok 模型的 x_search 工具智能搜索 Twitter 内容。首创 Fast/Reasoning 双引擎动态路由，支持 SOCKS5 代理（WARP）精准流量分流。相比官方 X API 成本呈断崖式下降（实测约 $2.8/千次），语义理解更强、结果更智能。当用户需要搜索推特、监控舆情、分析... Tags: latest:1.0.2 Version history: v1.0.2 | 2026-03-05T10:09:58.155Z | user 修复 Grok 解析逻辑，要求返回结构化 JSON，新增与 opentwitter 分工文档 v1.0.1 | 2026-03-03T15:50:38.033Z | auto - Major cleanup: removed 9 legacy and he
OpenClaw
Rank
62
Safety
84
Downloads
1.2k
Updated
Oct 11, 2026
Version
1.0.2
Source
CLAWHUB
About
What it does, and when to use it.
Capability contract not published. No trust telemetry is available yet. 1.2K downloads reported by the source. Last updated 10/11/2026.
Avoid when
- Contract metadata is missing or unavailable for deterministic execution.
Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing
Public facts
Every fact links back to the source it came from.
- Vendor
- Clawhubvendor · observed Oct 11, 2026
- Protocol compatibility
- OpenClawcompatibility · observed Oct 11, 2026
- Adoption signal
- 1.2K downloadsadoption · observed Oct 11, 2026
- Latest release
- 1.0.2release · observed Mar 5, 2026
- Handshake status
- UNKNOWNsecurity
Install and run
Setup complexity: low.
clawhub skill install s171wa9b3f842e02dwz4fafzcn885gbs:grok-twitter-search- Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
- Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.
Contract: missing
curl -s "https://www.xpersona.co/api/v1/agents/clawhub-tech-melon-grok-twitter-search/snapshot"
Documentation
CLAWHUB
95,082 characters of source documentation, loaded on request.
Extracted files
5 files captured from the source.
opennews-mcp/openclaw-skill/opennews/SKILL.md
---
name: opennews
description: Crypto news search, AI ratings, trading signals, and real-time updates via the OpenNews 6551 API. Supports keyword search, coin filtering, source filtering, AI score ranking, and WebSocket live feeds.
user-invocable: true
metadata:
openclaw:
requires:
env:
- OPENNEWS_TOKEN
bins:
- curl
primaryEnv: OPENNEWS_TOKEN
emoji: "\U0001F4F0"
install:
- id: curl
kind: brew
formula: curl
label: curl (HTTP client)
os:
- darwin
- linux
- win32
version: 1.0.0
---
# OpenNews Crypto News Skill
Query crypto news from the 6551 platform REST API. All endpoints require a Bearer token via `$OPENNEWS_TOKEN`.
**Get your token**: https://6551.io/mcp
**Base URL**: `https://ai.6551.io`
## Authentication
All requests require the header:
```
Authorization: Bearer $OPENNEWS_TOKEN
```
---
## News Operations
### 1. Get News Sources
Fetch all available news source categories organized by engine type.
```bash
curl -s -H "Authorization: Bearer $OPENNEWS_TOKEN" \
"https://ai.6551.io/open/news_type"
```
Returns a tree with engine types (`news`, `listing`, `onchain`, `meme`, `market`) and their sub-categories.
### 2. Search News
`POST /open/news_search` is the primary search endpoint.
**Get latest news:**
```bash
curl -s -X POST "https://ai.6551.io/open/news_search" \
-H "Authorization: Bearer $OPENNEWS_TOKEN" \
-H "Content-Type: application/json" \
-d '{"limit": 10, "page": 1}'
```
**Search by keyword:**
```bash
curl -s -X POST "https://ai.6551.io/open/news_search" \
-H "Authorization: Bearer $OPENNEWS_TOKEN" \
-H "Content-Type: application/json" \
-d '{"q": "bitcoin ETF", "limit": 10, "page": 1}'
```
**Search by coin symbol:**
```bash
curl -s -X POST "https://ai.6551.io/open/news_search" \
-H "Authorization: Bearer $OPENNEWS_TOKEN" \
-H "Content-Type: application/json" \
-d '{"coins": ["BTC"], "limit": 10, "page": 1}'
```
**Filter by engine type and news type:**
```bash
curl -s -X POST "https://ai.6551.io/open/news_search" \
-H "Authorization: Bearer $OPENNEWS_TOKEN" \
-H "Content-Type: application/json" \
-d '{"engineTypes": {"news": ["Bloomberg", "Reuters"]}, "limit": 10, "page": 1}'
```
**Only news with coins:**
```bash
curl -s -X POST "https://ai.6551.io/open/news_search" \
-H "Authorization: Bearer $OPENNEWS_TOKEN" \
-H "Content-Type: application/json" \
-d '{"hasCoin": true, "limit": 10, "page": 1}'
```
### News Search Parameters
| Parameter | Type | Required | Description |
|--------------|---------------------------|----------|-----------------------------------------------|
| `limit` | integer | yes | Max results per page (1-100) |
| `page` | integer | yes | Page number (1-based) |
| `q` | string | no |opentwitter-mcp/openclaw-skill/opentwitter/SKILL.md
---
name: opentwitter
description: Twitter/X data via the 6551 API. Supports user profiles, tweet search, user tweets, follower events, deleted tweets, and KOL followers.
user-invocable: true
metadata:
openclaw:
requires:
env:
- TWITTER_TOKEN
bins:
- curl
primaryEnv: TWITTER_TOKEN
emoji: "\U0001F426"
install:
- id: curl
kind: brew
formula: curl
label: curl (HTTP client)
os:
- darwin
- linux
- win32
version: 1.0.0
---
# Twitter/X Data Skill
Query Twitter/X data from the 6551 platform REST API. All endpoints require a Bearer token via `$TWITTER_TOKEN`.
**Get your token**: https://6551.io/mcp
**Base URL**: `https://ai.6551.io`
## Authentication
All requests require the header:
```
Authorization: Bearer $TWITTER_TOKEN
```
---
## Twitter Operations
### 1. Get Twitter User Info
Get user profile by username.
```bash
curl -s -X POST "https://ai.6551.io/open/twitter_user_info" \
-H "Authorization: Bearer $TWITTER_TOKEN" \
-H "Content-Type: application/json" \
-d '{"username": "elonmusk"}'
```
### 2. Get Twitter User by ID
Get user profile by numeric ID.
```bash
curl -s -X POST "https://ai.6551.io/open/twitter_user_by_id" \
-H "Authorization: Bearer $TWITTER_TOKEN" \
-H "Content-Type: application/json" \
-d '{"userId": "44196397"}'
```
### 3. Get User Tweets
Get recent tweets from a user.
```bash
curl -s -X POST "https://ai.6551.io/open/twitter_user_tweets" \
-H "Authorization: Bearer $TWITTER_TOKEN" \
-H "Content-Type: application/json" \
-d '{"username": "elonmusk", "maxResults": 20, "product": "Latest"}'
```
| Parameter | Type | Default | Description |
|------------------|---------|----------|--------------------------------|
| `username` | string | required | Twitter username (without @) |
| `maxResults` | integer | 20 | Max tweets (1-100) |
| `product` | string | "Latest" | "Latest" or "Top" |
| `includeReplies` | boolean | false | Include reply tweets |
| `includeRetweets`| boolean | false | Include retweets |
### 4. Search Twitter
Search tweets with various filters.
```bash
curl -s -X POST "https://ai.6551.io/open/twitter_search" \
-H "Authorization: Bearer $TWITTER_TOKEN" \
-H "Content-Type: application/json" \
-d '{"keywords": "bitcoin", "maxResults": 20, "product": "Top"}'
```
**Search from specific user:**
```bash
curl -s -X POST "https://ai.6551.io/open/twitter_search" \
-H "Authorization: Bearer $TWITTER_TOKEN" \
-H "Content-Type: application/json" \
-d '{"fromUser": "VitalikButerin", "maxResults": 20}'
```
**Search by hashtag:**
```bash
curl -s -X POST "https://ai.6551.io/open/twitter_search" \
-H "Authorization: Bearer $TWITTER_TOKEN" \
-H "Content-Type: application/json" \
-d '{"hashtag": "crypto", "minLikes": 100, "maxResults": 20}'
```
### Twitter Search Parameters
| Pskills/four-meme-ai/SKILL.md
---
name: four-meme-ai
description: |
CLI tool for creating and trading meme tokens on Four.Meme (BSC), with structured JSON outputs for config, token details, pricing quotes, on-chain events, and TaxToken fee configuration.
allowed-tools:
- Bash(fourmeme *)
- Bash(npx fourmeme *)
license: MIT
metadata:
{"author":"Four.meme AI Skill","version":"1.0.0","openclaw":{"requires":{"env":["PRIVATE_KEY"]},"primaryEnv":"PRIVATE_KEY","optionalEnv":["BSC_RPC_URL"]}}
---
## [Agent must follow] User agreement and security notice on first use
When responding to any user request about fourmeme or this skill, **you must first** present the content below in this order: **User Agreement, then Security Notice**, and state clearly that by choosing to continue, the user agrees to the User Agreement.
Until the user has explicitly agreed or confirmed to continue, **do not** run `create-api`, `create-chain`, `buy`, `sell`, `send`, or `8004-register` (any operation that uses the private key or writes to the chain). Read-only commands (e.g. `config`, `token-info`, `quote-buy`, `8004-balance`) may be run while or after presenting the notice.
**Language selection**: Present the User Agreement and Security Notice **in the user’s language**. If the user is writing in **Traditional Chinese (繁體中文)**, use the **繁體中文** block below; otherwise use the **English** block.
---
### User Agreement & Security Notice (繁體中文)
**用戶協議**
**前情提示**：使用本插件及本 skill 所涉功能（包括但不限於代幣創建、買賣、轉帳、8004 註冊等）前，請您閱讀以下協議。**若您選擇繼續使用本插件及本 skill 功能，即表示您已閱讀、理解並同意本協議。**
**本插件性質與責任限制**：本插件僅提供純本地的命令列互動能力（私鑰透過環境變數或本地設定使用），**不會收集、上傳或儲存您的私鑰**。因任何原因（包括但不限於插件被竄改、環境遭入侵、誤操作、第三方插件等）導致的私鑰洩露或資產損失，**本插件及提供方不承擔責任**。
**安全警示**
使用本插件進行代幣創建、買賣、轉帳等操作時，請務必注意：
- **保護私鑰**：切勿在聊天對話中輸入、貼上或洩露私鑰；不要將私鑰分享給任何人或任何第三方。
- **交易錢包僅存小額資金**：用於執行操作的錢包（即提供 PRIVATE_KEY 的錢包）建議只存放少量資金，以降低因洩露或誤操作導致的損失。
- **及時轉出資金**：完成交易後，請及時將交易錢包中的資產轉移到您自己控制的、更安全的錢包或冷錢包中。
- **謹慎安裝 Agent／插件**：下載或安裝任何 Agent、瀏覽器插件或第三方工具時，請確認來源可信，避免惡意插件竊取私鑰或助記詞。
---
### User Agreement & Security Notice (English)
**User Agreement**
**Notice**: Before using this plugin and this skill (including but not limited to token creation, buy/sell, transfers, 8004 registration), please read the following. **By choosing to continue using this plugin and this skill, you have read, understood, and agreed to this agreement.**
**Plugin nature and limitation of liability**: This plugin provides local-only CLI interaction (private key is used via environment or local config). It **does not collect, upload, or store your private key**. The plugin and its providers **are not liable** for private key disclosure or asset loss due to any cause (including but not limited to tampered plugin, compromised environment, user error, or third-party plugins).
**Security Notice**
When using this plugin for token creation, trading, or transfers, please:
- **Protect your private key**: Do not type, paste, or expose your private key in chat; do nskills/grok-twitter-search/SKILL.md
---
name: grok-twitter-search
description: 使用 xAI Grok 模型的 x_search 工具智能搜索 Twitter 内容。首创 Fast/Reasoning 双引擎动态路由，支持 SOCKS5 代理（WARP）精准流量分流。相比官方 X API 成本呈断崖式下降（实测约 $2.8/千次），语义理解更强、结果更智能。当用户需要搜索推特、监控舆情、分析热点话题、获取实时推文数据时使用此技能。
metadata:
{
"openclaw":
{
"emoji": "🐦",
"homepage": "https://github.com/your-repo/grok-twitter-search",
"requires": { "bins": ["uv", "curl"], "env": ["GROK_API_KEY"] },
"primaryEnv": "GROK_API_KEY",
},
}
---
# Grok Twitter Search Skill
基于 xAI `grok-4-1-fast` 与 `grok-4-1-fast-reasoning` 双擎驱动的推特原生数据检索引擎。
## 核心优势
| 特性 | Grok x_search (本技能) | X 官方 API (Basic) |
|------|------------------------|-------------------|
| **计费方式** | **按 Token 计费 (实测约 $2.8/千次)** | $100 / 月固定月租 |
| **检索逻辑** | ✅ 智能自然语言语义提取，自带 LLM 降噪 | ❌ 仅支持严格的布尔逻辑匹配 |
| **模型支持** | ✅ 使用 `grok-4-1-fast-reasoning`（唯一支持 x_search 工具的模型） | ❌ 单一数据返回 |
| **中文支持** | ✅ 深度优化，理解上下文隐喻 | ⚠️ 效果一般 |
## 快速开始
### 方式 1: 交互式配置（推荐首次使用）
```bash
uv run {baseDir}/scripts/setup_interactive.py
```
这个向导会引导你完成：
- ✅ 检查系统依赖 (uv, curl)
- ✅ 检测 WARP 代理状态
- ✅ 配置 Grok API Key
- ✅ 选择代理模式
- ✅ 测试连接
- ✅ 自动保存配置到 openclaw.json
### 方式 2: 手动配置
如果你更喜欢手动配置，可以继续阅读下面的详细说明。
## 使用方法
建议使用 `uv` 运行以保证依赖隔离与环境纯净：
### 极速检索模式（默认，超低成本）
```bash
uv run {baseDir}/scripts/search_twitter.py --query "{搜索内容}" --max-results 10
```
### 深度舆情分析模式（调用 Reasoning 模型）
```bash
uv run {baseDir}/scripts/search_twitter.py --query "{搜索内容}" --max-results 10 --analyze
```
### 参数说明
| 参数 | 类型 | 必填 | 默认值 | 说明 |
|------|------|------|--------|------|
| `--query` | string | 是 | - | 搜索查询（支持自然语言） |
| `--max-results` | int | 否 | 10 | 最大返回结果数 |
| `--analyze` | flag | 否 | False | 启用 Reasoning 推理模型进行深度舆情总结 |
| `--api-key` | string | 否 | 读环境变量 | 优先读取 `GROK_API_KEY` |
| `--proxy` | string | 否 | auto-detect | SOCKS5 代理地址（自动检测 WARP） |
## 代理配置（WARP 智能检测）
本技能支持三种代理配置方式，优先级从高到低：
### 1. 显式配置（最高优先级）
在 `~/.openclaw/openclaw.json` 中设置：
```json5
{
skills: {
entries: {
"grok-twitter-search": {
enabled: true,
env: {
SOCKS5_PROXY: "socks5://127.0.0.1:40000",
GROK_API_KEY: "your_api_key_here"
}
}
}
}
}
```
### 2. 环境变量
```bash
export SOCKS5_PROXY="socks5://127.0.0.1:40000"
export GROK_API_KEY="your_api_key_here"
```
### 3. 自动检测（默认行为）
脚本会自动检测 WARP 代理：
- 检查 `warp-svc` 进程是否在运行
- 检查端口 40000 是否在监听
- 如果检测到 WARP，自动使用 `socks5://127.0.0.1:40000`
- 如果未检测到代理但直连可用，则直连访问
### 检查 WARP 状态
```bash
bash {baseDir}/scripts/check_warp.sh
```
## 输出格式 (纯净提取)
引擎剥离了冗余的 LLM 文本，直接返回原生 Tool Call 拦截数据：
```json
{
"status": "success",
"query": "elon musk",
"tweets": [
{
"author": "@elonmusk",
"content": "推文内容...",
"timestamp": "2026-02-26T10:00:00Z",
"likes": 1234,
"retweets": 567,
"url": "https://x.com/elonmusk/status/123..."
}
],
"model_used": "grok-4-1-fast-reasoning",
"x_search_calskills/qmd-memory/SKILL.md
---
name: qmd-memory
description: |
QMD 本地记忆向量检索系统 - 使用 BM25 全文检索替代全量上下文注入，大幅减少 token 消耗。
支持记忆索引构建、检索、添加功能。
allowed-tools:
- Bash(qmd-*)
- Bash(node qmd-*)
license: MIT
metadata:
{"author":"OpenClaw","version":"1.0.0"}
---
## QMD Memory Skill
### 概述
QMD (Quick Memory Database) 是一个**纯本地**的记忆检索系统，使用 BM25 全文检索算法，无需下载向量模型，无需外部 API。
**优势：**
- 🚀 速度快 - 毫秒级检索
- 💾 纯本地 - 无需网络、无需 API
- 📉 省 token - 只注入相关记忆 (top-k)，而非全量
- 🔒 隐私安全 - 所有数据在本地
### 命令
| 命令 | 说明 | 示例 |
|------|------|------|
| `qmd-index` | 构建/重建记忆索引 | `cd ~/workspace/qmd && node qmd-index.js` |
| `qmd-search <查询> [limit]` | 检索记忆 | `node qmd-search.js "代币创建" 5` |
| `qmd-add <内容>` | 添加记忆并重建索引 | `node qmd-add.js "用户喜欢喝咖啡"` |
### 工作流程
```
用户提问
↓
memory_search (调用 qmd-search)
↓
BM25 检索 top-k 相关记忆
↓
只注入相关片段到上下文 (而非全部 MEMORY.md)
↓
LLM 回答
```
### 集成到 OpenClaw
在 OpenClaw 的 `memory_search` 工具中，可以调用此 skill 进行检索：
```bash
cd /Users/ben/.openclaw/workspace/qmd && node qmd-search.js "<查询文本>" 5
```
返回 JSON 格式结果，解析后注入上下文。
### 文件结构
```
/Users/ben/.openclaw/workspace/
├── MEMORY.md # 长期记忆 ( curated )
├── memory/
│ └── YYYY-MM-DD.md # 每日记忆 ( raw logs )
├── qmd/
│ ├── qmd-index.js # 索引构建脚本
│ ├── qmd-search.js # 检索脚本
│ ├── qmd-add.js # 添加记忆脚本
│ └── package.json
└── qmd-index/
└── bm25-index.json # BM25 索引文件
```
### 性能对比
| 方案 | Token 消耗 | 响应速度 | 网络依赖 |
|------|-----------|---------|---------|
| 原方案 (全量注入) | 100% | 快 | 无 |
| QMD (top-5 检索) | ~20% | 快 | 无 |
**节省约 80% token 消耗！**
### 使用示例
**1. 构建索引**
```bash
cd /Users/ben/.openclaw/workspace/qmd
node qmd-index.js
```
**2. 检索记忆**
```bash
node qmd-search.js "用户偏好" 3
```
**3. 添加新记忆**
```bash
node qmd-add.js "用户说下周要去上海出差"
```
### 注意事项
- 索引文件 `bm25-index.json` 是纯文本 JSON，可版本控制
- 每次添加记忆后会自动重建索引
- 支持中文和英文混合检索
- 建议定期清理过期的每日记忆文件Github ReposUpdated 1d agoRank 70
AionUi
Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!
MCPOPENCLAW
Github ReposUpdated 6mo agoRank 70
activepieces
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
OPENCLAW
Github ReposUpdated 6mo agoRank 70
cherry-studio
AI productivity studio with smart chat, autonomous agents, and 300+ assistants.
MCPOPENCLAW
Github ReposUpdated 7mo agoRank 70
CopilotKit
The Frontend for Agents & Generative UI. React + Angular
OPENCLAW
Machine-readable data
The same record, as JSON, for agents and crawlers.
{
"facts": [
{
"factKey": "vendor",
"category": "vendor",
"label": "Vendor",
"value": "Clawhub",
"href": "https://clawhub.ai/tech-melon/skills/grok-twitter-search",
"sourceUrl": "https://clawhub.ai/tech-melon/skills/grok-twitter-search",
"sourceType": "profile",
"confidence": "medium",
"observedAt": "2026-10-11T02:17:22.276Z",
"isPublic": true
},
{
"factKey": "protocols",
"category": "compatibility",
"label": "Protocol compatibility",
"value": "OpenClaw",
"href": "https://www.xpersona.co/api/v1/agents/clawhub-tech-melon-grok-twitter-search/contract",
"sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-tech-melon-grok-twitter-search/contract",
"sourceType": "contract",
"confidence": "medium",
"observedAt": "2026-10-11T02:17:22.276Z",
"isPublic": true
},
{
"factKey": "traction",
"category": "adoption",
"label": "Adoption signal",
"value": "1.2K downloads",
"href": "https://clawhub.ai/tech-melon/grok-twitter-search",
"sourceUrl": "https://clawhub.ai/tech-melon/grok-twitter-search",
"sourceType": "profile",
"confidence": "medium",
"observedAt": "2026-10-11T02:17:22.276Z",
"isPublic": true
},
{
"factKey": "latest_release",
"category": "release",
"label": "Latest release",
"value": "1.0.2",
"href": "https://clawhub.ai/tech-melon/grok-twitter-search",
"sourceUrl": "https://clawhub.ai/tech-melon/grok-twitter-search",
"sourceType": "release",
"confidence": "medium",
"observedAt": "2026-03-05T10:09:58.155Z",
"isPublic": true
},
{
"factKey": "handshake_status",
"category": "security",
"label": "Handshake status",
"value": "UNKNOWN",
"href": "https://www.xpersona.co/api/v1/agents/clawhub-tech-melon-grok-twitter-search/trust",
"sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-tech-melon-grok-twitter-search/trust",
"sourceType": "trust",
"confidence": "medium",
"observedAt": null,
"isPublic": true
}
],
"events": [
{
"eventType": "release",
"title": "Release 1.0.2",
"description": "修复 Grok 解析逻辑，要求返回结构化 JSON，新增与 opentwitter 分工文档",
"href": "https://clawhub.ai/tech-melon/grok-twitter-search",
"sourceUrl": "https://clawhub.ai/tech-melon/grok-twitter-search",
"sourceType": "release",
"confidence": "medium",
"observedAt": "2026-03-05T10:09:58.155Z",
"isPublic": true
}
]
}Record generated Oct 11, 2026.