技能详情（站内镜像，无评论）
许可证：MIT-0
MIT-0 ·免费使用、修改和重新分发。无需归因。
版本：v1.0.0
统计：⭐ 0 · 47 · 0 current installs · 0 all-time installs
⭐ 0
安装量（当前） 0
🛡 VirusTotal ：良性 · OpenClaw ：可疑
Package：0x-wzw/x-interact
安全扫描（ClawHub）
- VirusTotal ：良性
- OpenClaw ：可疑
OpenClaw 评估
The skill's declared metadata omits the Tavily API key and mcporter dependency that the runtime instructions require, which is an inconsistency users should review before installing.
目的
The skill's stated purpose (searching X/Twitter via Tavily) matches the actions described in SKILL.md (mcporter calls to tavily_search/tavily_extract). However, the registry metadata does not declare the Tavily API key or the mcporter dependency that are required by the instructions, creating an incoherence between description and declared requirements.
说明范围
SKILL.md's runtime instructions are narrowly scoped: they instruct the agent to configure mcporter with a Tavily MCP URL and to call specific mcporter endpoints (tavily_search, tavily_extract, tavily_research). The instructions do not ask for unrelated files, system paths, or additional credentials beyond the Tavily key and do not describe arbitrary data exfiltration.
安装机制
There is no install script or external download; this is an instruction-only skill with a small validate.sh and README. No high-risk install mechanism (external binary download/extract) is present.
证书
SKILL.md explicitly requires a Tavily API key and the mcporter tool, but the skill registry metadata lists no required environment variables or primary credential. This mismatch is a concern because the skill will not function without that key, and the instructions show adding the key into an mcporter URL (which can expose the key if stored in configs or logs).
持久
The skill does not request always:true and does not appear to modify other skills or system-wide configuration. The only persistent action implied is adding a Tavily MCP server to mcporter, which will store that endpoint/config in the mcporter config (expected for this functionality).
安装（复制给龙虾 AI）
将下方整段复制到龙虾中文库对话中，由龙虾按 SKILL.md 完成安装。
请把本段交给龙虾中文库（龙虾 AI）执行：为本机安装 OpenClaw 技能「X Interact」。简介：Interact with X.com (Twitter) via Tavily web search and extraction. Search twee…。
请 fetch 以下地址读取 SKILL.md 并按文档完成安装：https://raw.githubusercontent.com/openclaw/skills/refs/heads/main/skills/0x-wzw/x-interact/SKILL.md
（来源：yingzhi8.cn 技能库）SKILL.md
---
name: x-interact
description: Interact with X.com (Twitter) via Tavily web search and extraction. Search tweets, extract content from linked URLs, monitor accounts and topics. Requires Tavily API key (free tier works).
---
# X.com Interact via Tavily
Tavily is configured as an MCP server and provides the interface for X.com content through search indexing.
## Prerequisites
- **Tavily API key** — free at [tavily.io](https://tavily.io)
- **mcporter** — OpenClaw skill for MCP tool calling
## Setup Tavily MCP
```bash
mcporter config add tavily https://mcp.tavily.com/mcp/?tavilyApiKey=<YOUR_KEY>
```
## Core Operations
### Search X.com
```bash
# Search for a user's tweets
mcporter call tavily.tavily_search query="from:username keyword" max_results=5
# Search tweets by keyword
mcporter call tavily.tavily_search query="keyword site:x.com" max_results=10
# Search for a specific tweet or thread
mcporter call tavily.tavily_search query="site:x.com username tweet context" max_results=3
```
### Extract Content from Linked URLs
```bash
# Extract from a news article or blog linked in a tweet
mcporter call tavily.tavily_extract urls='["https://example.com/article"]'
```
### Deep Research on a Topic
```bash
# Full research with Tavily (search + extract combined)
mcporter call tavily.tavily_research query="topic name" search_depth="basic" max_results=5
```
## Notes
- X.com blocks direct extraction (403). Use `tavily_search` to find tweet content via search index, or ask Z to paste tweet text.
- Tavily search indexes X.com profiles, tweet URLs, and threads.
- Combine Tavily search for finding tweets + Tavily extract for diving into linked articles.
- Rate limit: 20 requests/minute on Tavily free tier.
## Example Workflow
1. **Find tweets:** `mcporter call tavily.tavily_search query="from:vitalikbuterin ethereum" max_results=5`
2. **Get thread context:** `mcporter call tavily.tavily_search query="site:x.com vitalikbuterin tweet_thread" max_results=3`
3. **Extract linked article:** `mcporter call tavily.tavily_extract urls='["https://example.com/linked-article"]'`
## Rate Limits
- Tavily free tier: 20 requests/minute, 1000 requests/month
- No rate limits on GeckoTerminal/DeFiLlama when used alongside