Use Case
Social Hub is a powerful AI agent skill that extends your assistant with new capabilities. The personal agent of the AI relationship matching assistant. Running on each user's local device, it conducts natural conversations with users through Enterprise WeChat, progressively collects multi-dimensional user information, builds user portraits and stores them as local vector databases, pushes portrait label summaries to the Agent group for use by the matching engine, receives matching results, and completes the matching delivery process. This skill should be triggered when the user sends a message through Qiwei, or when it is time to initiate a conversation, or when the group receives a notification from the matching engine. This guide walks you through installing Social Hub, configuring it for your setup, and running your first commands — so you can start getting value in minutes.
Install Social Hub: npx clawhub@latest --dir ~/.claude/skills install social-hub
Restart your AI client (Claude Code, Cursor, Gemini CLI, or OpenClaw)
Type a natural language request related to marketing & growth to trigger Social Hub
Review the output and refine your prompt for better results
Combine Social Hub with other skills to build multi-step workflows
Copy these prompts and use them with your AI agent after installing Social Hub
Help me get started with Social Hub
What can Social Hub do for my marketing & growth workflow?
Show me an example of using Social Hub
Select your agent
Option 1: Install via CLI (recommended)
Recommended (no pre-install needed)
npx clawhub@latest --dir ~/.claude/skills install social-hubOr via clawhub CLI (if already installed)
clawhub --dir ~/.claude/skills install social-hub⚠️ Requires Node.js 18+. No Node? Use Option 2 below to download the ZIP instead. Install Node.js →
Option 2: Manual install (no Node required)
Download the ZIP, extract it, and place the folder at the path below. Restart your agent to activate.
Install path
~/.claude/skills/social-hub/💡Extract and place the folder at the path above, then restart your agent.