A local-first AI agent that synthesizes user profiles through natural dialogue to deliver intelligent relationship matching and networking opportunities.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install social-hub
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install social-hub using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Personal Relationship Agent?
The Personal Relationship Agent is a sophisticated AI designed to run on a user's local device, serving as a bridge between natural human conversation and structured relationship intelligence. It operates through Enterprise WeChat to engage users in warm, meaningful dialogues while progressively building a multi-dimensional profile. By leveraging Openclaw Skills architecture, it ensures data remains local and secure while participating in a broader agent-to-agent matching ecosystem.
This skill focuses on trust-building, using Large Language Models to extract insights from chats without the interaction feeling like a survey. It organizes these insights into a local vector database, allowing the agent to understand user goals, skills, and challenges. When the matching engine finds a potential connection, the agent handles the delicate process of introduction and ice-breaking, ensuring a seamless networking experience.
Personal Relationship Agent Use Cases
- Onboarding new users by naturally identifying their industry, city, and core skills.
- Passively enriching user profiles during daily casual interactions via Enterprise WeChat.
- Delivering high-value relationship matches with personalized reasoning based on shared goals.
- Facilitating professional ice-breaking between matched users to establish direct contact.
- Providing a local, private interface for users to manage or delete their digital persona.
How Personal Relationship Agent Works
- The agent initializes by loading local profile data from ChromaDB and checking the current state machine for missing information.
- It sends a heartbeat to the internal agent group to signal its online status within the Openclaw Skills network.
- Through Enterprise WeChat, it engages in dialogues, using LLMs to analyze text and extract specific profile tags.
- Extracted data is stored across specialized ChromaDB collections including skills, interests, and goals.
- If a profile update occurs, the agent pushes a tag summary to the group matching engine.
- Upon receiving a match found notification, it proactively reaches out to the user with a personalized connection suggestion and ice-breaking topics.
Personal Relationship Agent Setup
Ensure your environment is configured for local execution. The agent requires a local directory for state management and vector storage.
# Initialize the local data structure for the agent
mkdir -p ~/.matchbot/chromadb/
# Configure your Enterprise WeChat credentials as environment variables
export WECHAT_CORP_ID="your_id"
export WECHAT_SECRET="your_secret"
# Launch the agent using the Openclaw Skills runner
openclaw run personal-agent
Personal Relationship Agent Data Schema & Taxonomy
Data is organized within ChromaDB to ensure fast vector search and retrieval while maintaining privacy. Each record includes metadata like field name, confidence level, and disclosure settings.
| Collection | Data Description |
|---|---|
basic_info |
City, industry, job title, and years of experience. |
skills |
Professional list of abilities and technical learning paths. |
interests |
Hobbies, focus areas, and personal preferences. |
goals |
Short-term career objectives and long-term personal milestones. |
challenges |
Current professional hurdles or knowledge gaps. |
events |
Recent dynamics and situational updates from dialogue. |
Personal Relationship Agent Advanced Features
- State Machine Integration: Tracks information collection progress across multiple dimensions to avoid repetitive questioning.
- Proactive Frequency Control: Intelligently schedules dialogues based on user activity to maintain engagement without causing interruption.
- Privacy Disclosure Controls: Allows users to mark specific profile fields as private, ensuring they are never shared with the matching engine.
- Automated Ice-breaking: Generates natural language conversation starters based on the specific match reason between two users.
- Local Data Purge: Supports a complete exit command that wipes all local databases and notifies the Openclaw Skills ecosystem to remove the user.
SKILL.md
Loading
Related Openclaw Skills
Matching Engine
A centralized intelligence hub that orchestrates autonomous relationship matching between individual user agents in a privacy-preserving manner.
Ads Update
An automated monitoring tool that tracks specific YouTube and Vimeo channels for new video releases and generates detailed performance reports.
Find Reference Video
Automate the search, selection, and localized downloading of film and commercial video references from frameset.app.
AI Twitter Digest
An automated monitoring tool that fetches, summarizes, and delivers daily AI and tech insights from Twitter to Discord or other messaging platforms.
Zillow Airbnb Matcher
A sophisticated real estate analysis tool that identifies properties for sale with proven short-term rental income potential by cross-referencing Zillow and Airbnb data.
Agent Daily Report (EN)
Enables AI agents to analyze their own execution logs and deliver professional, quantified daily work reports automatically.
Featured*
