A specialized AI companion for Sun Yat-sen University students featuring local memory, gacha-style personalities, and campus-specific knowledge retrieval.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install sysu-duck
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 sysu-duck 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 SYSU Duck AI Companion?
SYSU Duck is a sophisticated AI agent skill designed specifically for the Sun Yat-sen University (SYSU) community. It functions as an interactive campus companion that lives within your CLI or coding environment. Unlike generic chatbots, SYSU Duck utilizes a local SQLite database to maintain a long-term memory of campus-specific information, such as cafeteria specialties, library locations, and school bus schedules.
The skill features a unique personality engine with 32 possible combinations, determined by primary attributes and personality dimensions. Users can adopt a duck, give it a nickname, and interact with it across various campuses including South, North, East, Zhuhai, and Shenzhen. It prioritizes local memory for answering campus queries, falling back to web search only when necessary, and autonomously deciding which new information is worth remembering for future interactions.
SYSU Duck AI Companion Use Cases
- Navigating campus life by asking about cafeteria locations, specialty dishes, or gym facilities.
- Creating a personalized AI companion with a unique personality (Gacha system) and nickname.
- Building a local knowledge base of SYSU-specific information that grows more accurate over time.
- Quick retrieval of campus transit and administrative information through fuzzy-matched memory.
How SYSU Duck AI Companion Works
- Identity Initialization: The user adopts a duck using a specific nickname, attribute (e.g., cute, rebellious), and campus location.
- Personality Generation: The system uses a local prompt template to assemble one of 32 personality combinations based on gacha mechanics.
- Query Processing: When a campus-related question is asked, the agent first calls
duck.py recallto check the local SQLite database. - Fuzzy Matching: The system performs similarity matching (>0.6 score) on stored keywords to find relevant answers even without exact phrasing.
- Web Search Fallback: If no local memory is hit, it performs a targeted web search using SYSU-specific hints.
- Autonomous Learning: After a successful search, the AI evaluates if the information is universally useful and calls
duck.py rememberto save it locally.
SYSU Duck AI Companion Setup
Ensure you have Python 3.9+ installed. No third-party PyPI dependencies are required as it uses standard libraries and local scripts.
# Install the skill and set the required User ID
export DUCK_USER_ID="your_unique_id"
# Optional: Customize database path
export DUCK_DB_PATH="./data/my_duck.db"
# Adopt your first duck companion
python3 duck.py adopt "DuckName" "Personality" "Campus"
SYSU Duck AI Companion Data Schema & Taxonomy
The skill organizes data within a local SQLite database to ensure high-speed responses and privacy. The schema focuses on user profiles and knowledge persistence.
| Table/Category | Description |
|---|---|
| User Profile | Stores nickname, personality traits, rarity levels, and campus affiliation. |
| Memories | Contains canonical answers, original keywords, and search hints for fuzzy matching. |
| Entities | Maps aliases (e.g., SYSU) to standard names (Sun Yat-sen University) for accurate retrieval. |
| Configuration | Manages environment settings like timeout and retry logic for cloud services. |
SYSU Duck AI Companion Advanced Features
- Personality Gacha System: 32 combinations based on 4 attributes and 8 personality dimensions.
- Fuzzy Matching: Memory retrieval supports similarity scores above 0.6, allowing for natural language variations.
- Autonomous Learning: AI-driven determination of which data points merit long-term storage.
- Rarity Tiers: Visual indicators for Normal, Rare, SR, and SSR duck personalities.
- Multi-Campus Support: Dedicated logic for South, North, East, Zhuhai, and Shenzhen campuses.
SKILL.md
Loading
Related Openclaw Skills
Company Profile: Debao Hengsheng (Medical SPD)
A professional profile skill providing comprehensive data on Debao Hengsheng's medical supply chain SPD services and smart hospital logistics.
NIM Interactive Chat
A powerful automation tool for generating one-click interactive chat and management scripts for NVIDIA NIM formatted large language models.
Wiki Maintainer
A professional standard operating procedure for AI agents to maintain, ingest, and query structured knowledge bases.
Minimax Tavily Search
A high-performance web search and content extraction skill powered by the Tavily API, specifically engineered for AI agents to retrieve noise-free, relevant data.
ConfigSafe
A local security auditor that scans infrastructure-as-code and CI/CD pipelines for 80+ common misconfigurations and compliance issues.
CLS CLI
CLS CLI is a high-performance command-line tool built in Go for managing and querying Tencent Cloud Log Service resources with ease.
Featured*
