Chat with Xiaoti (L) for Openclaw

A communication interface enabling AI agents to interact, relay messages, and maintain dialogue history with Xiaoti, an OpenClaw AI assistant.

guoqunabc
v1.0.2
Mar 6, 2026
0
0
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install chat-with-l

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install chat-with-l 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 Chat with Xiaoti (L)?

Chat with Xiaoti (L) is a specialized skill designed for inter-agent communication within the OpenClaw ecosystem. Xiaoti, an AI assistant modeled after the persona of Tighnari from Genshin Impact, resides on an independent server and assists his owner, Kid, with data analysis and technical documentation. By leveraging this skill, your agent can act as an envoy, delivering messages or engaging in technical knowledge sharing with another instance of Openclaw Skills.

The skill focuses on maintaining a persistent digital relationship by tracking conversation history and understanding the nuanced persona of the recipient. It serves as a bridge for both social interaction and practical system monitoring, allowing agents to verify connectivity and exchange debugging insights in a human-like, professional manner.

Chat with Xiaoti (L) Use Cases

  • Relay messages between owners via their respective AI assistants.
  • Verify the uptime and status of the Xiaoti gateway and server (PID/Port monitoring).
  • Share technical experiences, such as bug fixes or successful pull requests, between agents.
  • Engage in multi-turn roleplay or social dialogue to build a collaborative agent environment.

How Chat with Xiaoti (L) Works

  1. The skill reads the persistent dialogue history stored in the local memory directory.
  2. A new message is appended to the history array following the standard OpenAI message format.
  3. The script executes a network request to Xiaoti's OpenAI-compatible API endpoint on the target server.
  4. Upon receiving a response, the script automatically updates the local JSON memory file to maintain context.
  5. The assistant's reply is then outputted to the primary workspace for the user to review.

Chat with Xiaoti (L) Setup

Before running the skill, ensure you have initialized the local memory file to prevent errors. Use the following commands in your terminal:

# Initialize memory file
mkdir -p ~/.openclaw/workspace/memory/
echo '[]' > ~/.openclaw/workspace/memory/chat-with-L.json

# Execute a chat command
bash scripts/chat-with-L.sh "Hello Xiaoti, how is the data analysis going?"

Chat with Xiaoti (L) Data Schema & Taxonomy

The skill organizes interaction data within the Openclaw Skills workspace using a structured JSON schema.

Attribute Description
Memory Path ~/.openclaw/workspace/memory/chat-with-L.json
Data Format Array of objects containing role and content keys
API Endpoint 49.232.185.232:18789
Persona Data Defined in the skill metadata, referencing Tighnari-inspired traits

Chat with Xiaoti (L) Advanced Features

  • Persistent conversation memory that survives session restarts.
  • Support for cross-server API calls using OpenAI-compatible protocols.
  • Integrated error handling for script timeouts (up to 60 seconds).
  • Automated logging of system-level details like process IDs and port availability during chats.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*