A sophisticated tool for generating synthetic, multi-agent group chat records in Excel format for model training and simulation.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install chat-gene
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 chat-gene 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 Record Generator?
The Chat Record Generator is a technical skill designed to synthesize realistic WeChat group chat logs from scratch. By utilizing a multi-agent framework, it generates comprehensive .xlsx files containing group metadata, member profiles, and chronological message streams. This utility is perfectly compatible with training data formats for various AI platforms, making it an essential part of the Openclaw Skills ecosystem for developers who need high-quality synthetic datasets.
The skill focuses on structural integrity and conversational realism. It allows users to define specific group dynamics, including member count, AI assistant personas, and discussion topics. By simulating distinct linguistic styles and professional backgrounds for each participant, it creates a rich dataset that mirrors human interaction patterns in digital communication channels.
Chat Record Generator Use Cases
- Generating synthetic training datasets for conversational AI and group-chat-based assistants.
- Testing and benchmarking group chat FAQ systems and RAG-based knowledge bases.
- Simulating and visualizing multi-agent workflows for research and development.
- Creating sample datasets for social media analytics or behavioral studies without using sensitive private data.
How Chat Record Generator Works
- Group Definition: The user defines group parameters such as name, ID, member count (5-15), and specific topics of discussion.
- Multi-Agent Spawning: The system utilizes Openclaw Skills to spawn up to 5 concurrent subagents, each representing a unique group participant.
- Content Generation: Each subagent generates a set number of messages (based on a total goal of 50-200) according to their assigned persona, style, and professional background.
- Message Orchestration: The main agent collects JSON outputs from all subagents, ensuring messages align with the designated topics and flow naturally.
- Temporal Calculation: Logical time intervals are applied, with approximately 3-minute gaps between messages and 1-2 hour gaps between major topics.
- Data Serialization: The final dataset is processed through a Node.js script and written into a multi-sheet Excel file with specific cell formatting.
Chat Record Generator Setup
To use this skill, ensure Node.js is installed along with the xlsx library. You can set up the environment using the following commands:
mkdir -p /tmp/xlsxparse && cd /tmp/xlsxparse && npm install xlsx
Generate the initial group definition structure using the provided script:
node scripts/generate_group_def.js
Finally, execute the writing script after the agents have generated the conversation content:
node scripts/write_xlsx.js
Chat Record Generator Data Schema & Taxonomy
The skill generates a single Excel (.xlsx) file containing three mandatory sheets organized as follows:
| Sheet Name | Description | Mandatory Fields |
|---|---|---|
| group_info | Metadata about the simulated group | group_name, group_id, bot_config, task_list |
| active_members | Detailed profiles of all chat participants | nickname, age, profession, style_description |
| message_stream | Chronological log of all interactions | topic, sender, content, attachment, timestamp |
Technical notes on data integrity:
- Timestamps: Follow the Excel epoch (1899-12-30) and use
yyyy/m/d h:mmformatting. - Message Types: Supports 'text' (content required) and 'image/file' (content null, attachment specified).
- Constraints: The
task_listandbot_configcolumns are maintained as null to ensure compatibility with standard Openclaw Skills data importers.
Chat Record Generator Advanced Features
- Concurrent Subagent Execution: Efficiently handles high-volume data generation by parallelizing the roleplay tasks of up to 5 agents.
- Precision Temporal Formatting: Manually sets cell 'z' properties to overcome the aoa_to_sheet numFmt bug, ensuring timestamps are parsed correctly by downstream tools.
- Persona-Driven Conversations: Supports advanced prompt templates that force subagents to adhere to specific personas like 'Active Members' or 'Topic Starters'.
- Custom Attachment Simulation: Generates synthetic file and image references within the message stream to test multimodal data handling.
SKILL.md
Loading
Related Openclaw Skills
Datayes Macro
A professional-grade interface for querying Datayes and Tonglian macro-economic and industry indicators.
ClawTrace
A diagnostic utility that analyzes OpenClaw logs and session context to generate detailed performance reports and optimization insights.
Image Prompt Engineer
A technical prompt engineering framework designed to translate visual concepts into high-precision technical instructions for AI image generators.
Skill Evaluator SRL
An automated auditing tool that evaluates the reliability and engineering quality of AI agent skills using the SRL framework.
Top Coding Models
A dynamic analytical tool that cross-references BenchLM coding leaderboards with OpenRouter pricing to identify the best AI models for software development.
Teacher Lesson Plans & Assessment Generator
A comprehensive pedagogical assistant for UK teachers to generate curriculum-aligned lesson plans, worksheets, and student reports.
Featured*
