← Back to Skills Marketplace
260
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install data-generator-waai
Description
Data Generator / 数据生成器 - Generate training data from user instructions. Input: tool name + command list. Output: JSONL. / 根据用户指令生成训练数据。
README (SKILL.md)
📝 Data Generator / 数据生成器
Generate training data from Excel user instructions.
When to Use / 使用场景
| EN | CN |
|---|---|
| Generate training data from instructions | 从用户指令生成训练数据 |
| Batch produce AI training samples | 批量生成AI训练样本 |
| Build dataset from Excel | 从Excel构建数据集 |
Features / 功能
| Feature | EN | CN |
|---|---|---|
| Excel input | Excel file support | Excel文件输入 |
| JSONL output | JSONL output | JSONL格式输出 |
| Multi-tool support | Multi-tool support | 支持多种工具 |
| Customizable prompt | Customizable prompt | 可自定义提示词 |
Usage / 使用
from data_generator import Generator
# Simple / 简单
gen = Generator()
result = gen.generate(
tool_name="dev_control",
commands=["打开空调", "关闭窗帘"],
excel_file="data.xlsx"
)
# With prompt / 自定义提示词
result = gen.generate(
tool_name="alarm_remind",
commands=["提醒我起床"],
prompt_template="自定义提示词模板"
)
Parameters / 参数
| Parameter | Type | EN | CN |
|---|---|---|---|
| tool_name | str | Tool name | 工具名称 |
| commands | list | Command list | 命令列表 |
| excel_file | str | Excel file path | Excel文件路径 |
| prompt_template | str | Custom prompt | 自定义提示词(可选) |
Output / 输出
{"conversations": [...], "system": "..."}
{"conversations": [...], "system": "..."}
Installation / 安装
npx clawhub install data-generator-waai
Author / 作者
- WaaiOn
Usage Guidance
This skill's code is small and readable, but there are important mismatches to be aware of: (1) SKILL.md advertises Excel input and a prompt_template parameter that the shipped Python file does not implement — so the documentation is unreliable. (2) The code reads MINIMAX_API_KEY / OPENAI_API_KEY and an API_URL env var (defaulting to http://127.0.0.1:8766). While the current code does not include the API key in request headers, it does send prompts and generated text to the configured API_URL. Before installing or using: - Review and run the Python file locally to confirm behavior. - Ensure API_URL (if set) points to a trusted host (prefer localhost or an internal LLM) and do not set secrets in environment unless you trust the endpoint. - Do not supply sensitive or proprietary data until you're satisfied where prompts are sent. - If you need Excel support or prompt customization, note the current implementation lacks those features — expect to modify or extend the code. If you want a fully aligned/safer experience, ask the author to fix the documentation or update the code so declared inputs match implemented behavior.
Capability Analysis
Type: OpenClaw Skill
Name: data-generator-waai
Version: 1.1.0
The skill is a specialized utility for generating synthetic AI training data for smart home device interactions (e.g., 'GreeQA', 'dev_control'). The code in `data_generator.py` constructs prompts and sends them to a configurable LLM endpoint (defaulting to localhost). While there is a minor discrepancy between the documentation in `SKILL.md` (which mentions Excel support) and the actual implementation (which lacks it), the code contains no evidence of malicious intent, data exfiltration, or unauthorized execution. It handles API keys from environment variables but does not appear to transmit them to external or suspicious domains.
Capability Assessment
Purpose & Capability
Name/description: data generation for training data — matches the code's purpose. Mismatch: SKILL.md and usage examples mention Excel input (excel_file) and prompt_template parameters; data_generator.py does not implement reading Excel files nor accept a prompt_template or excel_file parameter. The SKILL.md API and the actual code signature are not aligned.
Instruction Scope
SKILL.md instructs use with Excel and customizable prompts and shows a Generator.generate signature that accepts excel_file and prompt_template. The runtime code only accepts a list of commands and an optional output_file — it never reads Excel or any other files. Also the SKILL.md metadata declares python3 as required but does not declare any env vars, while the code reads MINIMAX_API_KEY, OPENAI_API_KEY and API_URL from environment.
Install Mechanism
No install spec; this is an instruction-only skill with a small Python file. No remote downloads or archive extraction are performed by the registry/install metadata. Low install risk.
Credentials
Registry lists no required env vars, but the code reads MINIMAX_API_KEY and OPENAI_API_KEY and an API_URL (default http://127.0.0.1:8766). The api_key is captured in Generator but is not added to request headers in the current code (so not actively leaked). However the skill posts prompts to a configurable base_url; if API_URL is set to a remote host that host will receive prompts and LLM outputs. The mismatch between declared and accessed env vars and the ability to point to an arbitrary endpoint increases risk.
Persistence & Privilege
always is false, skill is user-invocable, and there is no code that modifies system or other skills' configuration. No special persistence or elevated privileges requested.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install data-generator-waai - After installation, invoke the skill by name or use
/data-generator-waai - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.1.0
- Added support for generating training data from user instructions using data_generator.py.
- No changes to documentation or usage examples.
- Version 1.1.0 focuses on internal improvements or feature extensions in the core Python file.
v1.0.0
- Initial release of Data Generator skill.
- Generates AI training data from user instructions using Python 3.
- Supports input from Excel files and outputs in JSONL format.
- Allows batch generation of training samples for multiple tools.
- Customizable prompt templates supported.
Metadata
Frequently Asked Questions
What is Data Generator?
Data Generator / 数据生成器 - Generate training data from user instructions. Input: tool name + command list. Output: JSONL. / 根据用户指令生成训练数据。 It is an AI Agent Skill for Claude Code / OpenClaw, with 260 downloads so far.
How do I install Data Generator?
Run "/install data-generator-waai" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Data Generator free?
Yes, Data Generator is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Data Generator support?
Data Generator is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Data Generator?
It is built and maintained by HuaiBuer (@huaibuer); the current version is v1.1.0.
More Skills