Mysteel_ChartGeneration

基于文本描述或数据自动生成各类图表（趋势图、对比图、结构图等）；当用户需要创建可视化图表、将数据转化为直观表达、生成分析报告插图时使用

This skill appears to implement an AI-driven chart generator, but take these precautions before installing or running it: - Verify the external endpoint: The script sends your API key and request payload to https://mcp.mysteel.com. Confirm you intend to use that service and that the API key you provide is only for this service. If you don't recognize the domain, do not provide secrets. - API key handling: The skill expects a local file references/api_key.md containing the API key. Prefer storing secrets in a secure secret manager or environment variable if possible, and avoid committing api_key.md into version control. Inspect the file contents format the script expects before creating it. - Documentation mismatch: SKILL.md shows running the .py files with 'node' — that's incorrect. Run the scripts with Python (python3 scripts/generate_chart.py ...) and ensure Python and the 'requests' package are installed. - Run in an isolated environment: Execute the scripts in a sandboxed or isolated environment (container or VM) until you are comfortable with network traffic and file outputs. - Review outputs and network traffic: After a test run, inspect the generated output/ files and, if possible, monitor outbound network requests to confirm only expected calls are made. Overall, the package is coherent with a chart-generation use-case but the documentation errors and the fact that it transmits a user-supplied key to an external service make it worth extra review before use.

Type: OpenClaw Skill Name: mysteel-chartgeneration Version: 1.0.0 The skill bundle provides a legitimate utility for generating ECharts visualizations via a Mysteel API (mcp.mysteel.com). The Python scripts (generate_chart.py and render_html.py) implement the stated functionality by sending user-provided data to the API and rendering the resulting configuration into a standard HTML template. While the SKILL.md documentation contains a minor technical error (instructing the agent to use 'node' to execute Python scripts), the code logic is transparent, lacks obfuscation, and only accesses the specific API key file (references/api_key.md) required for its operation.