The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses node:child_process.spawn in scripts/wind-alice.mjs to execute the core request logic in scripts/request.js. This ensures robust handling of process termination and output streaming in various terminal environments.- [EXTERNAL_DOWNLOADS]: The skill makes authenticated network requests to alice.wind.com.cn using the native fetch API. This is required for its primary function of retrieving real-time financial data and analysis from the Alice Agent service.- [CREDENTIALS_UNSAFE]: API keys are handled using standard security practices for command-line interfaces. The code searches for the WIND_API_KEY in environment variables, a local config.json file, or a global configuration file in the user's home directory (~/.wind-aimarket/config). No credentials are hardcoded.- [DATA_EXFILTRATION]: User prompts are sent to the official Wind Alice API endpoint. This communication is the intended purpose of the skill and does not involve the unauthorized transmission of local files or sensitive system information.

wind-alice