The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/batch_download_bilibili.py utilizes subprocess.run to invoke the yt-dlp command-line tool for downloading media files from Bilibili as part of its corpus building process.
[COMMAND_EXECUTION]: Instructions within SKILL.md direct the agent to execute shell commands via python -c to verify and update configuration settings in the local .env file during the initial setup.
[EXTERNAL_DOWNLOADS]: The skill is configured to fetch financial market data from the Tushare API and download video/audio content from Bilibili for transcription purposes.
[EXTERNAL_DOWNLOADS]: The audio transcription module in scripts/batch_transcribe.py initiates a download of the faster-whisper AI model from an external repository upon its first use.
[SAFE]: The skill implements a secure credential handling mechanism by instructing users to manually enter their API tokens into a local .env file, which is correctly excluded from version control via .gitignore to prevent accidental exposure.

zettaranc-perspective