The Agent Skills Directory

[SAFE]: The skill's functionality is strictly limited to environment diagnostics and configuration assistance as described in its documentation.
[COMMAND_EXECUTION]: The skill uses subprocess.run to execute node --version and check the help output of a sibling skill's runner script. These commands are used for version validation and environment discovery. They do not accept arbitrary user input and are executed using safe list-based arguments rather than a shell string.
[CREDENTIALS_UNSAFE]: The skill identifies missing API keys (e.g., SN_API_KEY) and offers an interactive prompt to save them into a local .env file. This is a standard and acceptable practice for local environment configuration and does not involve hardcoding secrets or unauthorized data exposure.
[EXTERNAL_DOWNLOADS]: No remote downloads or network requests were identified. The skill detects missing third-party libraries (like pypdf or python-docx) and provides the user with the relevant installation commands to run manually.
[DATA_EXFILTRATION]: There are no network operations or patterns suggesting that sensitive data is being transmitted to external servers.

sn-ppt-doctor