The Agent Skills Directory

[SAFE]: The skill is entirely documentation-based and does not contain any executable code or scripts that perform suspicious operations.
[EXTERNAL_DOWNLOADS]: References official GitHub Actions runners and various well-known third-party actions from the GitHub Marketplace (e.g., actions/checkout, codecov/codecov-action, dorny/test-reporter). All sources are established services.
[COMMAND_EXECUTION]: Includes standard command-line examples for setting up CI environments, running linters via Docker, and executing test suites (e.g., npm test, pytest). These are standard development practices.
[PROMPT_INJECTION]: No patterns attempting to bypass agent safety or override system instructions were found.
[DATA_EXFILTRATION]: No evidence of hardcoded credentials or unauthorized data access. The skill explicitly teaches how to securely manage secrets using the GitHub Actions secrets vault.

github-ci