The Agent Skills Directory

[CREDENTIALS_UNSAFE] (SAFE): The skill actively encourages security hygiene by instructing the agent to search for hardcoded secrets (password, secret, api_key, token) before committing code.
[COMMAND_EXECUTION] (SAFE): Contains standard Git and Node.js development commands (e.g., git worktree, npm test, npx tsc) that are strictly aligned with the skill's stated purpose of managing code workflows.
[DATA_EXFILTRATION] (SAFE): No network operations or external data transfer mechanisms were detected. The skill explicitly advises against committing sensitive environment files like .env or .pem keys.

git-workflow-and-versioning