The Agent Skills Directory

[NO_CODE]: The skill consists entirely of markdown instructions for the AI agent and does not contain any executable scripts, binaries, or configuration files that run code.
[CREDENTIALS_UNSAFE]: No hardcoded credentials or secrets were detected. The instructions explicitly mandate the use of environment variables and placeholders for management tokens and API keys in all examples.
[COMMAND_EXECUTION]: The skill strictly prohibits the creation, modification, or deletion of workflows and publish rules. The agent's role is limited to advisory guidance using read-only tools.
[INDIRECT_PROMPT_INJECTION]: The skill processes project data using Read, Grep, and Glob. While this represents a data ingestion surface, the agent lacks write or network capabilities, and the instructions focus on providing architectural advice, minimizing injection risks.

cms-workflows