The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown documentation, symptom catalogues, and technical guides. No executable scripts, binary files, or platform-level command injection configurations are present within the skill folder.
[INDIRECT_PROMPT_INJECTION]: The skill provides instructional content that an agent processes to gain knowledge of the n8n ecosystem.
Ingestion points: The agent reads SKILL.md and the reference files in the references/ directory to perform troubleshooting tasks.
Boundary markers: The skill does not use specific delimiters or control instructions to isolate the data it processes.
Capability inventory: The documentation identifies external tools like docker compose, ansible-playbook, terraform, and rclone as standard interfaces for managing the n8n lifecycle.
Sanitization: The skill provides explicit guidance on how to prevent 'unrendered template' injection in Ansible and how to verify that credentials are correctly handled by the container runtime.
[EXTERNAL_DOWNLOADS]: The documentation references external GitHub repositories belonging to the vendor (e.g., github.com/getcolors/n8n, github.com/getcolors/neon) as the authoritative reference implementations for the deployment patterns described. These references are documented neutrally and correspond to the author's own verified infrastructure code.
[COMMAND_EXECUTION]: The troubleshooting and verification sections describe the use of standard system utilities (e.g., pg_dump, psql, rclone, ssh, docker). These commands are provided as instructional examples for the agent to resolve specific, documented failure modes in the n8n application stack.

n8n-single-node