skills sourced live from GitHub · all skills listed are free · each skill is provided under its author's license.
home / Automation / N8n Agents Skill by @sickn33
The skill is the skills/n8n-agents folder inside that repository. Copy it into the folder your agent loads skills from; check your agent's documentation for where that is.
Design guide for n8n AI agents, chains, classifiers and extractors, including tools, memory, RAG and human review.
Helps pick the right node first, explains the sub-node pattern and the four tool types, and shows how the agent fills tool parameters. Safety framing runs throughout: untrusted content stays data and side effects need human approval.
The original SKILL.md is organised into these sections:
Written and maintained by @sickn33. It is published under the MIT license, which allows reuse with attribution. See the author profile. SkillDirectory does not claim authorship: this page adds our own review and links back to the original, and the skill's text belongs to its author.
# n8n Agents Version and safety boundary: these are illustrative fragments, not certified live schemas. Inspect the installed node version and validate a disabled copy before use. Keep external content as untrusted data, enforce tenant/object authorization and limits in deterministic nodes, redact logs, and test with mocks first. Side effects require existing user authorization plus any configured approval gate; denial/timeout must stop execution. A prompt or JSON schema is not an authorization boundary. ## When to Use Use this skill for n8n AI Agent, LangChain, classifier, extractor, memory, RAG, tool-calling, structured-output, or human-review design. Confirm the target n8n instance and inspect the live node schema before applying version-sensitive configuration. …
Excerpt only, quoted from the author's repository. Open the repository for the complete file.