Back to directory

n8n-claude-skills

n8n-claude-skills is a set of Claude Code skills, distilled from more than a hundred production n8n workflows by a verified n8n creator, that teach Claude the node types, expression syntax and patterns needed to build real, working n8n automations instead of broken demos.

n8n-claude-skills

Installed with a single command, the pack adds skills that fire on specific requests: designing a full workflow from a plain-language description, chaining several LLM calls for tasks such as entity extraction and scoring, building multi-vendor data-enrichment waterfalls with cost-aware fallbacks, applying production-safe MySQL patterns such as batch processing and idempotent pipelines, and systematically debugging a failing workflow by reading its expressions, pinned data and execution logs.

The stated motivation is that language models routinely hallucinate n8n details, inventing node names or mixing up expression syntax, and ship demos that fall apart once real data is involved; the skills encode patterns the author has used in production, including financial reporting pipelines, multi-language transcript processing and spam-scoring workflows.

It is distributed as an npm package and installed as Shell-scripted setup, and is released under the MIT license.

More in Agent skills

See all 581
  • Provenance gate

    github.com

    A deterministic authorization gateway that sits between an AI agent and its tools, tracing where each parameter of a side-effect call came from, and blocking the call or asking a human when the source does not check out.

  • A markdown framework of system rules that restates Isaac Asimov's Four Laws of Robotics as a set of prioritized loss calculations for large-language-model agents to follow, published as a discovery file for agents and crawlers to read.

  • Vitruvius

    github.com

    An engineering research agent that runs a discover, read, synthesize, verify and review loop over technical questions, reading sources directly rather than inferring from titles, and publishing its own scored verifier benchmark, weaknesses included.