What does this skill do, and when should you use it?
This is one standalone skill from czlonkowski/n8n-skills, focused on writing, validating, and troubleshooting n8n expressions. It covers double-curly-brace syntax, $json, $node, $now, $env, webhook payload structure, and data mapping between nodes. It also explains when to use an expression, an Edit Fields IIFE, or a Code node, along with practical guidance on expression complexity and workflow performance. It fits n8n builders who need reliable field mappings or expression troubleshooting, especially when n8n-mcp validation tools are available.
It guides the model in writing {{}} expressions for n8n fields, reading current-node and previous-node data, accessing webhook body, query, and header values, and handling nested objects, arrays, strings, numbers, and Luxon date-time values. It identifies and fixes missing braces, invalid bracket or dot notation, case-sensitive node-name mismatches, incorrect webhook paths, and expression usage inside Code nodes. It also provides a decision order for expressions, Edit Fields IIFEs, and Code nodes, plus recommendations for branch convergence and unnecessary Set nodes.
- An n8n builder is mapping webhook submissions into Slack and needs to read user data from $json.body.
- An automation engineer is referencing an upstream node named HTTP Request and needs exact quoted, case-sensitive node syntax.
- A workflow maintainer is debugging literal expression text, undefined properties, or method errors in node fields.
- A user needs to format dates, transform arrays, manipulate strings, or add conditional values directly in n8n fields.
- An n8n developer is deciding whether a complex single-item transformation should remain an expression or move to a Code node.
How do you install this skill?
- Do not place API keys in URLs or ordinary expression text; prefer n8n credentials and confirm the instance's environment-variable access policy.
- Obtain confirmation and retain a recoverable copy before deleting or rewiring Set nodes, because the recommendation can change data flow.
- Verify $node, $('Node'), webhook body behavior, IIFEs, credential fields, and expression performance against the target n8n version and node types.
- The external API, SQL-construction, and webhook examples do not cover escaping, missing fields, empty arrays, sensitive-data logging, or error responses.
- MCP Server
n8n-mcp MCP server
This skill is distributed in the n8n-skills collection. In Claude Code, install the collection with /plugin install czlonkowski/n8n-skills. Alternatively, clone it with git clone https://github.com/czlonkowski/n8n-skills.git and copy n8n-skills/skills/n8n-expression-syntax to ~/.claude/skills/. The collection documentation requires an n8n-mcp MCP server to be configured. In Claude.ai, download skills/n8n-expression-syntax and upload it through Settings → Capabilities → Skills. The supplied material does not provide detailed API/SDK installation steps.
tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/czlonkowski/n8n-skills.git "$tmp"
mkdir -p ~/.claude/skills
cp -R "$tmp/skills/n8n-expression-syntax" ~/.claude/skills/
rm -rf "$tmp"Generated from the source repository and skill path; it copies only this skill's folder. If the author's install steps above differ, follow those first. To scope it to one project, replace ~/.claude/skills with that project's .claude/skills.
How do you use this skill?
Once installed, send your agent any of these to trigger it:
- How do I correctly read the email field from an n8n webhook?
- Check whether {{$node["HTTP Request"].json.data}} is valid.
After installation, ask a relevant prompt such as “How do I correctly read the email field from an n8n webhook?” or “Check whether {{$node["HTTP Request"].json.data}} is valid.” The skill is designed to activate for requests involving {{}}, $json, $node, webhook data, expression errors, or performance tradeoffs. For actual validation, the material points to n8n-mcp validation tools; it does not show that the skill independently executes validation.
What are this skill's strengths and limitations?
- Covers common expression sources, including current nodes, previous nodes, webhooks, environment variables, and date-time values.
- Clearly identifies contexts where expressions should not be used, including Code nodes, webhook paths, and credential fields.
- Includes error fixes, working examples, transformation guidance, and branch-convergence recommendations.
- Can be installed as part of the n8n-skills collection or uploaded as an individual skill folder.
- It depends on the n8n-mcp MCP server for the referenced validation tooling and is not itself an n8n execution engine.
- The supplied material provides no independent test results, platform coverage data, or reproducible performance benchmark.
- The performance figures are reported for an n8n 2.x instance and should not be assumed universal across deployments.
- The full COMMON_MISTAKES.md catalog and EXAMPLES.md content are referenced but not included in the supplied material.
How does this skill compare with similar options?
Side by side with related skills; every score comes from the same FSRS standard.
| Skill | FS score | Stars | Last updated | License |
|---|---|---|---|---|
| n8n Expression Syntax Guide this page | 47 · Use with care | ★ 6.4k | 19d ago | MIT |
| n8n JavaScript Code Node Guide | 47 · Use with care | ★ 6.4k | 19d ago | MIT |
| n8n AI Code Tool Guide | 54 · Use with care | ★ 6.4k | 19d ago | MIT |
| n8n Python Code Node Guide | 49 · Use with care | ★ 6.4k | 19d ago | MIT |
| Azure Storage Skill ✓ Microsoft · Official | 51 · Use with care | ★ 2.7k | 3mo ago | MIT |
How did FollowSkills review this skill?
The material explicitly warns about environment-variable and credential risks and recommends the credential system. However, it still demonstrates placing API keys in headers or URLs, and it recommends deleting Set nodes and rewiring workflows without explicit confirmation, backup, rollback, or data-flow review. No malware, covert exfiltration, or gross overreach is evident, so the score is reduced but not zero.
The documentation is organized and covers common syntax, mistakes, and debugging steps, making the happy path plausible. There is no executable test or CI evidence, and several claims depend on n8n version and node context, including webhook structure, credential fields, IIFE support, and performance figures. These uncertainties justify a score below the static ceiling of 10.
The audience, trigger phrases, and primary scenarios are reasonably clear, covering expressions, webhooks, Code nodes, and node references. Non-fit boundaries, version differences, input-shape assumptions, and Chinese-language guidance are limited. The core function does not entirely depend on unreachable overseas services, so no such deduction is applied.
The skill has a main guide, mistake catalog, examples, and README, with dependency notes, related skills, an MIT license, an update date, and evaluation claims. Maintenance ownership, changelog, compatibility matrix, complete installation path, and escalation process are incomplete; repository-level documentation cannot fully substitute for skill-specific governance, so points are deducted.
The examples and quick-reference material can directly help with many expression-writing problems, and the core benefit is clear. However, key examples lack execution evidence, some recommendations may vary by n8n version or node type, and claims such as performance measurements and 95% coverage are not supported by committed tests. The score therefore remains within the static ceiling of 7.
The review material includes a pinned revision, concrete code examples, an error catalog, and declared evaluation scenarios. It does not include a committed test suite, CI results, independent review, or reproducible execution records. Claims about real workflows, MCP testing, and performance measurement are primarily author assertions, so the score remains below the static ceiling of 5.
Open a dimension to read why it scored that way
Evidence confidence：Low — Mostly static review, author material or a limited demo; useful for discovery, not high-risk decisions.
See the full review method →