n8n-architect

Use when the user explicitly wants to create, edit, validate, sync, or troubleshoot n8n workflows, asks about n8n nodes or automation, or wants to use n8n-as-code in the current context root.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

77%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-sequenced CLI workflow skill with strong validation and feedback loops. Its main weaknesses are redundant restatements of the same commands across sections and a monolithic structure with no progressive disclosure into bundled reference files.

Suggestions

Deduplicate repeated guidance: consolidate the recurring 'env status --json', 'env add/auth set/use', and 'stop after two repeated failures' rules into a single canonical statement and reference it, rather than restating across Bootstrap Order, Environments, Managed Local Runtime, and Response Discipline.

Introduce progressive disclosure by extracting the stable catalogs (Knowledge Commands, Native MCP routing policy, AI/LangChain node rules) into files under references/ and linking to them from SKILL.md, keeping the body as a concise overview + operating loop.

Trim or merge near-duplicate sections (e.g. the credential/setup rules repeated in Environments, Managed Local Runtime, and Response Discipline) so each rule lives in exactly one place.

Dimension	Reasoning	Score
Conciseness	The body is directive and command-heavy with no padding of concepts Claude already knows, but it repeats the same commands and rules across sections (e.g. 'env status --json' restated many times, 'stop after two repeated failures' appears three times, overlapping Bootstrap/Environments/Operating Loop/Response Discipline guidance), so it is 'mostly efficient but could be tightened' rather than fully lean.	2 / 3
Actionability	Provides fully executable, copy-paste-ready guidance throughout — exact 'npx --yes n8nac ...' commands with flags, credential/sync/test sequences, and a complete TypeScript workflow skeleton — matching the top anchor; not the 'pseudocode / incomplete' level (score 2).	3 / 3
Workflow Clarity	Multi-step processes are explicitly sequenced (numbered Bootstrap Order and Operating Loop) with validation checkpoints ('push --verify', 'test-plan --json', 'skills validate') and feedback loops for risky ops (conflict handling, 'stop after two repeated failures', native-vs-local divergence), satisfying the top anchor.	3 / 3
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ absent) and the ~519-line body is a monolithic inline document; section headers organize it well, but knowledge-command catalogs, MCP routing policy, and authoring rules are inline content that could be split into referenced files, fitting 'some structure but content that should be separate is inline'.	2 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description with an explicit 'Use when...' trigger and multiple concrete capabilities scoped to a distinct n8n-as-code niche. It cleanly answers what the skill does and when to use it without fluff or over-claiming.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'create, edit, validate, sync, or troubleshoot n8n workflows' — matching the top anchor rather than the single-domain 'Names domain and some actions' (score 2).	3 / 3
Completeness	Explicitly answers both what (the create/edit/validate/sync/troubleshoot actions) and when via the 'Use when the user explicitly wants...' trigger clause, satisfying the top anchor; not capped at 2 because the trigger is explicit, not implied.	3 / 3
Trigger Term Quality	Covers natural terms users would say — 'n8n workflows', 'n8n nodes', 'automation' — alongside the jargon 'n8n-as-code'/'context root', so it is not the 'missing common variations' level (score 2).	3 / 3
Distinctiveness Conflict Risk	A clear n8n-as-code niche with distinct triggers ('n8n-as-code in the current context root') unlikely to fire for unrelated skills; the 'n8n nodes or automation' phrasing is specific enough to avoid the 'could still overlap' level (score 2).	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (520 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: EtienneLescot/n8n-as-code
Path: plugins/claude/n8n-as-code/skills/n8n-architect/SKILL.md
Commit: 878d54d

Reviewed: 12 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.