n8n-subworkflows

Build reusable, composable n8n sub-workflows. Use when extracting shared logic, building anything multi-step or reused across workflows, or any workflow over ~10 nodes — and whenever the user mentions sub-workflows, Execute Workflow, reuse, shared/common logic, modular workflows, "Define Below" inputs, waitForSubWorkflow, mode each vs all, or exposing a workflow as an agent tool. Covers typed sub-workflow inputs, all-vs-each execution, verb-first naming for discovery, stateless vs stateful design, and splitting by input shape.

Quality

94%

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

88%Weight 40%Scale 1-5

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

A dense, highly actionable body that covers when to extract, input/output contracts, calling modes, and anti-patterns with concrete code, commands, tables, and a validation-backed checklist. Its main weaknesses are mild editorial padding in the intro and two referenced files that are signaled but not actually shipped in the bundle.

Suggestions

Trim the motivational framing in the opening paragraphs (encapsulation/reuse/drift) — Claude already knows why duplication is bad; lead with the mechanism instead.

Ship SUBWORKFLOW_PATTERNS.md and NAMING_AND_DISCOVERY.md in a references/ directory, or inline the essential bits they promise (the N+1 worked example, the fire-and-forget polling pattern, the verb-first prefix convention) so the signaled references resolve.

Move the long 'Integration with other skills' list toward the end or into a reference file; it is navigational context rather than core instruction and competes with the actionable sections for attention.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and dense with concrete JSON, tables, and commands, but the opening framing ('the things functions buy you everywhere... badly underused... quietly drift apart') and occasional editorial flourishes ('ambushes every caller') explain motivations Claude already knows and could be trimmed.	4 / 5
Actionability	Provides copy-paste-ready JSON for the trigger's workflowInputs.values, concrete MCP commands (n8n_list_workflows, n8n_get_workflow, n8n_test_workflow, validate_workflow), exact expression syntax ($json.<field>, $('When Executed by Another Workflow').first().json.<field>), and explicit return shapes covering the common cases.	5 / 5
Workflow Clarity	Multi-step processes are clearly sequenced with explicit validation checkpoints ('verify with validate_workflow and n8n_get_workflow before you're done'), a feedback loop for destructive field renames (enumerate callers → migrate → verify), and a closing shipping checklist.	5 / 5
Progressive Disclosure	Well-organized into focused sections with a clear 'Reference files' table and one-level-deep, clearly signaled pointers to SUBWORKFLOW_PATTERNS.md and NAMING_AND_DISCOVERY.md, but neither referenced file is present in the bundle (no references/ directory exists), leaving those navigation targets dangling.	4 / 5
	Total	18 / 20 Passed

Description

100%Weight 40%Scale 1-5

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 that concretely states what the skill does and gives explicit, comprehensive 'use when' triggers covering both reuse-oriented and feature-keyword scenarios. It is dense without being padded and clearly distinguishable from neighboring n8n skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions and capabilities — 'extracting shared logic', 'typed sub-workflow inputs', 'all-vs-each execution', 'verb-first naming for discovery', 'stateless vs stateful design', and 'splitting by input shape' — giving comprehensive coverage rather than vague language.	5 / 5
Completeness	Explicitly answers both 'what' (build reusable composable sub-workflows covering typed inputs, execution modes, naming, stateful/stateless design, splitting) and 'when' ('Use when extracting shared logic... or any workflow over ~10 nodes — and whenever the user mentions...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger terms including synonyms and product-specific tokens — 'sub-workflows', 'Execute Workflow', 'reuse', 'shared/common logic', 'modular workflows', 'Define Below inputs', 'waitForSubWorkflow', 'mode each vs all', and 'exposing a workflow as an agent tool'.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear n8n-specific niche with distinct triggers (Execute Workflow, waitForSubWorkflow, Define Below) that are unlikely to fire for unrelated skills, minimizing conflict risk.	5 / 5
	Total	20 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: czlonkowski/n8n-skills
Path: skills/n8n-subworkflows/SKILL.md
Commit: 2df0f18

Reviewed: 22 hours 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.