workflow-builder

Load before calling build-workflow. Default path for all single-workflow work: new one-off workflows, existing-workflow edits, verification repairs, and workflow-local data tables. Write or edit a workspace source file, run workflow-sdk validate via workspace_execute_command, then call build-workflow with filePath. When the workflow creates or writes Data Tables, load data-table-manager first, then this skill. Do not load planning or create-tasks first. Load planning only when multiple coordinated workflows or shared cross-task data tables require a dependency-aware task graph.

Quality

74%

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

Fix and improve this skill with Tessl

tessl review fix ./packages/@n8n/instance-ai/skills/workflow-builder/SKILL.md

Quality

Content

81%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.

The body is highly actionable with a rigorously sequenced, validation-checked build workflow and concrete executable code, and it uses one-level-deep references well. Its one weak spot is conciseness: several policy-heavy sections could be tightened without losing clarity.

Suggestions

Move the Credential Rules and Gateway credits Preference sections into a reference file (like compositional-workflows.md) and keep a short routing pointer in SKILL.md to cut the inline token load.

Compress the Escalation and Credential Rules conditional clauses into a short table or bulleted decision list to reduce stacked sub-clauses.

Pull the long SDK import block out of the main body into the SDK Patterns Reference or a reference file, keeping only the minimal set inline.

Dimension	Reasoning	Score
Conciseness	The ~860-line body avoids explaining basic concepts Claude knows and almost all content is operational guidance Claude would not otherwise have, but the stacked conditional clauses in Escalation, Credential Rules, and Gateway credits Preference could be tightened; matches anchor 3 leaning toward 4.	3 / 5
Actionability	Provides fully executable, copy-paste-ready guidance: the exact validate CLI command, concrete tool calls with action/parameters, and complete TypeScript SDK patterns (trigger, node, ifElse, merge, switch) plus the full import block — matching anchor 5.	5 / 5
Workflow Clarity	The 12-step Mandatory Process is a clear sequence with explicit validation checkpoints (step 7 validate, step 10 fix → re-validate → rebuild loop) and a verification contract with feedback loops and budgets; the destructive/batch validation cap is satisfied, matching anchor 5.	5 / 5
Progressive Disclosure	SKILL.md is an overview with two real, clearly-signaled one-level-deep references (references/compositional-workflows.md and references/error-workflows.md, both present on disk) plus knowledge-base pointers; matches anchor 4, not 5 because sizable material like Credential Rules and Gateway credits Preference is inlined rather than split out.	4 / 5
	Total	17 / 20 Passed

Description

67%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.

The description is specific, complete, and well-routed for an internal workflow-building skill, with concrete actions and explicit load-order/when guidance. Its main weakness is trigger-term quality: it relies on internal tool names rather than natural language a user would actually say.

Suggestions

Add natural user-facing trigger phrases (e.g. 'Use when the user asks to create, edit, or fix an n8n workflow') alongside the tool-name routing.

Include common synonyms/extensions users say ('build a workflow', 'n8n automation', 'workflow not working') to improve trigger-term coverage.

Lead with a one-sentence plain-language summary of what the skill does before the routing rules, so the 'what' reads as a capability rather than a process.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Write or edit a workspace source file, run workflow-sdk validate ... then call build-workflow', 'new one-off workflows, existing-workflow edits, verification repairs'), matching anchor 4; not a 5 because coverage is framed as workflow-build operations rather than a fully comprehensive action list.	4 / 5
Completeness	Explicitly answers both what (build/edit/verify n8n workflows) and when ('Default path for all single-workflow work: ...', 'Load before calling build-workflow', load-order rules), but the 'when' is routing-oriented rather than concrete user trigger phrases, keeping it below 5.	4 / 5
Trigger Term Quality	Keywords are mostly internal tool names ('build-workflow', 'workflow-sdk validate', 'Data Tables', 'planning', 'create-tasks') rather than natural phrases a user would say; some relevant terms but missing common user-facing synonyms like 'create an n8n workflow'.	3 / 5
Distinctiveness Conflict Risk	Scoped to single-workflow n8n building and explicitly distinguished from sibling skills ('Do not load planning or create-tasks first', 'load data-table-manager first'); mostly distinct with minor overlap risk, not a 5 because triggers are tool-call names rather than distinctive user phrases.	4 / 5
	Total	15 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (892 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: n8n-io/n8n
Path: packages/@n8n/instance-ai/skills/workflow-builder/SKILL.md
Commit: 7700b76

Reviewed: ~1 hour 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.