agent-builder

Load before calling build-agent for a new or existing n8n Agent. Governs prerequisite creation, faithful handoff of the user's request, agent targeting across turns, builder questions, testing, and publishing. Use directly for routine follow-ups when the conversation already targets an Agent; rerun intent-recognition only when the requested artifact is no longer clear.

Quality

77%

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/agent-builder/SKILL.md

Quality

Content

75%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 well-structured, actionable instruction skill that gives Claude concrete field-level rules for building and targeting n8n Agents across turns. It is efficient and clearly sequenced, with only minor trimming, validation, and optional file-split opportunities.

Suggestions

Tighten the long enumeration lists and consolidate the faithful-handoff restatement between "Faithful handoff" and "Builder-owned interactions" to improve conciseness.

Add an explicit verify/confirm checkpoint after build-agent calls (e.g., confirm the returned agentRef and requiredArtifacts before proceeding) to strengthen workflow_clarity.

Consider moving the detailed requiredArtifacts relationship handling into a short referenced file to lift progressive_disclosure, keeping the core routing rules inline.

Dimension	Reasoning	Score
Conciseness	Dense operational rules with no concept-explanation padding and respect for Claude's competence, but lengthy enumerations (e.g., "model, instructions, tools, tool types, integrations, channels, MCP servers…") and mild restatement of the faithful-handoff principle across sections could be trimmed.	4 / 5
Actionability	Provides concrete, executable guidance via specific field names (agentRef, agentId, createNew, workflowContext, requiredArtifacts, relationship) and clear decision branches; occasional phrasing like "handle them the same way based on whether…" leaves minor gaps.	4 / 5
Workflow Clarity	Multi-step processes (prerequisites, requiredArtifacts handling, saved sub-agent dependencies) are clearly sequenced with a built-in feedback loop (builder returns requiredArtifacts → create → re-call); explicit validation checkpoints are absent but the destructive/batch cap does not apply to agent building.	4 / 5
Progressive Disclosure	Well-organized into clear section headers (Routing, Faithful handoff, Prerequisites, Targeting across turns, Saved sub-agent dependencies, Builder-owned interactions) with no nested references and cohesive inline policy, though at ~110 lines some prerequisite detail could justify a one-level-deep reference file.	4 / 5
	Total	16 / 20 Passed

Description

80%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, well-scoped description that clearly states both capability and triggering conditions for an n8n-specific builder workflow. Its main weakness is jargon-heavy trigger language that omits the natural phrasings a user might actually say.

Suggestions

Add user-natural trigger phrases (e.g., "Use when the user asks to build, edit, or publish an n8n Agent") alongside the operational terms to improve trigger_term_quality.

Consider naming one or two more concrete capabilities (e.g., "creates prerequisite workflows and data tables") to lift specificity from several actions toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete governed actions ("prerequisite creation, faithful handoff of the user's request, agent targeting across turns, builder questions, testing, and publishing"), but the actions are domain-abstract rather than fully enumerated, leaving minor coverage gaps.	4 / 5
Completeness	Explicitly answers both what ("Governs prerequisite creation… testing, and publishing") and when ("Use directly for routine follow-ups when the conversation already targets an Agent; rerun intent-recognition only when the requested artifact is no longer clear") with concrete trigger phrasing.	5 / 5
Trigger Term Quality	Includes relevant terms ("build-agent", "n8n Agent", "routine follow-ups", "intent-recognition") but leans on operational jargon and misses common user-level synonyms or phrasings a requester might naturally say.	3 / 5
Distinctiveness Conflict Risk	Tightly scoped to n8n Agent construction via build-agent with a clear routing relationship to intent-recognition, giving it a distinct niche with minimal conflict risk against unrelated skills.	5 / 5
	Total	17 / 20 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

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

Reviewed: 39 minutes 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.