Conciseness

Extremely dense with essentially no concept-explanation padding — every sentence carries a rule, a trap, or a pointer ("A Set node holding a token referenced via {{ $json.token }} is a leak with extra steps") — but the ~60-line inline per-tool catalog (folder-delete semantics, evaluations 403 causes, canvas-group pruning) is reference material beyond 'minor trimming' that belongs in the specialist skills. It sits above level 3 because the inline catalog is explicitly justified ("closes the gap where a tool's full description isn't loaded until first use") and the signal density is high, and below level 5 because a meaningful fraction of the tool section is detail owned by n8n-mcp-tools-expert.

Actionability

Fully concrete, executable guidance throughout: exact tool names, exact parameter shapes ("{topic:\"ai_agents_guide\", depth:\"full\"}", "mode=\"filtered\"" + nodeNames, "transferToFolderId: \"0\""), and both node-type forms named with the mixing trap called out (SHORT "nodes-base.set" vs LONG "n8n-nodes-base.set"). For an instruction-only router skill this is copy-paste-ready guidance covering the common cases, matching the level-5 anchor.

Workflow Clarity

"The protocol, in order" is a numbered sequence with explicit validation checkpoints (validate_workflow before activating, n8n_get_workflow after edits to inspect connections), error-recovery loops (drift surfacing, "If they are absent, nothing is broken and there is nothing to retry"), and the red-flags table functioning as a pre-action checklist — clear sequence, explicit validation, and feedback loops, matching the level-5 anchor.

Progressive Disclosure

No bundle files exist for this skill; navigation runs through a skill-index table plus clearly signaled, one-level-deep "See n8n-x" pointers, which is good structure. It falls short of level 5 because a substantial block of reference-grade content (the full tool catalog) is inlined in the router rather than placed in the specialist bodies it repeatedly points to; it stays above level 3 because the pointers that do exist are clear and easy to navigate.

Specificity

Comprehensively lists concrete actions ("building, editing, validating, testing, or debugging an n8n workflow… designing a flow, configuring a node, writing an expression or Code node, wiring credentials"), matching the level-5 anchor, but the second-person phrase "it routes you to the right specialist skill" incurs the rubric's -1 voice penalty, landing it at 4 — still above level 3 because the action coverage is comprehensive rather than partial.

Completeness

Explicitly answers both questions: the what ("routes you to the right specialist skill, gives working knowledge of every n8n-mcp tool… states the rules that keep workflows from breaking in production") and a concrete, enumerated when ("Always consult it first on any n8n, workflow, node, or automation task — even a quick one-off, and even when the user names no skill"), matching the level-5 anchor; level 4 would require the 'when' to be less explicit.

Trigger Term Quality

Natural trigger words cover the space with synonyms: "n8n", "workflow", "node", "automation", "expression", "credentials", "flow", plus build/edit/validate/test/debug/fix variations; no common user phrasing is missing, so it fits the level-5 anchor rather than level 4's "a few natural terms missing".

Distinctiveness Conflict Risk

The niche (n8n work through the n8n-mcp MCP server) is unmistakable, but "Always consult it first… even when the user names no skill" deliberately claims every n8n/automation task, creating real (intentional) overlap with its own pack's specialist skills — mostly distinct with minor overlap risk, i.e., level 4 rather than level 5's minimal conflict risk.