Content
88%Weight 40%Scale 1-5Reviews 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 body with concrete commands, working TypeScript examples, and strong validation feedback loops. The main weakness is progressive disclosure — the large amount of reference-style material (command catalogs, node rules) is inlined rather than split into one-level-deep bundle files.
Suggestions
Move the long command catalogs (e.g. 'Knowledge Commands', 'Managed Local Runtime' command lists) into a references/ file and link to it from SKILL.md, so the body stays a concise overview with one-level-deep references.
De-duplicate recurring phrases like 'Run npx --yes n8nac env status --json' and 'stop after two repeated failures with the same diagnostic' by stating each rule once and back-referencing it.
Consider extracting the TypeScript authoring rules (decorators, .uses() AI connections, workflow-map navigation) into a references/authoring.md to reduce body length and token load.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean and free of padding about concepts Claude already knows — it is dense n8n-as-code specifics throughout — but there is noticeable repetition (e.g. 'env status --json' and 'stop after two repeated failures' recur across sections) that could be tightened, keeping it just below the score-5 'every token earns its place' bar. | 4 / 5 |
Actionability | Fully executable guidance: exact `npx --yes n8nac ...` and `npx --yes @n8n-as-code/n8n-manager ...` commands with flags, plus copy-paste-ready TypeScript decorator examples and AI sub-node wiring patterns covering the common cases. | 5 / 5 |
Workflow Clarity | Clear numbered sequences ('Bootstrap Order', 'Operating Loop') with explicit validation checkpoints (`--verify`, `--json`, `test-plan`), error-feedback loops ('stop after two repeated failures with the same diagnostic'), and dedicated conflict-resolution and destructive-op safeguards. | 5 / 5 |
Progressive Disclosure | Well-organized into clearly headed sections, but the skill is a large single-file monolith (no references/, scripts/, or assets/ bundle files exist) so everything is inlined; the simple-skill exception does not apply at this length, keeping it just below the score-5 one-level-deep-reference bar. | 4 / 5 |
Total | 18 / 20 Passed |