Content
80%Weight 40%Scale 1-3Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
An excellent, highly actionable CLI reference that is concise and copy-paste-ready throughout, with no wasted conceptual padding. Its main gaps are the absence of validation checkpoints around destructive/batch operations and a fully inline structure with no progressive disclosure to deeper reference files.
Suggestions
Add a verification step before destructive/batch operations — e.g. recommend `n8n-cli workflow get <id>` or `--include-data` review before `workflow delete`, and show a confirm-then-delete pattern for `data-table delete-rows` — to introduce explicit feedback loops.
For multi-step composability patterns (such as the get-modify-update pipeline), add an explicit checkpoint that re-reads or validates the result after the mutating command.
Consider splitting the full command reference and the Workflow JSON Structure into a one-level-deep reference file (e.g. references/REFERENCE.md) so SKILL.md serves as a leaner overview pointing to detail.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and command-dense with no concept explanations Claude already knows; the two-sentence intro and per-command `#` comments earn their tokens, with only negligible cross-section redundancy. It is efficient rather than padded, fitting the top anchor. | 3 / 3 |
Actionability | It is almost entirely concrete, copy-paste-ready commands (e.g. `n8n-cli workflow get <id> --jq '.nodes[].name'`, `cat rows.json | n8n-cli data-table add-rows <id> --stdin`) plus a complete workflow JSON example, leaving nothing abstract. | 3 / 3 |
Workflow Clarity | Sequencing exists in the Setup alternatives and the Composability Patterns pipelines, but there are no validation/feedback checkpoints around destructive and batch operations (e.g. `workflow delete`, `data-table delete-rows`, `credential delete`), which the rubric caps at 2. It is not a 1 because pipelines and setup steps are clearly ordered. | 2 / 3 |
Progressive Disclosure | The skill is well-organized into headed sections but is a single ~260-line monolith with no one-level-deep references or split-out detail files, and it exceeds the under-50-line carve-out; this matches the anchor where content that could be separate lives inline. It is not a 1 because sections are clearly labeled and navigable. | 2 / 3 |
Total | 10 / 12 Passed |