Content
92%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.
An excellent, dense CLI reference: fully executable, well-organized, and with rare attention to validation and error-recovery in the multi-step promotion workflow. The one structural weakness is that it is monolithic — a reference file for Promotions would keep the main skill to an overview.
Suggestions
Move the Promotions deep-dive (~130 lines: provider/environment JSON, GitLab setup, apply/apply-continue semantics, and key points) into a PROMOTIONS.md reference and keep a short overview with a clearly signaled one-level-deep link.
Consider extracting the per-resource command reference (workflows, executions, credentials, projects, tags, variables, data tables) into a COMMANDS.md file so SKILL.md stays a lean overview of setup, global flags, and composability patterns.
Verify no bundle files are needed at publish time: the body references none, so the skill currently depends on inline content alone for all detail.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is almost entirely executable commands with terse comments and never explains concepts Claude already knows (n8n, REST APIs, jq, git). Every section is operational detail, not padding, so each token earns its place. | 5 / 5 |
Actionability | Commands are copy-paste ready and cover the common cases, e.g. "n8n-cli workflow list --jq '.[].id'", "cat workflow.json | n8n-cli workflow create --stdin", and full promote/apply invocations with concrete JSON payloads. Not below 5: no pseudocode or missing steps are present. | 5 / 5 |
Workflow Clarity | Multi-step processes are clearly sequenced with explicit validation and feedback loops: the Promotions flow is numbered 1-4, apply failure handling is explicit ("Exit 3: the source changed since the review. Review again", "Check $?, or the status field... before you read counts"), and recovery is scripted via apply-continue with expected-* guards — matching anchor 5. | 5 / 5 |
Progressive Disclosure | There are no bundle files (references/, scripts/, assets/ are absent) and everything is inlined in one ~400-line SKILL.md. Section headers are well-organized, but the ~130-line Promotions deep-dive and the bulk command reference clearly belong in one-level-deep reference files — anchor 3 (structure present, but content that should be separate is inline) rather than anchor 4, which expects references to actually be present and clear. | 3 / 5 |
Total | 18 / 20 Passed |