Content
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The body delivers genuinely expert, actionable n8n guidance — the validation lifecycle, SplitInBatches semantics, performance model, and integration gotchas are excellent. It is let down by length/filler (generic component lists, percentage statistics) and by progressive-disclosure gaps where referenced pattern files are missing and content that belongs in them is inlined.
Suggestions
Create the referenced pattern files (webhook_processing.md, http_api_integration.md, database_operations.md, ai_agent_workflow.md, scheduled_tasks.md) or remove the dead links, so the 'Detailed Pattern Files' navigation actually resolves.
Trim the generic 'Common Workflow Components' and 'Pattern Statistics' sections — these are either common knowledge or unsourced figures — to tighten conciseness.
Move the inline 'Quick Start Examples', 'Real Template Examples', and per-pattern detail into the pattern reference files so SKILL.md stays a lean overview.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean, high-value sections (the batchSize cost model, validation lifecycle, integration gotchas) earn their tokens, but the body is ~540 lines padded with generic 'Common Workflow Components' building blocks and a dubious 'Pattern Statistics' (e.g. 'Webhook - 35%') that reads as filler. Matches score-2 'mostly efficient but includes some unnecessary explanation', not score-3 'every token earns its place'. | 2 / 3 |
Actionability | Provides executable JavaScript blocks (the dry-run verification snippet, the Math.abs threshold check), specific node/operation names ('NEVER use append', 'convertToGoogleDocument: true', 'values.update PUT'), and concrete MCP tool calls (validate_workflow, n8n_test_workflow, activateWorkflow). This is a pattern/instruction skill whose guidance is specific and actionable, meeting the score-3 bar. | 3 / 3 |
Workflow Clarity | The 'validate, verify, test, activate' lifecycle is a clear four-gate sequence with explicit validation checkpoints, a fix-and-re-validate feedback loop, and a full creation checklist — exactly the score-3 anchor of 'clear sequence with explicit validation steps; feedback loops for error recovery; checklists'. | 3 / 3 |
Progressive Disclosure | Pattern files are signaled with proper markdown links and a dedicated 'Detailed Pattern Files' section, but the referenced bundle files (webhook_processing.md, http_api_integration.md, etc.) do not exist in references/scripts/assets, and the 540-line body keeps statistics, component lists, and examples inline that would belong in those files. Matches score-2 'content that should be separate is inline', falling short of score-3 'appropriately split'. | 2 / 3 |
Total | 10 / 12 Passed |