Content
77%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.
The body is highly actionable with exact tool-call syntax, nodeType format distinctions, and validation-first workflows that include explicit feedback loops. Its weaknesses are redundancy (repeated timing statistics and a Summary that restates prior sections) and a broken progressive-disclosure structure: three guide files are referenced but absent from the bundle while substantial reference material remains inlined.
Suggestions
Ship the referenced bundle files (SEARCH_GUIDE.md, VALIDATION_GUIDE.md, WORKFLOW_GUIDE.md) or remove the references — as delivered, the skill's detailed-guide navigation points to files that do not exist.
Cut cross-section duplication: drop the repeated timing statistics (18s/23s/58s/56s figures appear 4+ times) and trim the 8-point Summary to only the nodeType-format distinction and profile recommendation not already stated verbatim elsewhere.
Move the Unified Tool Reference, Performance Characteristics table, and Template Usage sections into the referenced guide files so SKILL.md serves as a lean overview with working one-level-deep references.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Each section is individually dense and free of explanations of known concepts, but content is noticeably duplicated across sections: the timing stats ("18s average", "23s thinking, 58s fixing", "56s average between edits") recur 4+ times, and the Summary restates 8 points already covered, so it could be tightened considerably. Not 2 because there is no fluff or padding of concepts Claude already knows; not 4 because the cross-section repetition goes beyond minor. | 3 / 5 |
Actionability | Fully concrete, parameter-exact tool calls throughout — e.g. `get_node({nodeType: "nodes-base.slack", detail: "standard"})`, `validate_node({nodeType, config, profile: "runtime"})`, `n8n_update_partial_workflow({id, intent, operations: [...]})` — with WRONG/CORRECT contrasts covering the dominant use cases. Not 4 because the examples are copy-paste ready and span the common cases comprehensively. | 5 / 5 |
Workflow Clarity | Multi-step processes are clearly sequenced with explicit validation checkpoints and a feedback loop: "validate → fix → validate" with error checking ("if (!result.valid) { ... Validate again"), the 7-step common workflow (search → get_node → validate → create → validate → update → activate), and "Validate after every significant change" in the Do list. Not 4 because checkpoints are explicit in every build/manage workflow, not merely present for some. | 5 / 5 |
Progressive Disclosure | References are clearly signaled and one level deep ("See SEARCH_GUIDE.md for: ..."), but those referenced files (SEARCH_GUIDE.md, VALIDATION_GUIDE.md, WORKFLOW_GUIDE.md) do not exist in the bundle, and ~640 lines of detailed tool reference, performance tables, and template usage are inlined in SKILL.md. Scored against the actual bundle structure, this fits "some structure but could be better organized; content that should be separate is inline" — not 4/5 because the navigation promise is broken by missing files; not 2 because section structure is good and references are prominently signaled, not buried. | 3 / 5 |
Total | 16 / 20 Passed |