Conciseness

The body is dense and assumes competence — no JS tutorials, no 'what is n8n' padding, and high-value specifics like the per-item cost table and sandbox flags. It falls between anchors 3 and 4 because several key facts repeat: the $helpers-undefined note appears in Essential Rules #5 and again in the Built-ins section, the auto-wrap return behavior is explained in Rules #3, the Return Format section, and Top Mistakes #3, and webhook .body nesting appears three times. Noticeably above the midpoint, but the redundancy is trimmable.

Actionability

Fully executable throughout: quick-start template, mode-specific examples, wrong/right code pairs for returns and webhook access, exact env flags (N8N_BLOCK_ENV_ACCESS_IN_NODE, N8N_RUNNERS_ALLOWED_BUILT_IN_MODULES), and exact failure strings ('Code doesn't return items properly', ReferenceError, paired_item_no_info). Copy-paste ready and covers the common cases; not a 4 because there are no pseudocode gaps.

Workflow Clarity

Clear decision sequencing with explicit checkpoints: a mode-selection guide with a decision shortcut, an ordered transform gatekeeper (expression → IIFE → Code node), wrong/right error-recovery pairs, and a pre-deploy Quick Reference Checklist that functions as validation for batch/deployment risk. Not a 4 because validation checkpoints (checklist, error lookup) are explicit rather than implied.

Progressive Disclosure

Section structure is excellent — every section ends with a well-signaled one-level-deep pointer ('**See**: [DATA_ACCESS.md](DATA_ACCESS.md) → ...') — but the actual bundle contains no referenced files at all: DATA_ACCESS.md, COMMON_PATTERNS.md, ERROR_PATTERNS.md, and BUILTIN_FUNCTIONS.md do not exist in the skill directory, so every link dangles and navigation to the detail content is impossible. This is a genuine organization defect, not the 'minor organization gaps' of anchor 4, but the in-body structure is too good for anchor 2's 'minimal structure'.

Specificity

Lists multiple concrete actions — 'Write JavaScript code in n8n Code nodes', 'making HTTP requests with this.helpers', 'working with dates using DateTime', 'troubleshooting Code node errors', 'choosing between Code node modes', plus 'data aggregation, filtering, API calls, format conversion, batch processing'. Coverage is comprehensive with no vague filler; a 4 would require minor gaps in the action list, which aren't present.

Completeness

Explicitly answers both: what ('Write JavaScript code in n8n Code nodes') and when, with multiple concrete trigger clauses ('Use when writing JavaScript in n8n...', 'Always use this skill when a workflow needs a Code node', 'Also use when asked why a Code node or workflow is slow'). A 4 would need a less explicit 'when', but the triggers here are direct and varied.

Trigger Term Quality

Good natural-phrase coverage: 'writing JavaScript in n8n', 'Code node', 'why a Code node or workflow is slow', 'which execution mode is faster', 'custom data transformation'. Falls between anchors 4 and 5 rather than matching 5 because a few natural variants are missing — notably the legacy 'Function node' name that users on older n8n versions still say, and phrasing around 'n8n expression vs code'.

Distinctiveness Conflict Risk

Clear niche (JavaScript in n8n Code nodes) with distinct triggers, and the EXCEPTION clause explicitly disambiguates from the closely related n8n-code-tool skill for @n8n/n8n-nodes-langchain.toolCode. Minimal conflict risk; a 4 would imply unresolved minor overlap, which the exception clause resolves.