Conciseness

The body is lean and assumes Python competence: dense tables (inputs, migration, sandbox limits, return shapes, onError matrix) with no re-teaching of basic Python or generic n8n concepts, e.g. 'Everything else in plain Python works (verified): comprehensions, generators, lambdas...'. Version pins ('Observed on n8n 2.38.5') are provenance notes with an explicit re-check caveat rather than date-conditional instructions, so the time-sensitivity penalty does not apply; every token earns its place, matching the 5 anchor.

Actionability

Copy-paste-ready code for both modes ('return [{"json": ...} for it in _items ...]', 'row = _item["json"]'), exact node config JSON, a legacy-to-native migration table with literal replacements, a one-line import probe ('import json + return [{"json": {"ok": True}}}]'), and exact fixes paired to exact error strings ('NameError: name 'type' is not defined' → 'isinstance(x, dict)'). Fully executable guidance covering the common cases, matching the 5 anchor.

Workflow Clarity

The decision flow is clear and sequenced: JavaScript first (with an explicit fallback gatekeeper), mode/variable matching, dict-only access, no unconfirmed imports, correct return shape — culminating in a Checklist with an explicit validation checkpoint ('Ran a real test execution and inspected the output items (validation alone won't catch the traps above)') and feedback loops (the import probe node, 'test-run before relying on it' for pairedItem). This matches the 5 anchor (clear sequence, explicit validation, feedback loops, checklist) rather than the 4 anchor's minor validation gaps.

Progressive Disclosure

Sections are well organized and the single reference is clearly signaled and one level deep ('**[COMMON_PATTERNS.md](COMMON_PATTERNS.md)**: 12 import-free patterns, each verified on a live n8n instance'), but that referenced file does not exist anywhere in the bundle — no references/ directory and no COMMON_PATTERNS.md — so the link is dangling and the promised detailed content is unavailable. This is above the 3 anchor (the reference is clearly signaled and no detail content is inlined) but the broken reference is more than the 5 anchor's 'easy navigation' allows.

Specificity

The description names the domain ('Write Python in n8n Code nodes (native Python, `language` pythonNative, n8n 2.x)') and enumerates concrete capabilities: 'the only two variables (_items/_item), dict-only access, imports blocked by default, the sandbox's denied builtins, accepted return shapes, and how errors interact with onError'. This is comprehensive coverage of multiple specific actions, matching the 5 anchor; it exceeds the 4 anchor because no meaningful capability gaps are evident.

Completeness

Both 'what' and 'when' are explicit: the what is 'Write Python in n8n Code nodes' with an enumerated scope, and the when is a literal 'Use when the user explicitly wants Python in a Code node, when migrating old Pyodide/'Python (Beta)' code..., or when a Python Code node fails with [concrete error messages]'. This mirrors the 5 anchor's structure (concrete capability statement plus explicit trigger phrases), so it cannot be capped at 3 or reduced to 4.

Trigger Term Quality

It includes the natural phrases users would actually say or paste: 'Python in a Code node', 'Python (Beta)', 'Pyodide', '_input/_json/_node/_now', plus verbatim error strings ('Security violations detected', '__build_class__ not found', 'A 'json' property isn't a dictionary', 'Python runner unavailable'). Coverage including synonyms and exact failure messages matches the 5 anchor; it is well above the 4 anchor, which expects only a few missing natural terms.

Distinctiveness Conflict Risk

The niche is precise (native Python in n8n Code nodes, pythonNative, n8n 2.x) and it actively disambiguates adjacent skills: 'JavaScript is the default for Code nodes' and 'EXCEPTION — for Python in the AI-agent-callable Custom Code Tool (@n8n/n8n-nodes-langchain.toolCode), use the n8n-code-tool skill instead'. Clear distinct triggers with minimal conflict risk, matching the 5 anchor rather than the 4 anchor's 'minor overlap risk'.