Conciseness

The body is dense with genuinely specialist data (penalty multipliers, filing deadlines, form numbers, thresholds), but notable portions re-teach concepts Claude already knows: 'The Harmonized System is a 6-digit international nomenclature maintained by the WCO', full Incoterms 2020 definitions (EXW/FCA/CIP/DDP), 'Ocean BOL serves as title to goods, contract of carriage, and receipt', and the complete GRI enumeration. These could be trimmed or pushed to references. Not a 2 because most lines carry non-obvious, compliance-critical specifics rather than padding.

Actionability

Concrete, executable guidance throughout: a 7-step classification sequence, a 6-step FTA qualification procedure with RVC formulas, a hierarchical valuation method selection, a screening protocol with explicit thresholds ('Matches below 85% name similarity with no address or country correlation are likely false positives'), message templates with subject-line formats, and escalation tables with timelines. Not a 5 because several steps defer to external lookups (FTA annexes, ruling databases) and the full detail lives in the reference files rather than being copy-paste ready inline.

Workflow Clarity

Multi-step processes are clearly sequenced with validation checkpoints: classification includes conditional branching ('If GRI 1 produces multiple candidate headings, apply GRI 2 then GRI 3'), subheading-level validation, binding-ruling checks, and mandatory rationale documentation; screening hit assessment is an explicit assess-verify-check-escalate loop with a hard stop ('Never proceed with a transaction while a screening hit is unresolved'). Not a 5 because some verification steps are implicit (e.g., no re-validation loop after correcting a classification) and the escalation chain lacks a defined failure path.

Progressive Disclosure

References are well-signaled and verified real: decision-frameworks.md (764 lines), edge-cases.md (362 lines), and communication-templates.md (631 lines) all exist, are one level deep (no nested references inside them), and are summarized inline with pointers ('Brief summaries here — see edge-cases.md for full analysis') plus an 'Additional Resources' index. Not a 5 because the ~230-line body still inlines substantial material that could live in references (full GRI enumeration, regional specialties, penalty schedules) and the duplicated 'When to Use' section (top and bottom) is an organization flaw.

Specificity

The description lists several specific capability areas — 'customs documentation, tariff classification, duty optimisation, restricted party screening, and regulatory compliance' — going beyond a bare domain name. It falls short of 5 because these are noun-phrase domains under a vague container ('Codified expertise for') rather than concrete actions like 'classify goods under HS codes' or 'prepare entry documentation'.

Completeness

The 'what' is clear (documentation, classification, duty optimisation, screening, compliance), but there is no 'Use when...' clause or equivalent explicit trigger guidance anywhere in the description; 'across multiple jurisdictions' scopes the domain, not the trigger. Per the rubric guideline, a missing 'Use when' clause caps completeness at 3.

Trigger Term Quality

Natural terms users would say are present: 'customs', 'tariff classification', 'duty', 'restricted party screening', 'regulatory compliance'. A few commonly used natural phrases are missing — 'HS codes', 'Incoterms', 'import/export', 'free trade agreements' — which keeps it below the comprehensive-synonym level of 5.

Distinctiveness Conflict Risk

Customs and trade compliance is a clear niche with distinct, unambiguous triggers (tariff classification, restricted party screening, duty optimisation); there is minimal overlap risk with any adjacent skill. It is not below 5 because no broader or generic capability terms appear that would pull in unrelated skills.