Q17 of 60 — CCA Practice Exam

Structured Data Extraction

Your structured data extraction pipeline uses a library of 120+ registered Skills. A post-deployment audit reveals that in roughly 18% of extraction requests involving PDF contracts, Claude is invoking the general-purpose "Processes data" document Skill instead of the dedicated "PDF Contract Extraction" Skill, which correctly handles signatures, clause tables, and nested form fields. Both Skills are registered and functional. What is the most likely root cause of this misrouting?

A. The PDF Contract Extraction Skill's SKILL.md implementation section is too detailed, causing Claude to deprioritize it during discovery in favor of simpler, more concise Skills.

B. The PDF Contract Extraction Skill's description field omits specific trigger terms and use-case context, so Claude cannot reliably distinguish it from the general-purpose Skill when selecting among 120+ candidates.

C. The general-purpose Skill is registered earlier in the Skill library, giving it positional priority during Skill selection when multiple descriptions overlap in scope.

D. The system prompt lacks an explicit instruction to prefer specialized Skills, so Claude defaults to the most broadly applicable Skill rather than the purpose-built one for PDF contracts.