CCARF Practice Question

Paper 5 · Question 30

D3 Claude Code Configuration & Workflows · Paper 5

[Scenario: Code Generation with Claude Code] Your team created a `/migration` skill that generates database migration files. It takes the migration name via `$ARGUMENTS`. In production you observe three issues: (1) developers often run the skill without arguments, causing poorly named files, (2) the skill sometimes uses database schema details from unrelated prior conversations, and (3) a developer accidentally ran destructive test cleanup when the skill had broad tool access. Which configuration approach fixes all three problems?

• A.Use positional parameters `$1` and `$2` instead of `$ARGUMENTS` to enforce specific inputs, include explicit schema file references via `@` syntax for context control, and add a frontmatter description warning about destructive operations.
• B.Add `argument-hint` in frontmatter to request required parameters, use `context: fork` to isolate execution, and restrict `allowed-tools` to file-write operations.
• C.Split into `/migration-create` and `/migration-apply` skills, add validation instructions to request migration name if missing, and use different `allowed-tools` scopes for each.
• D.Add validation instructions in the skill SKILL.md to ensure `$ARGUMENTS` is a valid name, add prompts to ignore prior conversation context, and list prohibited operations to avoid.

Show answer & explanations

Correct answer: B

A: Positional parameters do not prompt on a bare invocation, an @include does not isolate earlier chat, and a description warning does not remove a destructive tool.

B: This uses three separate configuration features to address each problem: `argument-hint` improves argument entry and reduces missing arguments, `context: fork` prevents context leakage from prior conversations, and `allowed-tools` constrains the skill to safe file-writing operations, preventing destructive actions. On the exam, treat allowed-tools as the restriction the study guide describes: it bounds what the skill may invoke.

C: Two skills can split create and apply, but they do not by themselves isolate context or stop a bare run.

D: Instructions to ignore prior context and avoid dangerous operations are still prompts. They do not fork the session or remove the tools.

Related Claude Code Configuration & Workflows questions

More: Paper 5 · All practice questions