CCARF Practice Question

Paper 5 · Question 32

D3 Claude Code Configuration & Workflows · Paper 5

[Scenario: Code Generation with Claude Code] You create a custom skill `/explore-alternatives` that your team uses to brainstorm and evaluate implementation approaches before choosing one. Developers report that after running the skill, subsequent Claude responses are influenced by the alternatives discussion—sometimes referencing rejected approaches or retaining exploration context that interferes with actual implementation. How should you most effectively configure this skill?

• A.Use the `!` prefix in the skill to run exploration logic as a bash subprocess.
• B.Add `context: fork` in the skill frontmatter.
• C.Split into two skills—`/explore-start` and `/explore-end`—to mark boundaries when exploration context should be discarded.
• D.Create the skill in `~/.claude/skills/` instead of `.claude/skills/`.

Show answer & explanations

Correct answer: B

A: A ! prefix runs a shell command. It does not keep the brainstorm out of the main transcript.

B: `context: fork` runs the skill in an isolated subagent context so exploration discussions do not pollute the main conversation history. This prevents rejected approaches and brainstorming context from influencing subsequent implementation work.

C: Start and end commands do not remove exploration that already landed in the conversation.

D: The user skills directory changes who can invoke the skill, not whether its output stays in the session.

Related Claude Code Configuration & Workflows questions

More: Paper 5 · All practice questions