CCDV-F practice question 6 of 10

A teammate has asked how to extend Claude Code with a custom Skill that the team can invoke during sessions. The Skill consists of a set of instructions and a few support scripts the team wants Claude to be able to call when the Skill is loaded. Where is the right place to define the Skill?

Full set: 95 questions
Answer options
A: Define the Skill as a long inline instruction at the top of every CLAUDE.md file in the team’s repositories so Claude has access to it on every session.
B: Define the Skill inside the application’s source code as a regular library module and call it from the application code instead of from Claude Code.
C: Define the Skill in a Skills directory recognized by Claude Code, where Claude can discover and load it during sessions for the team's repositories. Correct answer
D: Define the Skill in a personal scratch directory on each developer's machine and load it manually before each Claude Code session that needs it.
Correct Answer:
C. Define the Skill in a Skills directory recognized by Claude Code, where Claude can discover and load it during sessions for the team's repositories.
Explanation

When extending agentic tools like Claude Code with custom skills or tools intended for team-wide use across multiple repositories, defining them in a recognized, centralized directory (such as a Skills or MCP tools directory) is the best practice. This approach ensures that the skills are modular, easily discoverable by the agent during sessions, and maintainable without cluttering project-specific configuration files or requiring manual loading by each developer.

Why Incorrect

A: Placing long inline instructions at the top of every CLAUDE.md file violates DRY principles, clutters project context, and is highly unmaintainable. B: Defining the skill only in application source code prevents Claude Code from discovering and invoking it directly during interactive sessions. D: Using personal scratch directories prevents team sharing and requires manual, error-prone loading before each session.

References

1. Anthropic Documentation: "Claude Code" - Extending capabilities and managing project context.

2. Anthropic Documentation: "Model Context Protocol (MCP)" - Architecture for extending Claude with custom, discoverable tools and skills.

Scroll to Top