Claude Code Configuration & Workflows Quiz - Certifications Claude Architect Foundations

Free practice quiz: Claude Code Configuration & Workflows (Certifications Claude Architect Foundations). 70 multiple-choice questions with answers and explanations. Play online, no sign-up needed.

This Certifications Claude Architect Foundations practice quiz has 70 multiple-choice questions on Claude Code Configuration & Workflows, and 70 of them come with an explanation. Try the 5 sample questions below (tap an option to check yourself), then play the full quiz online. No sign-up needed.

Sample questions

1. What is the most likely reason the new team members do not get these instructions?

   1. Because they are in a user-level CLAUDE.md file not shared via version control.
   2. Because the new members need to run /init to generate their own CLAUDE.md first.
   3. Because they were not referenced with @import from the project CLAUDE.md.
   4. Because project instructions must be placed in CLAUDE.local.md to be shared.
   Show answer

   Answer: A. Because they are in a user-level CLAUDE.md file not shared via version control.

   User-level memory applies only to that user's sessions and is not shared with teammates. Team-shared instructions must be placed in a project-level CLAUDE.md that is committed to version control.

2. What configuration change most directly prevents this skill's output from polluting the main conversation while still preserving its results?

   1. Run /compact immediately after each skill invocation.
   2. Move the skill's instructions into CLAUDE.md.
   3. Add context: fork to the skill frontmatter.
   4. Add allowed-tools: Read to keep the skill from editing files.
   Show answer

   Answer: C. Add context: fork to the skill frontmatter.

   context: fork runs the skill in an isolated sub-agent context and returns only a summarized result to the main conversation, so verbose output does not pollute the session. allowed-tools restricts which tools the skill may use but has no effect on output volume. Running /compact after the fact or moving the skill into CLAUDE.md does not isolate the skill's output.

3. What is the most effective way to apply one consistent set of testing conventions to all of these files regardless of directory?

   1. Keep the per-directory CLAUDE.md files and add a script that keeps those copies synchronized
   2. Add one root CLAUDE.md section for testing conventions and remove all subdirectory CLAUDE.md files
   3. Create a testing skill and require running /testing manually before editing any test file
   4. Create a path-scoped .claude/rules/ testing rule matching all test files and remove duplicate instructions
   Show answer

   Answer: D. Create a path-scoped .claude/rules/ testing rule matching all test files and remove duplicate instructions

   A glob-pattern rule applies to all matching test files wherever they live, avoiding duplication and ensuring consistency. A root CLAUDE.md would load for every file in every session, duplication and scripts remain fragile, and a manually invoked skill does not activate automatically when editing tests.

4. What is the best first step in Claude Code?

   1. Ask an Explore subagent to decide which approach is better and implement it.
   2. Implement both approaches in separate branches, then ask Claude Code to run benchmarks.
   3. Ask Claude to implement the PostgreSQL full-text search directly because it requires no new infrastructure.
   4. Use plan mode to explore the current data layer and produce a plan comparing the approaches before deciding.
   Show answer

   Answer: D. Use plan mode to explore the current data layer and produce a plan comparing the approaches before deciding.

   Choosing between integration approaches with different infrastructure requirements is an architectural decision. Plan mode lets Claude safely explore and design before committing to code, preventing a premature choice that may be costly to reverse.

5. How should the developer sequence the fixes?

   1. Fix both failures in one message so Claude sees the full migration context and avoids duplicate work.
   2. Fix one general issue such as error handling first, then apply that pattern to both failures.
   3. Fix the failures sequentially, completing and verifying the first before starting the second.
   4. Write one shared regression test for both failures, then ask Claude to fix the first failing assertion.
   Show answer

   Answer: C. Fix the failures sequentially, completing and verifying the first before starting the second.

   Independent problems should be fixed sequentially so each change can be verified in isolation and regressions are easy to attribute. Combining independent issues in a single message creates a larger diff and makes it harder to isolate any new failure.

More questions in this quiz

Answers and explanations are in the full quiz.

1. What is the best way to make each package's CLAUDE.md include only its relevant standards without duplicating content?
2. What is the most effective structural change to ensure testing instructions are consistently available to the review agent?
3. How should the team configure each pipeline's CLAUDE.md so only the relevant domain standards are loaded per job?
4. Which location will make the rule apply to all team members only when they work in packages/api and not affect other packages?
5. What is the most likely reason the teammate's Claude Code did not follow the instruction?
6. What is the best way to organize these instructions?
7. What should the team check first to explain the inconsistency?
8. What is the most effective approach for maintainers to set this up?
9. Where should the deploy guidance be moved so it loads only for work in packages/billing?
10. What is the most effective way to make each package load only its own standards without duplicating the shared standards?
11. What is the best next action to align the first analyst's behavior with the team's snake_case rule?
12. What is the most effective fix to make /deploy available to the whole team?
13. What is the most maintainable way to prompt developers for the required order_id when they invoke /refund without arguments?
14. What is the best way to create this personal customization without affecting teammates?
15. Where should the team create this command?
16. Which frontmatter option best isolates this exploratory context from the main session?
17. Where should the command file be defined so it is personal and not shared through version control?
18. Which frontmatter field should you add so Claude Code prompts for the missing order ID at invocation?
19. What is the best frontmatter change to keep this verbose skill output from polluting the main conversation?
20. What is the best way to create your personal variant?
21. Which frontmatter option should be added to the skill to preserve the main session context?
22. Which frontmatter change is the most effective way to prevent this skill from running destructive Bash commands while still allowing file creation?
23. What is the best way to reduce constant context load while keeping both sets of guidance available to the team?
24. Which frontmatter change best prevents the skill from executing shell commands or modifying files during its analysis?
25. Which configuration best applies these conventions conditionally without loading irrelevant rules for configuration files or other packages?
26. What change most directly reduces irrelevant context and token use while ensuring each rule still applies when its file type is edited?
27. Which file and frontmatter best implements this conditional loading?
28. What is the best way to apply the single API error convention to all these TypeScript service source files while avoiding duplicate instructions?
29. Which setup is the best way to make these Go conventions load only when Claude Code works with Go files?
30. Which restructuring is the most effective first step?
31. Which approach best enforces that policy across the entire test suite during automated reviews?
32. What should the new rule file contain?
33. Which approach best applies the conventions across all spec files without overloading unrelated sessions?
34. Which approach is the best way to apply one consistent set of Dockerfile conventions to all Dockerfiles without loading those rules for unrelated source files?
35. What is the most effective way to enforce the migration policy for all SQL migration files while avoiding drift from directory-level instructions?
36. Which corrected paths list should be used so the rule applies to all Storybook stories across the repository regardless of directory or story-file suffix?
37. What is the best first step for this migration?
38. What is the most appropriate way to handle this change with Claude Code?
39. Why is it most important to switch to plan mode before asking Claude to make any edits in this situation?
40. What is the most appropriate way to use Claude Code right now?
41. What is the most appropriate way to handle this change with Claude Code?
42. What is the most effective first step in Claude Code to avoid another costly rework?
43. What should you ask Claude Code to do first?
44. What is the most appropriate first step with Claude Code?
45. What is the most appropriate way to handle this change with Claude Code?
46. What is the best next step after approving the plan?
47. Which sequence best follows Claude Code guidance for this task?
48. What is the best way to perform this discovery?
49. What is the most effective change to make to the prompt to fix the inconsistent phone number formatting?
50. How should the developer communicate these findings to Claude?
51. What should the developer add to the prompt to get consistent output?
52. What is the most effective first step to ensure the implementation meets these requirements?
53. What is the most effective way to communicate the required transformation?
54. How should the developer communicate these two failures to Claude Code?
55. What is the most effective first instruction to give Claude Code?
56. What is the best change to stop the CI step from hanging?
57. What is the best change to prevent the CI job from hanging on interactive input?
58. What is the best change to enforce the exact JSON shape?
59. What is the most effective way to produce findings the bot can post inline reliably?
60. What most likely explains why the in-session review missed these defects?

More quizzes

• Prompt Engineering & Structured Output▶ Play
• Tool Design & MCP Integration▶ Play
• Agentic Architecture & Orchestration▶ Play

Browse all Claude Architect Foundations quizzes

More to play