Filter:
QuestionTask 3.1

A new teammate clones the repo but never gets your conventions. Why, and the fix?

Space to flip
AnswerTask 3.1

The instructions live in user-level ~/.claude/CLAUDE.md, which is not shared via version control. Move them into project-level config (.claude/CLAUDE.md or root CLAUDE.md).

← → navigate
QuestionTask 3.1

What are the three levels of the CLAUDE.md hierarchy?

Space to flip
AnswerTask 3.1
  • User~/.claude/CLAUDE.md (personal)
  • Project.claude/CLAUDE.md or root CLAUDE.md (shared)
  • Directory — a CLAUDE.md inside a subdirectory
← → navigate
QuestionTask 3.1

Two ways to keep CLAUDE.md modular instead of one monolithic file?

Space to flip
AnswerTask 3.1

Use @import (@.claude/rules/testing.md) so each package pulls only relevant standards; or split into topic files under .claude/rules/testing.md, api-conventions.md, deployment.md.

← → navigate
QuestionTask 3.1

Behavior is inconsistent across sessions — which command diagnoses it?

Space to flip
AnswerTask 3.1

/memory — it shows which memory (CLAUDE.md) files are currently loaded, so you can spot a missing or unexpected one.

← → navigate
QuestionTask 3.2

Where do you create a /review command so every developer gets it on clone?

Space to flip
AnswerTask 3.2

.claude/commands/ — project-scoped, shared via version control. Not ~/.claude/commands/ (personal), not CLAUDE.md, and there is no .claude/config.json commands array.

← → navigate
QuestionTask 3.2

Where do skills live, and what configures their behavior?

Space to flip
AnswerTask 3.2

.claude/skills/ with a SKILL.md file whose frontmatter supports context: fork, allowed-tools, and argument-hint.

← → navigate
QuestionTask 3.2

What does context: fork do in skill frontmatter?

Space to flip
AnswerTask 3.2

Runs the skill in an isolated sub-agent context, so verbose output (codebase analysis) or exploratory context (brainstorming) doesn't pollute the main conversation.

← → navigate
QuestionTask 3.2

What do allowed-tools and argument-hint do?

Space to flip
AnswerTask 3.2

allowed-tools restricts tool access during skill execution (e.g. limit to file writes to prevent destructive actions). argument-hint prompts the developer for required parameters when the skill is invoked without arguments.

← → navigate
QuestionTask 3.2

When choose a skill vs CLAUDE.md — and where do personal skill variants go?

Space to flip
AnswerTask 3.2

Skill = on-demand, task-specific workflow; CLAUDE.md = always-loaded universal standards. Create personal variants in ~/.claude/skills/ under a different name to avoid affecting teammates.

← → navigate
QuestionTask 3.3

Test files are scattered across directories — how do you apply one convention automatically?

Space to flip
AnswerTask 3.3

A .claude/rules/ file with YAML frontmatter paths: glob — e.g. paths: ["**/*.test.tsx"] — which loads only when Claude edits a matching file.

← → navigate
QuestionTask 3.3

What's the benefit of path-scoped rules' conditional loading?

Space to flip
AnswerTask 3.3

Rules load only when editing matching files, so irrelevant context stays out and token usage drops — only the conventions relevant to the current file are present.

← → navigate
QuestionTask 3.3

When choose path-specific rules over a subdirectory CLAUDE.md?

Space to flip
AnswerTask 3.3

When a convention must apply to files of a type spread across many directories (**/*.test.tsx). A subdirectory CLAUDE.md is directory-bound and can't follow scattered files.

← → navigate
QuestionTask 3.3

Trap: why not use root-CLAUDE.md headers or per-type skills for path conventions?

Space to flip
AnswerTask 3.3

Root headers rely on Claude inferring which section applies (not explicit matching); skills require manual invocation (not automatic path matching). Path-scoped rules match explicitly and load automatically.

← → navigate
QuestionTask 3.4

When do you use plan mode?

Space to flip
AnswerTask 3.4

For complex tasks — large-scale changes, multiple valid approaches, architectural decisions, multi-file modifications (e.g. a microservice restructuring or a library migration affecting 45+ files).

← → navigate
QuestionTask 3.4

When is direct execution appropriate?

Space to flip
AnswerTask 3.4

For simple, well-scoped changes — a single validation check, a one-file bug fix with a clear stack trace, adding a date-validation conditional.

← → navigate
QuestionTask 3.4

Why enter plan mode first for an architectural task — not "only if complexity emerges"?

Space to flip
AnswerTask 3.4

Plan mode enables safe exploration and design before committing to changes, preventing costly rework. For architectural work the complexity is already known from the requirements.

← → navigate
QuestionTask 3.4

What is the Explore subagent for, and how does plan mode combine with direct execution?

Space to flip
AnswerTask 3.4

The Explore subagent isolates verbose discovery output and returns summaries, preserving the main context window. Combine the two: plan mode to investigate, then direct execution to implement the planned approach.

← → navigate
QuestionTask 3.5

Prose descriptions get interpreted inconsistently — most effective fix?

Space to flip
AnswerTask 3.5

Provide 2–3 concrete input/output examples of the transformation — examples communicate expected behavior more reliably than prose.

← → navigate
QuestionTask 3.5

What is test-driven iteration?

Space to flip
AnswerTask 3.5

Write a test suite (behavior, edge cases, performance) first, then iterate by sharing failing tests to guide progressive improvement. Give specific input/expected-output cases for edge cases (e.g. null values in migration scripts).

← → navigate
QuestionTask 3.5

What is the interview pattern, and when use it?

Space to flip
AnswerTask 3.5

Have Claude ask questions to surface considerations you may not have anticipated (cache-invalidation strategy, failure modes) before implementing — especially valuable in unfamiliar domains.

← → navigate
QuestionTask 3.5

When provide all issues in one message vs sequentially?

Space to flip
AnswerTask 3.5

One detailed message when the issues interact (fixes affect each other); fix them sequentially when the issues are independent.

← → navigate
QuestionTask 3.6

Your CI job running claude "…" hangs on interactive input. Fix?

Space to flip
AnswerTask 3.6

Add the -p (--print) flag to run non-interactively. (Wrong answers: CLAUDE_HEADLESS=true, --batch, and redirecting stdin from /dev/null — none of these is the correct mechanism.)

← → navigate
QuestionTask 3.6

How do you get machine-parseable findings to post as inline PR comments?

Space to flip
AnswerTask 3.6

Use --output-format json together with --json-schema to enforce structured output that automation can parse and post.

← → navigate
QuestionTask 3.6

How do you give CI-invoked Claude Code project context, and avoid duplicate tests?

Space to flip
AnswerTask 3.6

Document testing standards, fixture conventions, and review criteria in CLAUDE.md. Provide existing test files in context so generated tests don't duplicate scenarios already covered.

← → navigate
QuestionTask 3.6

Re-running a review after new commits — how do you avoid duplicate comments?

Space to flip
AnswerTask 3.6

Include the prior review findings in context and instruct Claude to report only new or still-unaddressed issues.

← → navigate
QuestionTask 3.6

Why not reuse the same session that generated the code to review it?

Space to flip
AnswerTask 3.6

Session context isolation: the session that generated the code is less effective at reviewing its own changes. Use an independent review instance.

← → navigate

Keyboard: navigate · Space flip · S shuffle · R restart · G got it · V review again