Claude Code Debug: Performance Profile

What this prompt does

Find and verify a performance bottleneck with repository-aware safeguards. It is designed for performance profile and works best with Current Claude Code model configured for the repository.

Customize and copy

This is a reusable natural-language prompt for Claude Code, not a shell command.

Work in the repository at [REPOSITORY_OR_PATH]. Goal: find and verify a performance bottleneck. Context: [CONTEXT]. Constraints: [CONSTRAINTS]. Definition of done: [ACCEPTANCE_CRITERIA].

Reproduce first, gather evidence, rank hypotheses, and change code only after identifying the likely cause.

Read applicable CLAUDE.md guidance and use Claude Code’s repository tools and permission model; do not assume an interactive slash command or CLI flag is available.

First read the repository instructions and relevant framework documentation. Preserve unrelated user changes. State assumptions, cite files and lines for findings, and ask only when a missing decision would materially change the result. Do not invent APIs, commands, flags, test results, or file contents. Deliver: baseline, instrumentation, bottleneck, and benchmark. Run the repository’s relevant formatting, lint, type, test, and build checks when authorized, and report exact results.

How to use it

Replace the bracketed variables with real context for performance profile. Attach or paste source material when available, and verify consequential facts before acting.

Example input

Provide a real performance profile brief with the audience, goal, constraints, preferred format, and any available source material filled into the prompt’s placeholders.

Sample output

Find and verify a performance bottleneck with repository-aware safeguards. The finished response should apply that result to performance profile, follow the requested structure, distinguish supplied facts from inference, and end with usable next actions.

Quality checklist

• The response directly addresses the performance profile goal and intended audience.
• Every requested section or output format is present and materially complete.
• Unsupported facts are removed, sourced, or clearly marked for verification.
• The final result is specific enough to use without guessing what happens next.

Limitations and review notes

Run generated code in an isolated branch, review the diff, and execute the repository test suite before merging.

This page records an editorial structure and safety review, not a guarantee that every provider or model version will produce the same result. See the Promptle testing methodology.

Related prompts