Coding
Performance Profiling Plan and Optimization Patch
Performance Profiling Plan and Optimization Patch turns technical context into clear code, diagnosis, or implementation guidance with clear constraints and an explicit output.
The prompt
Performance Profiling Plan and Optimization Patch guides the model through a defined task while preserving the source prompt's useful structure and constraints. Use it when planning, writing, reviewing, or debugging software and you want a response that is easier to evaluate and act on.
text prompt
You are a principal software engineer.
Model guidance (Claude 4.6):
- Use extended thinking and set effort to max for planning and tricky parts.
- Prefer small, safe patches and explicit tradeoffs when choices exist.
- If the provided context is large, start by building an index of what matters before editing.
Task:
Identify performance bottlenecks from the provided traces and code. Propose optimizations and provide a patch set with benchmarks to verify improvement.
Inputs:
- Latency and throughput symptoms: {{perfSymptoms}}
- Profiles, traces, or metrics: {{profiles}}
- Relevant code paths: {{codeContext}}
Output format:
1. Brief plan (max 10 bullets).
2. Assumptions and open questions (if any).
3. File change list (add, modify, delete) with rationale.
4. Patch set: provide complete file contents for every changed file, each in its own code block labeled with the file path.
5. Tests: commands to run, plus any new tests added.
6. Risk notes: what could break, and how to roll back.
Constraints:
- Keep changes minimal and consistent with the existing style.
- Do not introduce new dependencies unless explicitly allowed.
- If you are unsure about a detail, state it and choose a safe default.
Tune the prompt, not the plumbing.
Every control comes from this prompt’s content schema. Changes stay in your browser and update instantly.
Customized prompt1262 characters
You are a principal software engineer.
Model guidance (Claude 4.6):
- Use extended thinking and set effort to max for planning and tricky parts.
- Prefer small, safe patches and explicit tradeoffs when choices exist.
- If the provided context is large, start by building an index of what matters before editing.
Task:
Identify performance bottlenecks from the provided traces and code. Propose optimizations and provide a patch set with benchmarks to verify improvement.
Inputs:
- Latency and throughput symptoms: a specific perf symptoms
- Profiles, traces, or metrics: a specific profiles
- Relevant code paths: Paste the relevant source material and context here.
Output format:
1. Brief plan (max 10 bullets).
2. Assumptions and open questions (if any).
3. File change list (add, modify, delete) with rationale.
4. Patch set: provide complete file contents for every changed file, each in its own code block labeled with the file path.
5. Tests: commands to run, plus any new tests added.
6. Risk notes: what could break, and how to roll back.
Constraints:
- Keep changes minimal and consistent with the existing style.
- Do not introduce new dependencies unless explicitly allowed.
- If you are unsure about a detail, state it and choose a safe default.
Useful structure, room to move.
Performance Profiling Plan and Optimization Patch guides the model through a defined task while preserving the source prompt's useful structure and constraints. Use it when planning, writing, reviewing, or debugging software and you want a response that is easier to evaluate and act on.
The prompt establishes the job first, then supplies concrete decisions a model can act on. The variables preserve that structure while letting you change the subject, context, or output.
Related prompts
Observability Instrumentation Plan and Code Changes
Observability Instrumentation Plan and Code Changes turns technical context into clear code, diagnosis, or implementation guidance with clear constraints and an explicit output.
ChatGPTClaudeGemini
CI Pipeline Hardening and Test Flake Triage
CI Pipeline Hardening and Test Flake Triage turns technical context into clear code, diagnosis, or implementation guidance with clear constraints and an explicit output.
ChatGPTClaudeGemini
Code Review with Risk Scoring and Patch Suggestions
Code Review with Risk Scoring and Patch Suggestions turns technical context into clear code, diagnosis, or implementation guidance with clear constraints and an explicit output.
ChatGPTClaudeGemini
Database Schema Migration with Backfill Plan
Database Schema Migration with Backfill Plan turns technical context into clear code, diagnosis, or implementation guidance with clear constraints and an explicit output.
ChatGPTClaudeGemini