performance-pass

Identify performance bottlenecks in code and route them to a dedicated reviewer.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/Sokoliem/ultraprompt --skill performance-pass-sokoliem
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: performance-pass
Source: https://github.com/Sokoliem/ultraprompt/tree/main/skills/performance-pass
Command: npx skills add https://github.com/Sokoliem/ultraprompt --skill performance-pass-sokoliem

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Identifies and mitigates performance bottlenecks in code by routing issues to a dedicated reviewer discipline that focuses on performance.

Core Features & Use Cases

  • Profiling and bottleneck classification to distinguish I/O, CPU, memory, and concurrency constraints.
  • End-to-end workflow for performance audits, hot path review, latency and throughput improvements, and validated optimizations.
  • Governance and validation ensure changes are measured and safe, with structured evidence and an output contract.

Quick Start

Execute a performance audit on a suspect component and route findings to the reviewer with a focus on performance.

Frequently Asked Questions about performance-pass

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I identify performance bottlenecks in my code?

Performance bottlenecks are identified through profiling and constraint classification across I/O, CPU, memory, and concurrency, routing suspect code to a dedicated reviewer for targeted investigation and validated optimization.

How do I conduct a hot-path review for latency and throughput improvements?

Conduct a hot-path review by running a performance audit on the suspect component and routing the findings to a reviewer for a focused performance investigation, latency reduction, and throughput improvements.

Can I use this for a formal performance audit with structured evidence?

Yes, you can use this for a formal performance audit because it enforces a formal discipline with structured evidence handling, validation, and an explicit output contract to ensure measured and safe optimizations.

What is the best way to profile and classify memory and concurrency constraints?

The best way to profile and classify constraints is to audit the suspect component and route it to the reviewer, which distinguishes between I/O, CPU, memory, and concurrency bottlenecks for targeted optimization.

Do I need any specific profiling dependencies to optimize bottlenecks?

No specific profiling dependencies are required. You can execute a performance audit on a suspect component and route the findings directly to the reviewer for bottleneck classification and optimization.