team-perf-opt

Orchestrate a staged performance optimization pipeline with profiling, benchmarking, and review.

76|5|Updated Jul 7, 2026
One-click install
npx skills add https://github.com/catlog22/pi-maestro-flow --skill team-perf-opt-catlog22
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: team-perf-opt
Source: https://github.com/catlog22/pi-maestro-flow/tree/main/.pi/skills/team-perf-opt
Command: npx skills add https://github.com/catlog22/pi-maestro-flow --skill team-perf-opt-catlog22

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill turns a slow, serial performance tuning effort into a coordinated multi-agent workflow that can profile, plan, implement, benchmark, and review optimizations with clear ownership and checkpoints.

Core Features & Use Cases

  • End-to-end performance workflow: Runs profiling, strategy design, code changes, benchmarking, and review as a staged pipeline.
  • Parallel execution modes: Supports single, fan-out, and independent pipeline shapes for one or many optimization targets.
  • Guardrails and recovery: Enforces dependencies, review-fix cycles, branch-scoped artifacts, and validation before completion.
  • Use Case: Optimize a backend service by profiling hot paths, generating a prioritized plan, applying fixes, and verifying improvements without losing track of branches or regressions.

Quick Start

Ask the skill to profile your project, produce an optimization plan, implement the highest-priority changes, and verify the results with benchmarking and review.

Frequently Asked Questions about team-perf-opt

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

FAQPage Schema
How do I coordinate multi-agent performance optimization across profiling and benchmarking?

Multi-agent performance optimization is coordinated through a staged pipeline that runs profiling, strategy design, code changes, benchmarking, and review with clear ownership and validation checkpoints. This ensures correctness while improving speed.

What is the best way to automate code review and benchmarking for parallel optimization pipelines?

Automating code review and benchmarking for parallel pipelines requires enforced review-fix cycles and validation gates. The workflow maintains branch-scoped artifacts to verify improvements and catch regressions before completion.

Can I run fan-out and independent optimization workflows for multiple backend service targets?

Yes, fan-out and independent optimization workflows support multiple backend service targets. The pipeline shapes allow single-path optimization for one target or parallel execution for many independent codebase hot paths simultaneously.

How does profiling hot paths work with task coordination in a multi-agent workflow?

Profiling hot paths with task coordination uses persistent session state to track progress across agents. It generates a prioritized optimization plan, applies fixes, and verifies results through structured stages without losing branch context.

When should I not use parallel pipelines for performance tuning?

Parallel pipelines for performance tuning should be avoided when codebase targets have tight interdependencies. Independent workflows require branch-scoped artifacts and validation gates to prevent regressions, which may not suit highly coupled single-path modifications.