performance-analysis

Detect bottlenecks in Claude Flow swarms and generate performance reports.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/thepingdoctor/kumo-mta-ui --skill performance-analysis-thepingdoctor
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: performance-analysis
Source: https://github.com/thepingdoctor/kumo-mta-ui/tree/main/.claude/skills/performance-analysis
Command: npx skills add https://github.com/thepingdoctor/kumo-mta-ui --skill performance-analysis-thepingdoctor

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Identifying and resolving performance bottlenecks in complex AI swarm operations can be challenging and time-consuming. This Skill provides a comprehensive suite for performance analysis, bottleneck detection, and automated optimization, ensuring your Claude Flow swarms run efficiently and cost-effectively.

Core Features & Use Cases

  • Bottleneck Detection: Automatically identify communication, processing, memory, and network bottlenecks with configurable thresholds.
  • Performance Profiling: Gain real-time insights and historical analysis of agent utilization, task completion times, and resource contention.
  • Report Generation: Create detailed performance reports in JSON, HTML, or Markdown, including comparative analysis and actionable recommendations.
  • Use Case: Your development swarm is running slowly. Use this Skill to detect bottlenecks. It identifies that agent communication is delayed due to an inefficient topology. The Skill then recommends switching to a hierarchical topology and can even auto-fix the issue, leading to a 40% improvement in message delivery.

Quick Start

Basic bottleneck detection for current swarm

npx claude-flow bottleneck detect

Generate HTML performance report with all metrics

npx claude-flow analysis performance-report --format html --include-metrics

Analyze and auto-fix detected issues

npx claude-flow bottleneck detect --fix --threshold 15