How does it integrate with my existing CI/CD workflow?

The skill can be run via npx commands in GitHub Actions or other CI pipelines to export JSON metrics and fail builds if performance thresholds are not met.

What report formats are supported?

The skill can generate detailed performance reports in HTML for visualization, Markdown for documentation, and JSON for integration with other tools.

What types of bottlenecks can this skill detect?

It analyzes four main areas: communication (queue delays), processing (utilization rates), memory (cache hit rates), and network (API latency).

Can the Performance Analysis skill automatically fix issues?

Yes, by using the --fix flag, the skill can automatically apply optimizations such as adjusting agent priorities, enabling smart caching, and optimizing message routing.

Performance Analysis for Claude Flow

Name: Performance Analysis for Claude Flow
Author: while-basic

bywhile-basic

분석 및 모니터링

Analyzes and optimizes Claude Flow swarm performance by detecting bottlenecks and providing actionable AI-powered recommendations.

소개

The Performance Analysis skill is a comprehensive suite designed to monitor and optimize multi-agent swarm operations within the Claude Flow ecosystem. It provides deep visibility into communication overhead, processing delays, and resource utilization, enabling developers to identify hidden bottlenecks through real-time profiling. Beyond simple monitoring, the skill offers automated report generation in multiple formats and an intelligent 'auto-fix' feature that applies optimization patterns like topology adjustments and caching enhancements to significantly reduce task execution time.

주요 기능

Multi-dimensional bottleneck detection across communication, processing, and memory
Automated report generation in HTML, JSON, and Markdown formats
0 GitHub stars
Real-time swarm profiling and historical performance monitoring
AI-powered optimization recommendations with programmatic auto-fix capabilities
Deep Model Context Protocol (MCP) integration for automated performance audits

사용 사례

Diagnosing high latency and message delivery delays in complex multi-agent workflows
Integrating performance threshold checks into CI/CD pipelines to prevent regressions
Optimizing swarm topologies and caching strategies for resource-intensive AI tasks

소개

주요 기능

Multi-dimensional bottleneck detection across communication, processing, and memory
Automated report generation in HTML, JSON, and Markdown formats
0 GitHub stars
Real-time swarm profiling and historical performance monitoring
AI-powered optimization recommendations with programmatic auto-fix capabilities
Deep Model Context Protocol (MCP) integration for automated performance audits

사용 사례

Diagnosing high latency and message delivery delays in complex multi-agent workflows
Integrating performance threshold checks into CI/CD pipelines to prevent regressions
Optimizing swarm topologies and caching strategies for resource-intensive AI tasks