Agent Capability Analysis
The benchmark skill by affaan-m is an open-source official AI agent skill for Claude Code and other IDE workflows, helping agents execute tasks with better context, repeatability, and domain-specific guidance. Optimized for for Claude Code, performance benchmarking, regression detection.
Ideal Agent Persona
Perfect for Performance Optimization Agents needing advanced benchmarking and regression detection capabilities.
Core Value
Empowers agents to measure performance baselines, detect regressions, and compare stack alternatives using Core Web Vitals, API latency, and build performance metrics, including LCP, CLS, INP, FCP, and TTFB, via JSON output and Git-tracked baselines.
↓ Capabilities Granted for benchmark
! Prerequisites & Limits
- Requires browser MCP for page performance measurement
- Needs API endpoints for API performance benchmarking
- Limited to specific metrics, such as Core Web Vitals and API latency
Browser Sandbox Environment
⚡️ Ready to unleash?
Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.
benchmark
Optimize your code with the benchmark AI agent skill, measuring performance baselines and detecting regressions to ensure seamless user experiences. Try it...
FAQ & Installation Steps
These questions and steps mirror the structured data on this page for better search understanding.
? Frequently Asked Questions
What is benchmark?
Perfect for Performance Optimization Agents needing advanced benchmarking and regression detection capabilities. Benchmark is a performance measurement tool that helps developers detect regressions, measure performance baselines, and compare stack alternatives for optimal code performance.
How do I install benchmark?
Run the command: npx killer-skills add affaan-m/everything-claude-code/benchmark. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.
What are the use cases for benchmark?
Key use cases include: Automating performance benchmarking for web applications, Detecting regressions before and after pull requests, Comparing performance of different stack alternatives, Measuring API performance under load, Optimizing build performance for faster development feedback loops.
Which IDEs are compatible with benchmark?
This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.
Are there any limitations for benchmark?
Requires browser MCP for page performance measurement. Needs API endpoints for API performance benchmarking. Limited to specific metrics, such as Core Web Vitals and API latency.
↓ How To Install
-
1. Open your terminal
Open the terminal or command line in your project directory.
-
2. Run the install command
Run: npx killer-skills add affaan-m/everything-claude-code/benchmark. The CLI will automatically detect your IDE or AI agent and configure the skill.
-
3. Start using the skill
The skill is now active. Your AI agent can use benchmark immediately in the current project.