The Agent Skills Directory

[SAFE]: The skill defines a standard methodology for performance benchmarking and regression detection without including any executable code or risky instructions.- [COMMAND_EXECUTION]: The skill anticipates the agent will run development-related commands such as docker build, lint, and TypeScript check to measure build performance. These operations are within the expected scope of a performance benchmarking tool.- [EXTERNAL_DOWNLOADS]: The benchmarking workflow includes making network requests to user-specified URLs and API endpoints to capture browser metrics and response latencies.

benchmark