The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses npx to fetch and execute performance analysis tools including lighthouse, @next/bundle-analyzer, and source-map-explorer. These are standard tools from well-known sources in the web development ecosystem.
[COMMAND_EXECUTION]: The skill instructs the agent to run shell commands using npx and pipe output into jq for JSON parsing. These commands are intended for performance auditing and bundle analysis.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data (URLs and project file paths) by interpolating them into shell command strings.
Ingestion points: User-provided target URLs for Lighthouse audits and file paths for source map exploration.
Boundary markers: The skill does not provide specific delimiters or instructions for the agent to wrap or validate these inputs before execution.
Capability inventory: Shell execution via npx with the ability to pipe to other utilities like jq.
Sanitization: There are no instructions for sanitizing, escaping, or validating the input strings before they are passed to the shell.

core-web-vitals