The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes project-specific data to make decisions about build optimizations and troubleshooting. * Ingestion points: Reads package.json, vite.config.*, and source files using Read, Grep, and Glob tools. * Boundary markers: The instructions lack explicit delimiters or warnings to ignore potentially malicious instructions embedded in the analyzed project files. * Capability inventory: The skill has access to Bash for command execution and Edit/MultiEdit for file modification. * Sanitization: No evidence of sanitization or validation of the content read from the project files before it influences agent behavior.
[COMMAND_EXECUTION]: The skill instructs the agent to execute several shell commands for diagnosis and validation. Evidence: Use of vite --version, find, grep, lsof, and vite build to inspect the environment and validate configurations.
[EXTERNAL_DOWNLOADS]: The skill uses npx to run external utilities, which involves downloading packages from the npm registry. Evidence: npx vite-bundle-analyzer dist --no-open is used for bundle analysis.

vite-expert