The Agent Skills Directory

[COMMAND_EXECUTION]: The skill performs environment detection and project diagnosis using standard system utilities and development tools.
Executes grep and find to analyze source code patterns and project structure.
Utilizes npm and npx to run build scripts and diagnostic tools like @next/bundle-analyzer and lighthouse.
Uses curl to verify the accessibility of local API routes on localhost:3000.
[INDIRECT_PROMPT_INJECTION]: The skill implements an attack surface by reading and processing local source code files which could contain untrusted data.
Ingestion points: Files with .js, .jsx, .ts, and .tsx extensions in the app/ and pages/ directories are read using grep commands.
Boundary markers: None identified; the skill does not explicitly instruct the agent to ignore potential instructions embedded within the analyzed code.
Capability inventory: The skill has the ability to execute shell commands, perform local network requests via curl, and trigger project build processes.
Sanitization: Content read from files is not sanitized or escaped before being presented to the agent for analysis.
[DYNAMIC_EXECUTION]: The skill uses inline Node.js execution for environment detection.
Employs node -e to programmatically extract the Next.js version from the project's package.json file.

nextjs-expert