The Agent Skills Directory

[SAFE]: The skill's primary purpose is to provide documentation and architectural standards for Next.js development using the Feature-Sliced Design methodology.
[SAFE]: All referenced commands and configuration examples, such as those for bundling, runtime selection, and debugging, align with standard Next.js development practices and do not involve malicious operations.
[SAFE]: No signs of prompt injection, obfuscation, or unauthorized data exfiltration were detected across the skill body, references, or metadata.
[INDIRECT_PROMPT_INJECTION]: The skill describes a diagnostic surface where an agent interacts with application data and a local endpoint for debugging.
Ingestion points: Project source files (e.g., in src/features/**) and a hypothetical local endpoint (/_next/mcp).
Boundary markers: None explicitly mentioned in the documentation.
Capability inventory: Diagnostic tools for retrieving build errors (get_errors), routes (get_routes), and logs (get_logs).
Sanitization: The skill does not provide instructions for sanitizing external project data before agent processing.

nextjs-architecture