The Agent Skills Directory

[SAFE]: The skill is a legitimate development aid for Next.js, providing documentation and regex-based validation for project configuration and code patterns.
[SAFE]: Recommended CLI tools and packages, such as Next.js codemods and official utility libraries (@next/third-parties), are standard industry tools from the framework's official ecosystem.
[SAFE]: Documentation regarding the development-only Model Context Protocol (MCP) endpoint describes a standard feature for AI-assisted local debugging within the Next.js runtime.
[INDIRECT_PROMPT_INJECTION]: The skill analyzes local Next.js project source code to provide advice, which is a standard surface for indirect prompt injection if malicious instructions are present in the analyzed files.
Ingestion points: Project files matching pathPatterns (e.g., app/**, next.config.js, tsconfig.json).
Boundary markers: None explicitly defined within the skill's instructions.
Capability inventory: The skill defines bashPatterns for Next.js CLI commands, suggesting the agent may execute shell operations like next build or next dev based on detected context.
Sanitization: The skill does not implement specific sanitization or filtering for the code content it processes.

nextjs