The Agent Skills Directory

[SAFE]: The skill serves as a documentation and scaffolding guide for the Model Context Protocol (MCP). It contains no executable code or malicious instructions. It focuses on teaching best practices like avoiding hardcoded credentials and using environment variables for authentication.\n- [EXTERNAL_DOWNLOADS]: The skill references official SDKs and tools from well-known repositories (e.g., github.com/modelcontextprotocol/*) and documentation sites (modelcontextprotocol.io). These references follow the [TRUST-SCOPE-RULE] as they belong to a well-known service ecosystem and are used for standard developer workflows.\n- [CREDENTIALS_SAFE]: The skill explicitly advises against hardcoding credentials, providing code snippets that demonstrate safe secret management using process.env.\n- [COMMAND_EXECUTION]: Benign development commands are included as examples, such as npm run build and npx @modelcontextprotocol/inspector. These are standard developer tools for the intended workflow.

meta-mcp-builder