The Agent Skills Directory

[SAFE]: The skill serves as a technical documentation hub for developers building or consuming agent-related protocols. All provided code snippets are illustrative examples for mounting servers or implementing authentication middleware.
[SAFE]: The skill actively promotes security best practices, such as warning against using form-based elicitation for secrets, enforcing per-hop authorization, and treating tool output as untrusted input.
[SAFE]: External references and download patterns (e.g., fetching the mcp-publisher binary) target official and well-known repositories associated with the Model Context Protocol project on GitHub.
[SAFE]: No obfuscation, prompt injection, or persistence mechanisms were detected. The skill's content is consistent with its technical purpose and provides useful guidance for maintaining protocol compatibility.

agent-interop