The Agent Skills Directory

[SAFE]: The skill instructs the agent to use the mcp__deepwiki toolset to research specific GitHub repositories. The referenced repositories include vendor-owned resources (Lightprotocol) and trusted organizations (Anthropics).
[SAFE]: No obfuscation, prompt injection, or unauthorized data exfiltration patterns were detected. The skill focuses on technical precision and structured data retrieval.
[SAFE]: The execution steps describe standard tool usage for indexing repositories and querying external documentation without bypassing security controls.

ask-mcp