The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional documentation (Markdown) for guiding an AI agent's tool selection process. It contains no executable code, scripts, or binary files.
[SAFE]: The instructions promote security and efficiency best practices, such as applying least-privilege principles to tool parameters (limiting max_results and max_tokens_per_page) to prevent context exhaustion and accidental data bloat.
[SAFE]: No evidence of prompt injection, obfuscation, or credential harvesting was found. The skill references standard Model Context Protocol (MCP) tool names which are part of the platform's infrastructure.
[SAFE]: The 'Tool Selection Chain' correctly identifies and delegates tasks to specialized tools, reducing the risk of processing untrusted search data for tasks that should be performed locally or via authoritative documentation sources.

perplexity