The Agent Skills Directory

[SAFE]: The skill is purely instructional and provides a logical framework for designing RAG architectures. It does not contain any executable scripts, command-line operations, or network-enabled tools.
[NO_CODE]: The skill definition is limited to markdown text and metadata; it does not import or execute any Python or Node.js code, nor does it define any automation commands.
[INDIRECT_PROMPT_INJECTION]: The skill defines a procedure for analyzing source documents and query patterns. While this establishes a data ingestion surface common to RAG systems, the skill itself contains no active interpolation of untrusted data into sensitive commands or executable contexts.

rag-architecture