The Agent Skills Directory

[SAFE]: The skill operates as a static reference for building Retrieval-Augmented Generation systems. It contains no executable scripts, system commands, or persistence mechanisms that would pose a security risk.
[EXTERNAL_DOWNLOADS]: The reference files include links to official documentation and repositories for industry-standard tools like LangChain, LlamaIndex, Qdrant, and Pinecone. A reference to the TruLens evaluation framework was noted; while flagged by an automated scanner, TruLens is a well-known observability tool and the link is used here in a legitimate educational context.
[INDIRECT_PROMPT_INJECTION]: The skill describes pipelines that ingest external documents and recognizes the inherent security risks, such as indirect prompt injection. It proactively recommends defensive measures like input filtering, strict context adherence, and mandatory data access controls in production environments.

rag-development