{"id":77099,"plugin_id":"plugins_6ab42163e9048191ab6e8c14258a48c3","kind":"skill","collection_source":"plugin_package","comparison_source":null,"observed_at":"2026-11-03T00:12:26.400Z","digest":"839ba1860d27806794a764e3990733f58b182f9ea90e7395c22fc3220f01e258","against":null,"payload":{"description":"Upgrade legacy RAG repositories, APIs or vector infrastructure while preserving behavior, access controls and evidence.","included_files":[],"name":"modernize-rag","skill_md_contents":"---\nname: modernize-rag\ndescription: Upgrade legacy RAG repositories, APIs or vector infrastructure while preserving behavior, access controls and evidence.\n---\n\n\n# Modernize an existing RAG stack\n**Trigger:** SDK migration, changing embedding models/vector stores, retiring old endpoints, adding hybrid search or refactoring production RAG.\n\n1. Inspect project files, SDK versions, deployed configuration, data schemas, feature flags and baseline tests where accessible. Do not assume a product's latest API signature.\n2. Make a compatibility matrix for ingestion, vector dimensions, existing document IDs, metadata filters, citations, authorization and retrieval semantics.\n3. Prefer incremental migration with adapters/dual writes or shadow reads where justified; never silently switch embeddings without a reindex compatibility strategy.\n4. Preserve source IDs and permissions; migrate deletion/freshness rules and observability. Verify with known-answer, no-answer and unauthorized fixtures.\n5. Use official current docs, small diffs and regression gates. For deploy/production writes, get approval and offer rollback plan.\n6. Return exact scope, migration sequence, actual tests run, unsupported behavior, cutover and rollback conditions.\n\nRead `../../references/architecture-patterns.md`, `../../references/ingestion-indexing.md`, `../../references/evidence-contract.md`.\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}