rag-tracking
Memory Skill
Persistent memory for dragster document processing. Track collections, ingestion history, and issues across sessions.
When to Use This Skill
Use this skill when:
- Working with agents that lack persistent memory (Claude Code, Codex, OpenCode, etc.)
- Sharing ingestion state across multiple agents or team members
- Running in CI/CD environments where agent memory doesn't persist
NOT needed for:
- Letta Code — has built-in persistent memory (system, progressive, recall)
- Any agent platform with native long-term memory support
For Letta Code users, simply store collection state in your agent's memory files instead.
Memory Files
More from etalab-ia/dragster
memory
Maintain persistent memory for document ingestion and issues. Use when ingesting documents, tracking parsing problems, or recalling collection state. Works with ctx for cross-session persistence.
2rag-parse
Use this skill when the user asks to parse, perform multi-format document conversion or spatially extract text from an unstructured file (PDF, DOCX, PPTX, XLSX, images, etc.) locally without cloud dependencies.
2rag-index
Index a document corpus for semantic search. Use when the user wants to set up a knowledge base, create a searchable index from markdown documents, or enable semantic search. Triggers on keywords like "index documents", "create knowledge base", "setup search", "semantic search".
2rag-search
Search the knowledge base for relevant documents. Use when the user wants to find documents in their indexed corpus, has questions that could be answered by their documents, or needs context from their knowledge base. Triggers on keywords like "search documents", "find in knowledge base", "query index".
2parse
Use this skill when the user asks to parse, perform multi-format document conversion or spatially extract text from an unstructured file (PDF, DOCX, PPTX, XLSX, images, etc.) locally without cloud dependencies.
1search
Search the knowledge base for relevant documents. Use when the user wants to find documents in their indexed corpus, has questions that could be answered by their documents, or needs context from their knowledge base. Triggers on keywords like "search documents", "find in knowledge base", "query index".
1