Instructions file
Instructions for datachain-ai/datachain: Always read and follow AGENT.md — unconditionally, in full. It holds the general, durable insights about this product (architecture, warehouse backends, cross-cutting design principles). Treat them as binding context for any change here.
Command
Garbage collect temporary tables, failed dataset versions, and outdated checkpoints.
Command
DataChain is a command-line tool for wrangling unstructured AI data at scale. Use datachain -h to list all available commands.
Skill Claude CodeCodex
Use ONLY for abstract DataChain SDK questions — API usage, method signatures, or code patterns — when no specific dataset or bucket is referenced. If the request mentions creating, saving, listing, exploring datasets or buckets, use datachain-knowledge instead.
Skill Claude CodeCodex
Use when asked about Studio job analytics — compute hours, user spend, failure rates, cost estimation, cluster usage. Generates and maintains dc-knowledge/jobs/index.md.
Skill Claude CodeCodex
Use whenever datasets, cloud storage buckets, or data pipelines are mentioned — creating, saving, querying, listing, exploring, deleting, or processing data in S3, GCS, Azure Blob, or local storage. Also use when running any script that may create datasets as a side effect. Maintains a knowledge base at dc-knowledge/…