lance-format

Build or update the lance-context MCP server and Claude Code example that uses lance-context as a memory/knowledge store.

Run local test/style checks and open GitHub PRs for lance-context. Use when asked to run CI-equivalent checks (uv pytest, ruff/pyright, cargo fmt/clippy/test) and then create a PR with a proper title/body.

Guide Code Agents to help Lance users write/read datasets and build/choose indices. Use when a user asks how to use Lance (Python/Rust/CLI), how to write_dataset/open/scan, how to build vector indexes (IVF_PQ, IVF_HNSW_*), how to build scalar indexes (BTREE, BITMAP, LABEL_LIST, NGRAM, INVERTED, BLOOMFILTER, RTREE, etc.), how to combine filters with vector search, or how to debug indexing and scan performance.

Use this skill when configuring, testing, debugging, or documenting lance-spark with AWS Glue Data Catalog and S3, including Spark catalog options, Docker integration tests, CI Glue/S3 workflows, and code references for namespace-backed Lance tables.

Use when creating or revising an HF_DATASET_CARD.md file in this repo. Defines the six-section card structure (Search, Curate, Evolve, Train, Versioning, Materialize a subset), the writing voice, and the example style rules for Lance-format datasets published to the HuggingFace Hub.