For AI agents#

vd ships artifacts for coding agents alongside its code. This page lists them, says where each lives in the repository, and points at the machine-readable copies of this documentation.

Skills#

Skills are folders holding a SKILL.md (the Agent Skills format): a description that tells an agent when to use it and a body with the procedure. Install one into your agent with gh skill (any host: --agent claude-code, copilot, cursor, codex, gemini), or use the copy bundled in the wheel.

vd-add-backend#

Developer skill for implementing a new vector-database backend in the vd package. Use when adding, refactoring, or reviewing a vd backend adapter (qdrant, pinecone, weaviate, lancedb, pgvector, faiss, etc.) — covers the AbstractClient/AbstractCollection raw-primitive contract, filter handling, capability protocols, the escape hatch, and the provider registry. Trigger on “add a backend to vd”, “implement the X backend”, “vd adapter”.

gh skill install i2mint/vd vd-add-backend --agent claude-code

Source: vd/data/skills/vd-add-backend (bundled with the pip package).

vd-backend-choose#

Backend-selection tooling for the vd package. Use this skill when the user is picking a vector database with vd, asks “which backend should I use”, compares backends, or weighs persistence / cloud / cost / hybrid search / async / scale / license trade-offs. For installing, starting and verifying the chosen backend (pip, Docker, API keys), use vd-setup-backend.

gh skill install i2mint/vd vd-backend-choose --agent claude-code

Source: vd/data/skills/vd-backend-choose (bundled with the pip package).

vd-ingest#

Corpus-ingestion tooling for the vd package. Use this skill when the user has documents, files, articles, or long text they need to load into a vd collection — including cleaning text, splitting it into chunks, attaching metadata, and adding the result in batches. Trigger on requests like “load these docs into a vector DB”, “chunk this text”, “preprocess before embedding”, or “bulk insert”.

gh skill install i2mint/vd vd-ingest --agent claude-code

Source: vd/data/skills/vd-ingest (bundled with the pip package).

vd-ops#

Operational tooling for the vd package. Use this skill when the user is managing a vd collection beyond reads/writes — exporting or importing data (JSONL / JSON / directory), migrating between backends, computing collection statistics, finding duplicates / outliers, validating integrity, running health checks, benchmarking search or insert latency, or driving any of the above from the vd CLI.

gh skill install i2mint/vd vd-ops --agent claude-code

Source: vd/data/skills/vd-ops (bundled with the pip package).

vd-quickstart#

Vector-search tooling for the vd package. Use this skill when the user wants to do semantic / vector search in Python with the vd package — connecting to a backend, creating a collection, adding documents, and running a query. Also trigger on mentions of “vector database”, “embeddings + search”, or any time the user imports vd for a new task and needs the basic happy-path setup.

gh skill install i2mint/vd vd-quickstart --agent claude-code

Source: vd/data/skills/vd-quickstart (bundled with the pip package).

vd-setup-backend#

Install, start and verify a vector database for the vd package. Use this skill when the user needs to get a backend running — pip-installing a client, starting a server with Docker, setting cloud credentials (API keys, URIs, env vars), connecting vd to it, and smoke-testing the connection. Also trigger on BackendNotInstalledError, “connection refused” on a vector DB port, “how do I run qdrant / pgvector / redis / elasticsearch / milvus locally”, or “vd.connect fails”. For choosing which backend to use, see vd-backend-choose.

gh skill install i2mint/vd vd-setup-backend --agent claude-code

Source: vd/data/skills/vd-setup-backend (bundled with the pip package).

The bundled skills are also on disk after pip install vd, under the package’s data/skills/ directory; link them into an agent without network access with skill link-skills <that directory>.

Instruction files#

Files agents read before working in this repository.

Machine-readable documentation#

This site publishes the same documentation in forms that fit an agent’s context window:

  • llms.txt: an index of every page with a one-line description (llms.txt format)

  • vd.md: the whole documentation as one Markdown file

  • <page>.html.md: a rendered Markdown twin of every page, advertised from each page’s <head> with <link rel="alternate" type="text/markdown">

  • objects.inv: the Sphinx inventory: a symbol-to-URL index (sphobjinv convert plain objects.inv -)