# 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](https://agentskills.io) 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”. ```bash gh skill install i2mint/vd vd-add-backend --agent claude-code ``` Source: [`vd/data/skills/vd-add-backend`](https://github.com/i2mint/vd/tree/HEAD/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. ```bash gh skill install i2mint/vd vd-backend-choose --agent claude-code ``` Source: [`vd/data/skills/vd-backend-choose`](https://github.com/i2mint/vd/tree/HEAD/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”. ```bash gh skill install i2mint/vd vd-ingest --agent claude-code ``` Source: [`vd/data/skills/vd-ingest`](https://github.com/i2mint/vd/tree/HEAD/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. ```bash gh skill install i2mint/vd vd-ops --agent claude-code ``` Source: [`vd/data/skills/vd-ops`](https://github.com/i2mint/vd/tree/HEAD/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. ```bash gh skill install i2mint/vd vd-quickstart --agent claude-code ``` Source: [`vd/data/skills/vd-quickstart`](https://github.com/i2mint/vd/tree/HEAD/vd/data/skills/vd-quickstart) (bundled with the pip package). ### `vd-search` Advanced-search tooling for the vd package. Use this skill when the user goes beyond a single basic .search() call with vd — metadata filters with MongoDB-style operators, hybrid (keyword + vector) search, BM25, multi-query searches, reciprocal rank fusion, finding documents similar to an existing one, deduplicating result sets, or searching by a pre-computed query vector. ```bash gh skill install i2mint/vd vd-search --agent claude-code ``` Source: [`vd/data/skills/vd-search`](https://github.com/i2mint/vd/tree/HEAD/vd/data/skills/vd-search) (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. ```bash gh skill install i2mint/vd vd-setup-backend --agent claude-code ``` Source: [`vd/data/skills/vd-setup-backend`](https://github.com/i2mint/vd/tree/HEAD/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 `. ## Instruction files Files agents read before working in this repository. - [`.claude/CLAUDE.md`](https://github.com/i2mint/vd/tree/HEAD/.claude/CLAUDE.md): read by Claude Code ## Machine-readable documentation This site publishes the same documentation in forms that fit an agent’s context window: - [`llms.txt`](https://i2mint.github.io/vd/llms.txt): an index of every page with a one-line description ([llms.txt](https://llmstxt.org) format) - [`vd.md`](https://i2mint.github.io/vd/vd.md): the whole documentation as one Markdown file - `.html.md`: a rendered Markdown twin of every page, advertised from each page’s `` with `` - [`objects.inv`](https://i2mint.github.io/vd/objects.inv): the Sphinx inventory: a symbol-to-URL index (`sphobjinv convert plain objects.inv -`)