Vector Databases & Embeddings Storage

What it does

Vector Databases & Embeddings Storage is a Cursor skill: a SKILL.md playbook that AgenticKit installs at .cursor/skills/vector-database. Cursor's agent loads it when the task matches the skill description, instead of stuffing the same rules into every chat.

Vector database architecture for semantic search and retrieval, comparing cosine similarity, Euclidean distance, and HNSW index tuning.

pgvector, Pinecone, similarity search, HNSW indexing, and distance metrics. The file is domain knowledge, not a slash macro. You do not type it. The agent reads it when the job is vector database.

Why it exists

Default Cursor has no memory of how your team ships code, schema, and tests. Founders paste the same conventions into chat, then watch the model drift on the next turn. This skill exists so those conventions live on disk and load only when relevant.

It ships in the Engineering Kit. It is wired to the AI & Vector Engineer (ai-engineer) and PostgreSQL & Database Pro (postgres-pro) agents. It is wired to the /rag-pipeline: RAG Pipeline & Document Ingestion System and /ai-feature: AI Integration & Vector Pipeline Builder commands. That graph is the point: the skill is the standard, the agent is the role, the command is the trigger.

When to use it

• Use Vector Databases & Embeddings Storage when the work is specifically about pgvector, pinecone, similarity search, hnsw indexing, and distance metrics.
• Load it before a long session that will touch this surface more than once. A one-line edit does not need the full playbook.
• Use it on production SaaS work (multi-tenant apps, paid features, anything that will be reviewed) rather than a throwaway prototype.

When not to use it

• Do not treat the skill as a replacement for a slash command. Skills teach. Commands run a pipeline.
• Do not paste the whole SKILL.md into chat. If Cursor is not loading it, fix the description or invoke the matching command.
• Do not use it as a generic 'write better code' rule. Scope is this domain only.

Example workflow

1. Install the Engineering Kit so .cursor/skills/vector-database lands in the repo.
2. Open a new Cursor agent chat pointed at the files this skill governs.
3. Ask the AI & Vector Engineer (ai-engineer) to read the skill, or run /rag-pipeline: RAG Pipeline & Document Ingestion System.
4. Review the first artifact against the practices below. If it violates one, stop and correct the file. Do not prompt 'just finish it'.
5. Commit the skill-guided files with the rest of the slice so the next session inherits the same standard.

Example usage

Example prompt: "Read .cursor/skills/vector-database and apply it to this change. Do not invent extra conventions."

Or trigger the pipeline: /rag-pipeline: RAG Pipeline & Document Ingestion System. That command is written to load this skill.

Check the output against: Use pgvector HNSW indexes for sub-millisecond approximate nearest neighbor search

Example output

• The skill itself does not write a single output file. It changes what the agent is allowed to produce in code, schema, and tests.
• When you run /rag-pipeline: RAG Pipeline & Document Ingestion System, expect repo files plus notes under docs/, not a chat-only answer.

Best practices

• Use pgvector HNSW indexes for sub-millisecond approximate nearest neighbor search
• Normalize embedding vectors when using dot product or cosine distance
• Store original text chunks alongside embeddings to eliminate extra database joins
• Partition vector indexes by tenant ID to prevent cross-tenant vector leakage

Common mistakes

• Ignoring "Use pgvector HNSW indexes for sub-millisecond approximate nearest neighbor search" and hoping a later prompt will clean it up.
• Copying the skill into .cursor/rules as always-on. That burns context and fights Cursor's load-on-match design.
• Running two overlapping skills that contradict each other in the same turn.
• Letting the agent skip tests or types because 'the skill is about architecture'.