upstash-vector-db-skills — Claude Code skill for Upstash Vector search
This skill walks the agent through Upstash Vector: index setup, document upserts, semantic search and namespaces. Useful when you build vector search on Vercel.
npx skills add gocallum/nextjs16-agent-skills --skill upstash-vector-db-skills -a claude-codeWhat upstash-vector-db-skills does
The skill covers Upstash Vector through the @upstash/vector SDK. Your agent gets working snippets: creating an Index client, upserting single documents and batches, running query with topK and metadata. Text is embedded automatically when an embedding model is set on the index.
Namespaces split one index into isolated subsets, which fits multi-tenant apps. The file shows index.namespace("blog"), listNamespaces, deleteNamespace, plus reset and delete for clearing vectors. A separate section covers RAG: pull top-k documents and hand them to the LLM alongside the user question.
You need UPSTASH_VECTOR_REST_URL and UPSTASH_VECTOR_REST_TOKEN in .env before anything runs. The index itself is created in the Upstash console, where you also pick the embedding model; the skill favours MixBread AI, which requires its own API key. Upstash is eventually consistent, so a document you just upserted may not show up in the next query — worth knowing if you plan to read back immediately after writing.
What it helps with
- create an Upstash vector index and wire it into a project
- load documents into the index in batches
- run semantic search that returns metadata
- isolate each tenant's vectors with namespaces
- build a RAG flow from retrieval to LLM call
Example prompts for the agent
- Set up Upstash Vector in this project: create the client and a search function
- Add batch document indexing, 100 per batch
- Query the tenant-123 namespace with topK 5 and metadata
How to install upstash-vector-db-skills
1Skills CLI (Vercel)
npx skills add gocallum/nextjs16-agent-skills --skill upstash-vector-db-skills -a claude-code2Manually: put the files in place
~/.claude/skills/upstash-vector-db-skills/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/upstash-vector-db-skills/
1Skills CLI (Vercel)
npx skills add gocallum/nextjs16-agent-skills --skill upstash-vector-db-skills -a codex2Manually: put the files in place
.agents/skills/upstash-vector-db-skills/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add gocallum/nextjs16-agent-skills --skill upstash-vector-db-skills -a cursor2Manually: put the files in place
.cursor/skills/upstash-vector-db-skills/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install gocallum/nextjs16-agent-skills upstash-vector-db-skills2Manually: put the files in place
.github/skills/upstash-vector-db-skills/SKILL.md1Skills CLI (Vercel)
npx skills add gocallum/nextjs16-agent-skills --skill upstash-vector-db-skills -a gemini-cli2Platform CLI
gemini skills install https://github.com/gocallum/nextjs16-agent-skills --path skills/upstash-vector-db-skillsManually: put the files in place
.devin/skills/upstash-vector-db-skills/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add gocallum/nextjs16-agent-skills --skill upstash-vector-db-skills -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about upstash-vector-db-skills
How do I install upstash-vector-db-skills in Claude?
Run npx skills add gocallum/nextjs16-agent-skills --skill upstash-vector-db-skills -a claude-code. The skill file then lands at ~/.claude/skills/upstash-vector-db-skills/SKILL.md.
What does upstash-vector-db-skills do?
It gives the agent code examples for Upstash Vector: index creation, upsert, query, namespaces, RAG, and error handling for 401 and 429 responses.
What do I need before using it?
UPSTASH_VECTOR_REST_URL and UPSTASH_VECTOR_REST_TOKEN in your environment, plus the @upstash/vector package. Choosing MixBread AI as the embedding provider means you also need its API key.
