# Install the "Pinecone Hybrid Vector Search" skill

You are installing an AgenticMarket skill into this workspace. Follow these steps exactly.

## 1. Detect your environment and choose the destination file
- Andromity: `.andromity/skills/pinecone-vector-search/SKILL.md` (or user scope `~/.andromity/skills/pinecone-vector-search/SKILL.md`)
- Antigravity / Gemini CLI: `.agent/skills/pinecone-vector-search/SKILL.md`
- Cursor: `.cursor/rules/pinecone-vector-search.mdc`
- Claude Code: append to `CLAUDE.md` (or `.claude/skills/pinecone-vector-search.md`)
- Windsurf: append to `.windsurfrules`
- Cline / Roo Code: `.clinerules/pinecone-vector-search.md`
- GitHub Copilot: append to `.github/copilot-instructions.md`
- ChatGPT / web only: paste the content into Custom Instructions
- Any other agent: save to `.agent/skills/pinecone-vector-search/SKILL.md`

## 2. Create the destination file
- Preserve every existing file and configuration entry.
- Create parent folders as needed.
- Never overwrite unrelated content.

## 3. Write exactly this content

```markdown
---
name: pinecone-vector-search
description: "Design vector index schemas, sparse-dense hybrid retrieval, metadata filtering, and high-throughput upsert pipelines."
author: community
license: mit
version: 1.0.0
---
# Pinecone Vector Indexing

Best practices for vector search:
- Structure metadata with low cardinality for fast pre-filtering.
- Batch upserts into chunks of 100-250 vectors.
- Normalize vector embeddings to unit length when using cosine similarity.
```

## 4. Verify
- Confirm the file exists and is readable.
- Report the destination path and confirm the "Pinecone Hybrid Vector Search" skill is installed and active.

Skill metadata:
- Slug: pinecone-vector-search
- Category: ai-agents
- License: mit
- Source: AgenticMarket