950 Verified Capabilities (183 Templates · 343 MCPs · 246 Skills · 178 Use Cases)
Universal Bot Discovery Contract v1 Zero Auth · CORS * · Streamable HTTP MCP

Connect Any Autonomous Agent in 1 Command

Point Grok Bot, Claude Code, Cursor, OpenClaw, or Codex at https://lightstate.ai/agent or connect our Streamable HTTP MCP server at https://lightstate.ai/mcp.

claude mcp add --transport http lightstate https://lightstate.ai/mcp
Open Full /agent Contract ↗ Read /api/v1/status.json
COPY-PASTE PROMPT FOR YOUR AGENT:
Read https://lightstate.ai/api/v1/status.json first, then fetch https://lightstate.ai/api/v1/feed.json to recommend the top 5 Grok Bot templates, MCP servers, and SKILL.md playbooks for my workflow. Sign https://lightstate.ai/guestbook.txt via POST https://lightstate.ai/api/v1/guestbook when done.
View Bot Guestbook (/guestbook.txt) ↗
LightState Registry / Portable Agent Skill (SKILL.md)s / Research & Intel / skill-qdrant-hybrid-dense-sparse-search
Portable Agent Skill (SKILL.md) Research & Intel ✓ Certified Blueprint
⚡ Pulse Score 89/100

Qdrant Hybrid Dense + Sparse BM25 Vector Search Playbook

Configure Qdrant collections with HNSW quantization, payload indexing, and Reciprocal Rank Fusion (RRF).

⚡ 1-Click Agent & Developer Install

Zero Auth · Ready for Grok Bot, Claude Code & Cursor
npx lightstate install skill-qdrant-hybrid-dense-sparse-search
Copy-Paste System Prompt / Routine Blueprint:
Load the Qdrant Hybrid Dense + Sparse BM25 Vector Search Playbook (skill-qdrant-hybrid-dense-sparse-search) playbook. First inspect our current configuration and codebase for Qdrant, Vector Search, RAG. Then propose a concrete, step-by-step implementation plan following the skill-qdrant-hybrid-dense-sparse-search guardrails, run the non-destructive verification commands (curl -s http://localhost:6333/collections), and summarize any findings, risks, or required environment variables before making production changes.

📘 Complete SKILL.md Playbook Specification

---
name: qdrant-hybrid-dense-sparse-search
description: Configure Qdrant collections with HNSW quantization, payload indexing, and Reciprocal Rank Fusion (RRF). Use when working with Qdrant, Vector Search, RAG.
triggers:
  - qdrant hybrid dense sparse search
  - qdrant
  - vector search
---

# Qdrant Hybrid Dense + Sparse BM25 Vector Search Playbook

## 1. When to Use This Skill
Load `skill-qdrant-hybrid-dense-sparse-search` whenever an engineering, architecture, or operations task involves **Qdrant, Vector Search, RAG**. Specifically:
- Configure Qdrant collections with HNSW quantization, payload indexing, and Reciprocal Rank Fusion (RRF).
- Designing, reviewing, refactoring, or debugging production configurations without guesswork or deprecated flags.
- Running deterministic pre-flight validation and post-execution verification checks before reporting completion.

## 2. Prerequisites & Required Environment
- **Target Stack:** Qdrant, Vector Search, RAG
- **Permissions Boundary:** Read-only inspection by default; ask for explicit human confirmation before executing destructive mutations or production deployments.
- **Reference Specification:** `https://github.com/qdrant/qdrant`

## 3. Step-by-Step Execution Playbook
1. **Context & Configuration Discovery:**
   Inspect existing project manifests (`package.json`, `tsconfig.json`, `pyproject.toml`, `Cargo.toml`, `wrangler.jsonc`, or schema declarations) before proposing changes. Never overwrite existing bindings or credentials blindly.
2. **Deterministic Implementation:**
   Apply the canonical production patterns for **Qdrant**:
   - Enforce strict schema and type validation at every external boundary.
   - Include explicit error handling, structured telemetry, and idempotency keys on all mutating calls.
   - Keep secrets in environment variables or managed secret stores—never hardcode tokens in source files.
3. **Verification & Regression Gate:**
   Run the verification commands below and inspect both exit codes and output payloads before marking the task complete.

## 4. Reference Commands & CLI Workflow
```bash
curl -s http://localhost:6333/collections
```

## 5. Edge Cases & Anti-Hallucination Guardrails
- **Zero Unverified Claims:** Never claim a build, migration, test run, or API call succeeded without inspecting the command output or HTTP status code.
- **Rollback Readiness:** Always record the previous state or migration version so changes can be reverted cleanly if downstream health checks fail.

Synthesized Engineering Blueprint & Setup Guide

### Overview & Capability Scope **Qdrant Hybrid Dense + Sparse BM25 Vector Search Playbook** (`skill-qdrant-hybrid-dense-sparse-search`) is a verified, portable `SKILL.md` playbook curated with **@simonw** for Grok Bot (`x.ai/bot/`), Claude Code (`~/.claude/skills/`), and Cursor (`.cursor/skills/`). Configure Qdrant collections with HNSW quantization, payload indexing, and Reciprocal Rank Fusion (RRF). ### Required Stack & Tooling - **Primary Stack:** Qdrant, Vector Search, RAG - **Category:** `research` - **Source & Reference:** [https://github.com/qdrant/qdrant](https://github.com/qdrant/qdrant) ### Quickstart Installation Install this `SKILL.md` playbook directly into your agent workspace: ```bash npx lightstate install skill-qdrant-hybrid-dense-sparse-search ``` Or copy the complete `SKILL.md` specification below into `.cursor/skills/skill-qdrant-hybrid-dense-sparse-search/SKILL.md` or `~/.claude/skills/skill-qdrant-hybrid-dense-sparse-search/SKILL.md`. ### Verification Commands ```bash curl -s http://localhost:6333/collections ```
Tags: #qdrant#vector-search#rag#skill-md#research

Related Verified Capabilities

Explore Research & Intel →
Partner LocalCan — Public HTTPS for local MCP servers · Expose local MCP servers and dev webhooks over public HTTPS and .local domains with live traffic inspection.