{
  "id": "skl_1bced52d87ae",
  "slug": "skill-rag-hybrid-search",
  "asset_type": "skill",
  "name": "Hybrid Vector + BM25 Full-Text Search & Reranking RAG Skill",
  "tagline": "Build high-precision Retrieval-Augmented Generation (RAG) pipelines combining dense vector embeddings, sparse BM25 keyword matching, Reciprocal Rank Fusion",
  "description_md": "### Overview & Capability Scope\n**Hybrid Vector + BM25 Full-Text Search & Reranking RAG Skill** (`skill-rag-hybrid-search`) is a verified, portable `SKILL.md` playbook curated with **@swyx** for Grok Bot (`x.ai/bot/`), Claude Code (`~/.claude/skills/`), and Cursor (`.cursor/skills/`).\n\nBuild high-precision Retrieval-Augmented Generation (RAG) pipelines combining dense vector embeddings, sparse BM25 keyword matching, Reciprocal Rank Fusion (RRF), and cross-encoder reranking.\n\n### Required Stack & Tooling\n- **Primary Stack:** Hybrid Search, Reciprocal Rank Fusion, Vector DB, Citations\n- **Category:** `research`\n- **Source & Reference:** [https://qdrant.tech/documentation/](https://qdrant.tech/documentation/)\n\n### Quickstart Installation\nInstall this `SKILL.md` playbook directly into your agent workspace:\n```bash\nnpx lightstate install skill-rag-hybrid-search\n```\nOr copy the complete `SKILL.md` specification below into `.cursor/skills/skill-rag-hybrid-search/SKILL.md` or `~/.claude/skills/skill-rag-hybrid-search/SKILL.md`.\n\n### Verification Commands\n```bash\nnpx lightstate inspect qdrant-mcp\n```\n",
  "primary_category": "research",
  "categories_json": "[\"research\", \"skills\"]",
  "tags_json": "[\"hybrid-search\", \"reciprocal-rank-fusion\", \"vector-db\", \"citations\", \"skill-md\", \"research\"]",
  "compatible_agents_json": "[\"grok-bot\", \"claude-code\", \"cursor\"]",
  "integrations_json": "[\"Hybrid Search\", \"Reciprocal Rank Fusion\", \"Vector DB\"]",
  "includes_json": "[]",
  "safety_level": "Read-Only / Ask-First",
  "safety_summary": "Verified capability blueprint by @swyx.",
  "share_url": "",
  "deep_link_uri": "",
  "mcp_endpoint": "",
  "mcp_transport": "http",
  "install_command": "npx lightstate install skill-rag-hybrid-search",
  "skill_markdown": "---\nname: rag-hybrid-search\ndescription: Build high-precision Retrieval-Augmented Generation (RAG) pipelines combining dense vector embeddings, sparse BM25 keyword matching, Reciprocal Rank Fusion (RRF), and cross-encoder reranking. Use when working with Hybrid Search, Reciprocal Rank Fusion, Vector DB, Citations.\ntriggers:\n  - rag hybrid search\n  - hybrid search\n  - reciprocal rank fusion\n---\n\n# Hybrid Vector + BM25 Full-Text Search & Reranking RAG Skill\n\n## 1. When to Use This Skill\nLoad `skill-rag-hybrid-search` whenever an engineering or operations task involves **Hybrid Search, Reciprocal Rank Fusion, Vector DB, Citations**. Specifically:\n- Build high-precision Retrieval-Augmented Generation (RAG) pipelines combining dense vector embeddings, sparse BM25 keyword matching, Reciprocal Rank Fusion (RRF), and cross-encoder reranking.\n- Designing, reviewing, or debugging production configurations without guesswork or deprecated flags.\n- Running deterministic pre-flight and post-execution verification checks before reporting completion.\n\n## 2. Prerequisites & Required Environment\n- **Target Stack:** Hybrid Search, Reciprocal Rank Fusion, Vector DB, Citations\n- **Permissions:** Read-only inspection by default; ask for explicit confirmation before executing destructive mutations or production deployments.\n- **Reference Repository:** `https://qdrant.tech/documentation/`\n\n## 3. Step-by-Step Execution Playbook\n1. **Context & Configuration Discovery:**\n   Inspect existing project manifests (`package.json`, `wrangler.jsonc`, schema files, or environment declarations) before proposing changes. Never overwrite existing bindings or credentials blindly.\n2. **Deterministic Implementation:**\n   Apply the canonical patterns for **Hybrid Search**:\n   - Enforce strict schema/type validation at every external boundary.\n   - Include explicit error handling, structured logging, and idempotency keys on all mutating calls.\n   - Keep secrets in environment variables or secret stores—never hardcode tokens in source files.\n3. **Verification & Regression Gate:**\n   Run the verification commands below and inspect both exit codes and output payloads before marking the task complete.\n\n## 4. Reference Commands & CLI Workflow\n```bash\nnpx lightstate inspect qdrant-mcp\n```\n\n## 5. Edge Cases & Anti-Hallucination Guardrails\n- **Zero Unverified Claims:** Never claim a deployment, migration, or API call succeeded without inspecting the command output or HTTP status code.\n- **Rollback Readiness:** Always record the previous state or migration version so changes can be reverted cleanly if downstream health checks fail.\n",
  "starter_prompt": "Load the Hybrid Vector + BM25 Full-Text Search & Reranking RAG Skill (skill-rag-hybrid-search) playbook. First inspect our current configuration and codebase for Hybrid Search, Reciprocal Rank Fusion, Vector DB, Citations. Then propose a concrete, step-by-step implementation plan following the skill-rag-hybrid-search guardrails, run the non-destructive verification commands (npx lightstate inspect qdrant-mcp), and summarize any findings, risks, or required environment variables before making production changes.",
  "project_url": "https://qdrant.tech/documentation/",
  "repo_url": "https://qdrant.tech/documentation/",
  "creator_handle": "swyx",
  "creator_name": "Shawn Wang (@swyx)",
  "creator_avatar_url": null,
  "creator_url": "https://x.com/swyx",
  "creator_platform": "x",
  "creator_cal_url": null,
  "claimed_by_user_id": null,
  "scouted_by_handle": null,
  "source_url": "https://qdrant.tech/documentation/",
  "source_tweet_id": null,
  "source_origin": "certified_builder",
  "source_posted_at": null,
  "x_likes": 208,
  "x_bookmarks": 519,
  "x_retweets": 129,
  "x_views": 2912,
  "human_upvotes": 208,
  "human_installs": 208,
  "bot_pulls": 519,
  "pulse_score": 89,
  "gravity_rank_score": 1833,
  "is_featured": 0,
  "is_verified": 1,
  "is_sponsored": 0,
  "sponsor_tier": "free",
  "sponsor_label": "",
  "sponsor_cta_url": "",
  "sponsor_expires_at": null,
  "commercial_intent_score": 0,
  "status": "active",
  "created_at": "2026-10-24T20:00:00Z",
  "updated_at": "2026-10-24T20:00:00Z",
  "verified_at": null,
  "primitive": "skill",
  "title": "Hybrid Vector + BM25 Full-Text Search & Reranking RAG Skill",
  "description": "Build high-precision Retrieval-Augmented Generation (RAG) pipelines combining dense vector embeddings, sparse BM25 keyword matching, Reciprocal Rank Fusion",
  "category": "research",
  "tags": "[\"hybrid-search\", \"reciprocal-rank-fusion\", \"vector-db\", \"citations\", \"skill-md\", \"research\"]",
  "agent_compatibility": "[\"grok-bot\", \"claude-code\", \"cursor\"]",
  "author_handle": "swyx",
  "author_name": "Shawn Wang (@swyx)",
  "author_avatar": null,
  "source_tweet_url": "https://qdrant.tech/documentation/",
  "github_url": "https://qdrant.tech/documentation/",
  "external_url": "https://qdrant.tech/documentation/",
  "upvotes_count": 208,
  "installs_count": 208
}