qdrant-search-quality

A guide for finding and improving the quality of search results in Qdrant, a database for searching data by meaning. It checks whether problems come from text chunks, the embedding model, database settings, or the search method.

In plain words
What is it for?
Use it to investigate irrelevant or missing results, compare exact and meaning-based search, and decide whether to change chunking, embedding models, reranking, or hybrid search settings.
Why use it?
It helps distinguish poor data preparation from ranking or database problems before changing settings. This avoids tuning the wrong part of the search system.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/secondlifes/code-intel/qdrant-search-quality
Any agent
npx skills add SecondLifes/code-intel --skill qdrant-search-quality
Clone the repo
git clone --depth 1 https://github.com/SecondLifes/code-intel

Made for: Claude Code, Codex.

Per session 122 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 543 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00122 $0.00543
Opus 5 $0.00061 $0.00271
Sonnet 5 $0.00024 $0.00109
Haiku 4.5 $0.00012 $0.00054

Measured 2d ago against content hash e4b6baaf3de9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qdrant-search-quality scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/skills/qdrant-search-quality/SKILL.md · 33 lines

What it actually says

Qdrant Search Quality

Usage

You say What happens
"Search results are bad/irrelevant" / "which embedding model" / "recall@k" Check chunk quality first — CodeIntel's own chunker (src/chunker.py) already splits at statement boundaries specifically to avoid mid-sentence splits (this skill's own #1 quality killer), so a real regression usually means a chunker bug, not a Qdrant tuning issue.
"Should we add reranking / change hybrid fusion?" This repo already does hybrid dense+sparse with its own weighted RRF fusion in src/retrieval.pynot Qdrant's built-in RRF query feature this skill assumes. Use its guidance to inform tuning decisions on top of that custom implementation, not as a drop-in Qdrant-side config change.
Ambiguous/no specific quality question Test with exact search first to isolate whether the issue is retrieval or ranking.

First determine whether the problem is the embedding model, Qdrant configuration, or the query strategy. Most quality issues come from the model or data, not from Qdrant itself. If search quality is low, inspect how chunks are being passed to Qdrant before tuning any parameters. Splitting mid-sentence can drop quality 30-40%.

  • Start by testing with exact search to isolate the problem Search API

Diagnosis and Tuning

Isolate the source of quality issues, establish labeled baselines to measure recall and relevance, tune HNSW parameters, and choose the right embedding model. Diagnosis and Tuning

Search Strategies

Hybrid search, reranking, relevance feedback, and exploration APIs for improving result quality. Search Strategies

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 33 lines · 122 tokens per session scan A e4b6baaf3de9

Subscribe to this mod's changes

qdrant-search-quality is a skill published in the GitHub repository SecondLifes/code-intel (2 stars, last pushed 22d ago), licensed Apache-2.0. It adds 122 tokens to every session and 543 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

agent-platform-rag-engine-management

Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…

google/skills · 85 tokens

9router-embeddings

Generate vector embeddings via 9Router /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.

decolua/9router · 66 tokens

potpie-source-ingestion

Use when the user explicitly asks to ingest, refresh, or deeply understand a repository, PR, issue, ticket, runbook, incident report, document, or web link into Potpie. The harness performs todo-driven discovery, uses local/GitHub/integration tools and read-only subagents when available, builds evidence-backed…

potpie-ai/potpie · 82 tokens

ai

AI/LLM 能力索引。Agent 开发、LLM 安全、RAG 系统。当用户提到 AI、LLM、Agent、RAG、Prompt 时路由到此。.

fengshao1227/ccg-workflow · 45 tokens

embedding-strategies

Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.

foryourhealth111-pixel/Vibe-Skills · 37 tokens

generate-rag-dataset

Generate a synthetic evaluation dataset from your RAG knowledge base. Creates diverse Q&A pairs with expected answers and relevant context, ready for LangWatch experiments and platform import. Use when you need test data for your RAG pipeline.

langwatch/langwatch · 51 tokens