About qdrant-search-quality
A routing skill for diagnosing Qdrant search-quality problems. It maps symptoms to the relevant guidance files, covering topics such as recall, embeddings, hybrid search, reranking, and relevance feedback.
Key features
- 01Routes symptoms to guidance files
- 02Covers recall and precision issues
- 03Directs embedding-quality investigations
- 04Covers hybrid search strategies
- 05Includes reranking and relevance feedback
Use cases
- 01Finding guidance for irrelevant results
- 02Investigating missing search matches
- 03Choosing an approach to hybrid search
- 04Improving result diversity or relevance
Install
Copy the command and run it in a terminal.
npx skills add https:/After installing, type/qdrant-search-qualityin Claude Code to confirm it loaded.
Details
From the project READMEQdrant Search Quality
Route first, then answer. Match the user's symptom in the table, Read that file, and answer from it.
Do not answer from this page alone: it contains routing only, not the guidance. If two rows match, read both.
| The user says | Read |
|---|---|
| Search results are bad or irrelevant, wrong results, missing expected matches | diagnosis/SKILL.md |
| Low recall, expected results are missing | diagnosis/SKILL.md |
| Low precision, too many wrong matches | diagnosis/SKILL.md |
| Which embedding model to use, quality dropped after quantization, model change, or data growth | diagnosis/SKILL.md |
| Not sure if the model, the data, or Qdrant is at fault | diagnosis/SKILL.md |
| Want to measure recall, build a golden set, ground truth dataset, recall@k | diagnosis/SKILL.md |
| Is my improvement real, statistically significant, fine-tune the embedding model | diagnosis/SKILL.md |
| Need to combine keyword and semantic search, hybrid search, sparse + dense, fusion / RRF, prefetch | search-strategies/hybrid-search/SKILL.md |
| Should I rerank, results too similar, need diversity, MMR, recommendation/discovery API | search-strategies/SKILL.md |
| Improving results with relevance feedback or user clicks, cheaper alternative to reranking | search-strategies/relevance-feedback/SKILL.md |
Most quality issues come from the embedding model or the data, not from Qdrant's configuration — splitting chunks mid-sentence alone can drop quality 30-40%. Rule that out with exact search before tuning any Qdrant parameter: Search API