Testing & QAlow risk

qdrant-search-quality

Diagnoses and improves Qdrant search relevance. Use when someone reports 'search results are bad', 'wrong results', 'low precision', 'low recall', 'irrelevant matches', 'missing expected results', or asks 'how to improve search quality?', 'which embedding model?', 'should I use hybrid search?', 'should I use reranking?'. Also use when search quality degrades after quantization, model change, or data growth.

github/awesome-copilot·skills/qdrant-search-quality/SKILL.md

100/ 100品質

↓

この Skill を導入

coding agent を選び、プロジェクト用または個人用コマンドをコピーします。

収録 commit に固定

プロジェクトに導入.agents/skills/qdrant-search-quality

npx skills add https://github.com/github/awesome-copilot/tree/0aaced533251f5b86c69dfbc5e55db74c4b4d1af/skills/qdrant-search-quality -a codex -y

個人環境に導入~/.agents/skills/qdrant-search-quality

npx skills add https://github.com/github/awesome-copilot/tree/0aaced533251f5b86c69dfbc5e55db74c4b4d1af/skills/qdrant-search-quality -a codex -g -y

手動配置先.agents/skills/qdrant-search-qualityOfficial docs ↗

プロジェクトに導入.claude/skills/qdrant-search-quality

npx skills add https://github.com/github/awesome-copilot/tree/0aaced533251f5b86c69dfbc5e55db74c4b4d1af/skills/qdrant-search-quality -a claude-code -y

個人環境に導入~/.claude/skills/qdrant-search-quality

npx skills add https://github.com/github/awesome-copilot/tree/0aaced533251f5b86c69dfbc5e55db74c4b4d1af/skills/qdrant-search-quality -a claude-code -g -y

手動配置先.claude/skills/qdrant-search-qualityOfficial docs ↗

プロジェクトに導入.agents/skills/qdrant-search-quality

npx skills add https://github.com/github/awesome-copilot/tree/0aaced533251f5b86c69dfbc5e55db74c4b4d1af/skills/qdrant-search-quality -a github-copilot -y

個人環境に導入~/.copilot/skills/qdrant-search-quality

npx skills add https://github.com/github/awesome-copilot/tree/0aaced533251f5b86c69dfbc5e55db74c4b4d1af/skills/qdrant-search-quality -a github-copilot -g -y

手動配置先.agents/skills/qdrant-search-qualityOfficial docs ↗

プロジェクトに導入.agents/skills/qdrant-search-quality

npx skills add https://github.com/github/awesome-copilot/tree/0aaced533251f5b86c69dfbc5e55db74c4b4d1af/skills/qdrant-search-quality -a cursor -y

個人環境に導入~/.cursor/skills/qdrant-search-quality

npx skills add https://github.com/github/awesome-copilot/tree/0aaced533251f5b86c69dfbc5e55db74c4b4d1af/skills/qdrant-search-quality -a cursor -g -y

手動配置先.agents/skills/qdrant-search-qualityOfficial docs ↗

プロジェクトに導入.agents/skills/qdrant-search-quality

npx skills add https://github.com/github/awesome-copilot/tree/0aaced533251f5b86c69dfbc5e55db74c4b4d1af/skills/qdrant-search-quality -a gemini-cli -y

個人環境に導入~/.gemini/skills/qdrant-search-quality

npx skills add https://github.com/github/awesome-copilot/tree/0aaced533251f5b86c69dfbc5e55db74c4b4d1af/skills/qdrant-search-quality -a gemini-cli -g -y

Native Gemini CLI

gemini skills install https://github.com/github/awesome-copilot.git --scope workspace --path skills/qdrant-search-quality

手動配置先.agents/skills/qdrant-search-qualityOfficial docs ↗

⚠ インストールには open-source skills CLI を使用します。実行前にソースと権限を確認してください。

Skill の指示

GitHub で元ファイルを表示 ↗

# Qdrant Search Quality

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](https://search.qdrant.tech/md/documentation/search/search/?s=search-api)


## Diagnosis and Tuning

Isolate the source of quality issues, tune HNSW parameters, and choose the right embedding model. [Diagnosis and Tuning](diagnosis/SKILL.md)


## Search Strategies

Hybrid search, reranking, relevance feedback, and exploration APIs for improving result quality. [Search Strategies](search-strategies/SKILL.md)