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.
- License 许可
- MIT
- 最近更新
- 2026-11-11
- Stars
- ★ 4.1w
- Forks
- 5.3k
01 前言 Front Matter
- name
- qdrant-search-quality
- description
- 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.
- allowed-tools
- [ "Read", "Grep", "Glob" ]
02 资源文件 9
- 脚本append-handoff.sh10.8 KB
- 脚本append-pr-decision.sh6.5 KB
- 脚本check-autoload-safety.sh2.7 KB
- 参考文档handoffs-index.template.md485 B
- 参考文档issue-brief.template.md1.5 KB
- 其他issue-comment-fingerprint1.4 KB
- 脚本latest-handoff.sh5.5 KB
- 参考文档pr-decisions.template.md1.4 KB
- 脚本status.sh3.8 KB
03 SKILL.md 正文
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
Diagnosis and Tuning
Isolate the source of quality issues, 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
04 同仓库更多 Skills
supabase-rls-policies
Write, review, and test Supabase Row Level Security (RLS) policies so that one user cannot read or change another user's rows. Use when creating or changing tables, policies, views, or security definer functions in a Supabase project, when reviewing a migration that touches RLS, or when asked to prove user isolation with pgTAP tests that sign in as two users.
skill-distribution-audit
Audit a skill collection before release or investigate installer omissions, archived/template leakage, duplicate identities, and manifest drift. Reconcile the intended public source set, distribution manifest, and actual discovery output for a specified consumer version. Includes a deterministic set-comparison helper.
logicapps-custom-code-net10-migration
Migrate Azure Logic Apps Standard local-function custom-code projects from .NET 8 to .NET 10. Use for legacy Logic Apps custom-code workspace upgrades, project/package configuration, custom-worker settings, publication, and integrated VS Code debugging. Not for ordinary .NET applications, standalone Azure Functions, Consumption workflows, or cloud deployment.
winmd-api-search
Find and explore Windows desktop APIs. Use when building features that need platform capabilities — camera, file access, notifications, UI controls, AI/ML, sensors, networking, etc. Discovers the right API for a task and retrieves full type details (methods, properties, events, enumeration values).
resemble-detect
Deepfake detection and media safety — detect AI-generated audio, images, video, and text, trace synthesis sources, apply watermarks, verify speaker identity, and analyze media intelligence using Resemble AI
quality-playbook
Run a complete quality engineering audit on any codebase. Derives behavioral requirements from the code, generates spec-traced functional tests, runs a three-pass code review with regression tests, executes a multi-model spec audit (Council of Three), and produces a consolidated bug report with TDD-verified patches. Finds the 35% of real defects that structural code review alone cannot catch. Works with any language. Trigger on 'quality playbook', 'spec audit', 'Council of Three', 'fitness-to-purpose', or 'coverage theater'.