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.

跳到安装

仓库: github/awesome-copilot
最近来源活动: 2026年4月17日 00:54
检测到的 SKILL.md 语言: 英语
星标: 39,498
分支: 5,019

安装方式

默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

直接命令不会经过审查 Prompt；运行前请先检查来源。

npx skills add https://github.com/github/awesome-copilot --skill qdrant-search-quality

命令会保持在同一行。复制前请横向滚动并检查完整内容。

想先保存到本地？可下载 SkillsMP 当前能够提供的文件。

检查来源文件

决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。

文件资源管理器

3 个文件

SKILL.md

来源说明 · 只读预览

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"]

# 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)

在 GitHub 查看

返回搜索返回安装

v-development

Guide GitHub Copilot through V language development: installing the toolchain, project layout with v.mod, building, testing, formatting, and writing idiomatic V including Option/Result error handling. Use when the user works with V source files, v.mod projects, or asks about V syntax, tooling, and conventions.

2026-09-29

lean-comments

Audits, writes, and refines maintained first-party source-code comments and declaration-level documentation across languages. Use when adding, editing, reviewing, cleaning up, or auditing comments, doc comments, docstrings, TODO, FIXME, NOTE, suppressions, or other source commentary, including while modifying code and deciding whether a comment is warranted at all. Defaults to no comment unless it preserves meaningful, non-obvious information that cannot reasonably be recovered from the code or nearby repository context.

2026-09-29

audit-integrity

Enforce output quality, evidence verification, and quality gates across security audits. Use this skill when you perform SAST, SCA, threat modeling, or security code reviews. Use this skill to verify code locations and taint traces for all findings. Use this skill to prevent the suppression of valid security findings. Use this skill to evaluate reports against quality thresholds (score ≥ 8/10) before delivery.

2026-09-29

查看这个仓库的全部 Skills

qdrant-search-quality

来源信息

安装方式

检查来源文件

同仓库更多 Skills

同仓库更多 Skills