Skip to content
Back to skills

Query

ASecurity

Use when retrieving from a project knowledge-base/ — multi-channel RAG recall (vector plus lexical plus metadata, RRF-fused) returning locate-pointer cards; multi-round and multi-angle querying allowed. Trigger /ragkit:query, or called by name by workflows like specode. Building or refreshing the index instead uses ragkit:embed.

  • 3 stars
  • 0 votes
  • 0 copies
  • 2 views
  • Added September 6, 2026
development

Security analysis

A100/100

Scanned September 6, 2026

npx -y skills add qxbyte/specode --skill query --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Query?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Query
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/qxbyte-query/badge)](https://www.skillsdirectory.com/skills/qxbyte-query)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: query
description: Use when retrieving from a project knowledge-base/ — multi-channel RAG recall (vector plus lexical plus metadata, RRF-fused) returning locate-pointer cards; multi-round and multi-angle querying allowed. Trigger /ragkit:query, or called by name by workflows like specode. Building or refreshing the index instead uses ragkit:embed.
---

# RagKit Query

对项目 `knowledge-base/` 做多路召回(向量+词汇+元数据,RRF 融合),返回**定位卡片**。

## 执行

脚本在本插件的 `scripts/` 目录(本 skill 目录的上两级);用本 skill 的 base directory 把下面的相对路径拼成绝对路径执行。

```sh
sh ../../scripts/run.sh ../../scripts/ragkit.py \
   query '<检索词>' --kb <项目根>/knowledge-base
```

- 检索词由你根据用户问题/需求**自行提炼**:优先用页面名、字段名、接口路径、功能域词。
- **允许多轮、多角度**:一轮不够就换角度再查(按页面查 / 按字段查 / 按调用链查),直到定位充分或确认无相关知识。
- 需要程序化消费时加 `--json`;`--top N` 调数量。

## 结果使用纪律(硬约束)

1. 卡片是**定位指针,非事实来源**——命中后用「路径」`Read` 原文,再跳到真实代码验证;禁止仅凭卡片摘要下结论。
2. tag/词面命中 ≠ 语义相关:逐条判断该知识点的改动类型/语义是否真适用,不适用就丢弃。
3. 独立 RAG 用法(用户直接提问系统历史逻辑):召回 → Read 命中文档 → 综合整理回答,并注明来源文档路径。

## 降级与错误(stderr 信号,固定文案)

- `无可用向量后端`:结果仍有效(词汇+元数据路);stderr 会带一个 ╭─ RagKit ─╮ 提示块,**原样转述给用户**(不改写、不省略)。
- `向量后端调用失败`(`vector_error`):云端密钥失效/网络异常等,query **不崩溃**,已自动降级词汇+元数据路,结果仍有效;stderr 带失败详情,转述并提示用户检查密钥(环境变量是否设对、是否用了完整 key)或网络后重试。
- `索引不存在`:提示用户先跑 `/ragkit:embed`。
- `model_mismatch` / `index_stale`:提示用户重跑 `/ragkit:embed`(必要时 `--rebuild`)。

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.