跳到正文
TakoAPI
返回技能列表

hk101-living-rag

由 metatronsdoob369 提供

Search & Research
758下载量由 clawskills.sh 提供
2星标
0浏览量
0 个赞登录后即可为这个技能点赞
—暂无评分
你的评分

简介

Simple RAG over local text/markdown.

描述

该技能的功能

Runs retrieval-augmented generation over a local folder of text or markdown files. Given a query, it finds the most relevant document chunks and returns a synthesized answer with source snippets.

Keeps documents local and avoids uploading sensitive content to external search or indexing services.

何时使用

  • Querying a local knowledge base without a cloud service
  • Searching project documentation by natural language
  • Answering questions from a folder of meeting notes
  • Looking up policies stored as markdown files
  • Finding relevant content across a large docs directory

示例工作流

输入

User asks: 'What is our refund policy?' with docsPath set to ./company-docs

智能体
  1. 1

    Scans the target folder for text and markdown files

  2. 2

    Chunks documents into searchable segments

  3. 3

    Embeds the query and document chunks using OpenAI

  4. 4

    Retrieves the top k matching chunks by similarity score

  5. 5

    Synthesizes an answer from the matched content

输出

A direct answer to the query plus an array of matches with file path, score, and snippet for each

前置要求

  • OPENAI_API_KEY environment variable

安装

clawhub install metatronsdoob369/hk101-living-rag

运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。

链接