dsh-doc-search
Skill79 starsChanged 14 days agoMITView on GitHub
手机本地代码仓库、技术文档、配置文件与日志的秒级轻量级索引与精准智能检索（Local Code & Doc RAG）。用于“帮我查一下源码里怎么写的”、“检索本地文档”、“针对某个项目进行代码问答”等需求。
In this repository26 other files it gives its agents.
- doc-tidySkill
- dsh-backupSkill
- dsh-claude-styleSkill
- dsh-code-craftSkill
- dsh-crewSkill
- dsh-data-craftSkill
- dsh-deep-researchSkill
- dsh-diagramSkill
- dsh-doc-publisherSkill
- dsh-doc-tidySkill
- dsh-excel-copilotSkill
- dsh-flashgouSkill
- dsh-lifeSkill
- dsh-mail-craftSkill
- dsh-meeting-copilotSkill
- dsh-memory-syncSkill
- dsh-mobileSkill
- dsh-reviewSkill
- dsh-scrum-masterSkill
- dsh-slidesSkill
- dsh-storyboardSkill
- dsh-tierSkill
- dsh-videoSkill
- dsh-voiceSkill
- dsh-web-crawlerSkill
- dsh-write-craftSkill
The file
Files
本地文档与代码库智能检索技能 (dsh-doc-search)
本技能为 DSH 安卓端提供了零第三方依赖的本地知识库秒级分块与高精度智能问答检索能力。
知识库索引文件存放在 /sdcard/Download/DSH_Knowledge/。
常用操作
脚本位置：优先使用随包分发的
<本技能目录>/scripts/rag.mjs，或/sdcard/DeepSeekHarness/tools/rag.mjs。
1. 为指定目录/代码仓建立知识库
node <本技能目录>/scripts/rag.mjs index <目录路径> [--name 知识库名称]- 自动过滤
node_modules、.git、build等冗余目录，提取所有源码与 Markdown/文本文件分块切片。
2. 查看所有已有知识库
node <本技能目录>/scripts/rag.mjs list3. 多维关键词/语义检索
node <本技能目录>/scripts/rag.mjs search "<查询内容/函数名/报错信息>" [--kb 知识库名称]4. 获取 AI 问答参考上下文
node <本技能目录>/scripts/rag.mjs context "<问题>" [--kb 知识库名称]- 直接输出结构化 Markdown 上下文代码段与行号，供 AI 精准分析作答。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.