How do I install the RAG Project Query skill?

Run npx skillmds@latest add zhaixin244-wq/rag-project-query in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is RAG Project Query safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with RAG Project Query?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is RAG Project Query free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published RAG Project Query?

zhaixin244-wq (@zhaixin244-wq) published this skill. Their other Agent Skills are listed on their SkillMD profile.

RAG Project Query by zhaixin244-wq — Agent Skill

Name: RAG Project Query
Author: zhaixin244-wq

File contents

RAG Project Query — Project Knowledge Graph

Query the project-level LightRAG knowledge graph for architecture decisions, conventions, dependencies, and project-specific context.

Query Modes

Mode	When to use	What it does
`hybrid` (default)	Most queries	Combines local entity relationships + global topic summaries
`local`	"What's related to X in this project?"	Traverses entity relationships from specific nodes
`global`	"What are the project conventions?"	Summarizes across all project documents
`naive`	Simple keyword lookup	Basic text search, fastest but least intelligent

How to query

Full query

node -e "
const BASE = 'http://YOUR_LIGHTRAG_HOST:YOUR_PROJECT_PORT';
const API_KEY = process.env.LIGHTRAG_API_KEY || 'YOUR_API_KEY';
(async () => {
  const res = await fetch(BASE + '/query', {
    method: 'POST',
    headers: {
      'Content-Type': 'application/json',
      'X-API-Key': API_KEY
    },
    body: JSON.stringify({
      query: 'QUERY_HERE',
      mode: 'hybrid'
    })
  });
  const data = await res.json();
  console.log(JSON.stringify(data, null, 2));
})();
"

Context-only query

node -e "
const BASE = 'http://YOUR_LIGHTRAG_HOST:YOUR_PROJECT_PORT';
const API_KEY = process.env.LIGHTRAG_API_KEY || 'YOUR_API_KEY';
(async () => {
  const res = await fetch(BASE + '/query', {
    method: 'POST',
    headers: {
      'Content-Type': 'application/json',
      'X-API-Key': API_KEY
    },
    body: JSON.stringify({
      query: 'QUERY_HERE',
      mode: 'hybrid',
      only_need_context: true
    })
  });
  const data = await res.json();
  console.log(typeof data === 'string' ? data : JSON.stringify(data, null, 2));
})();
"

Response format

When presenting results:

Distinguish project memory from personal memory — prefix with "Project context:" when relevant
Be concise — summarize, don't dump raw JSON
Cite the source type (e.g., "from an architecture decision stored on 2026-03-20")
Flag stale info (>30 days old)
If no results, say so — don't fabricate

Infrastructure

Server: YOUR_LIGHTRAG_HOST:YOUR_PROJECT_PORT
Auth: X-API-Key header (auth-enabled mode)
Env var: LIGHTRAG_API_KEY
Workspace: Project-specific (separate from personal graph)

---name: rag-project-querydescription: Query the project-level LightRAG knowledge graph for project-specific context and decisions---# RAG Project Query — Project Knowledge GraphQuery the project-level LightRAG knowledge graph for architecture decisions, conventions, dependencies, and project-specific context.## Query Modes| Mode | When to use | What it does ||------|------------|--------------|| `hybrid` (default) | Most queries | Combines local entity relationships + global topic summaries || `local` | "What's related to X in this project?" | Traverses entity relationships from specific nodes || `global` | "What are the project conventions?" | Summarizes across all project documents || `naive` | Simple keyword lookup | Basic text search, fastest but least intelligent |## How to query### Full query```bashnode -e "const BASE = 'http://YOUR_LIGHTRAG_HOST:YOUR_PROJECT_PORT';const API_KEY = process.env.LIGHTRAG_API_KEY || 'YOUR_API_KEY';(async () => { const res = await fetch(BASE + '/query', { method: 'POST', headers: { 'Content-Type': 'application/json', 'X-API-Key': API_KEY }, body: JSON.stringify({ query: 'QUERY_HERE', mode: 'hybrid' }) }); const data = await res.json(); console.log(JSON.stringify(data, null, 2));})();"```### Context-only query```bashnode -e "const BASE = 'http://YOUR_LIGHTRAG_HOST:YOUR_PROJECT_PORT';const API_KEY = process.env.LIGHTRAG_API_KEY || 'YOUR_API_KEY';(async () => { const res = await fetch(BASE + '/query', { method: 'POST', headers: { 'Content-Type': 'application/json', 'X-API-Key': API_KEY }, body: JSON.stringify({ query: 'QUERY_HERE', mode: 'hybrid', only_need_context: true }) }); const data = await res.json(); console.log(typeof data === 'string' ? data : JSON.stringify(data, null, 2));})();"```## Response formatWhen presenting results:- Distinguish project memory from personal memory — prefix with "Project context:" when relevant- Be concise — summarize, don't dump raw JSON- Cite the source type (e.g., "from an architecture decision stored on 2026-03-20")- Flag stale info (>30 days old)- If no results, say so — don't fabricate## Infrastructure- **Server**: `YOUR_LIGHTRAG_HOST:YOUR_PROJECT_PORT`- **Auth**: X-API-Key header (auth-enabled mode)- **Env var**: `LIGHTRAG_API_KEY`- **Workspace**: Project-specific (separate from personal graph)

Frequently asked questions

RAG Project Query