How do I install the RAG Project Remember skill?

Run npx skillmds@latest add butchokoy25/rag-project-remember 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 Remember 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 Remember?

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 Remember free to use?

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

Who published RAG Project Remember?

butchokoy25 (@butchokoy25) published this skill. Their other Agent Skills are listed on their SkillMD profile.

RAG Project Remember by butchokoy25

Name: RAG Project Remember
Author: butchokoy25

File contents

RAG Project Remember — Store to Project Knowledge Graph

Store project-specific knowledge — architecture decisions, conventions, dependencies, and requirements — into the project-level LightRAG graph.

Formatting rules

Format each entry as:

[TYPE] Title — YYYY-MM-DD

What: Brief description
Why: The reasoning or constraint behind it
Files: Relevant file paths (if applicable)

Entry types

Type	Use for
`ARCHITECTURE`	System design choices, component structure, data flow
`CONVENTION`	Coding standards, naming patterns, file organization rules
`DECISION`	Technology choices, library selections, approach decisions
`DEPENDENCY`	External services, APIs, packages, version constraints
`CONFIG`	Environment setup, build config, deployment settings
`REQUIREMENT`	Business rules, constraints, acceptance criteria
`INSIGHT`	Performance findings, gotchas, non-obvious behaviors

How to store

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 + '/documents/text', {
    method: 'POST',
    headers: {
      'Content-Type': 'application/json',
      'X-API-Key': API_KEY
    },
    body: JSON.stringify({
      file_source: '[TYPE] Title — YYYY-MM-DD',
      text: 'Full content here with What/Why/Files structure'
    })
  });
  console.log('Status:', res.status);
})();
"

After inserting

Confirm to the user: "Stored to project memory: [TYPE] Title"
Do NOT dump the raw API response

When NOT to use this

Use /rag-remember (personal graph) instead for:

User preferences — working style, tool preferences, communication style
Cross-project knowledge — things that apply to all projects
Personal context — roles, responsibilities, machine config
People info — contacts, working relationships

This skill is for things specific to the current project that wouldn't be relevant elsewhere.

Infrastructure

Server: YOUR_LIGHTRAG_HOST:YOUR_PROJECT_PORT
Auth: X-API-Key header (auth-enabled mode)
Env var: LIGHTRAG_API_KEY

---name: rag-project-rememberdescription: Store project-specific knowledge into the project-level LightRAG knowledge graph---# RAG Project Remember — Store to Project Knowledge GraphStore project-specific knowledge — architecture decisions, conventions, dependencies, and requirements — into the project-level LightRAG graph.## Formatting rulesFormat each entry as:```[TYPE] Title — YYYY-MM-DDWhat: Brief descriptionWhy: The reasoning or constraint behind itFiles: Relevant file paths (if applicable)```### Entry types| Type | Use for ||------|---------|| `ARCHITECTURE` | System design choices, component structure, data flow || `CONVENTION` | Coding standards, naming patterns, file organization rules || `DECISION` | Technology choices, library selections, approach decisions || `DEPENDENCY` | External services, APIs, packages, version constraints || `CONFIG` | Environment setup, build config, deployment settings || `REQUIREMENT` | Business rules, constraints, acceptance criteria || `INSIGHT` | Performance findings, gotchas, non-obvious behaviors |## How to store```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 + '/documents/text', { method: 'POST', headers: { 'Content-Type': 'application/json', 'X-API-Key': API_KEY }, body: JSON.stringify({ file_source: '[TYPE] Title — YYYY-MM-DD', text: 'Full content here with What/Why/Files structure' }) }); console.log('Status:', res.status);})();"```## After inserting- Confirm to the user: "Stored to project memory: [TYPE] Title"- Do NOT dump the raw API response## When NOT to use thisUse `/rag-remember` (personal graph) instead for:- **User preferences** — working style, tool preferences, communication style- **Cross-project knowledge** — things that apply to all projects- **Personal context** — roles, responsibilities, machine config- **People info** — contacts, working relationshipsThis skill is for things **specific to the current project** that wouldn't be relevant elsewhere.## Infrastructure- **Server**: `YOUR_LIGHTRAG_HOST:YOUR_PROJECT_PORT`- **Auth**: X-API-Key header (auth-enabled mode)- **Env var**: `LIGHTRAG_API_KEY`

Frequently asked questions

RAG Project Remember