agentleFS
ThisisYoYoDevThisisYoYoDev/claude-rag/skills/setup/SKILL.md

setup

Skill9 starsChanged 8 months agoMITView on GitHub

First-time setup for the Claude RAG plugin — configure backend connection, test everything, show quick reference

  • Reads credentials
  • Sends data out

191 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use add-voice-transcription, add-discord and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • juancruzmunozalbeloSkill

    add-voice-transcription

    Add voice message transcription to NanoClaw using OpenAI's Whisper API. Automatically transcribes WhatsApp voice notes so the agent can read and respond to them.

    Also in 5 projects that use this

  • MicrosoftSkill

    add-discord

    Add Discord bot channel integration via Chat SDK.

    Also in 11 projects that use this

  • MicrosoftSkill

    add-slack

    Add Slack channel integration via Chat SDK.

    Also in 11 projects that use this

  • juancruzmunozalbeloSkill

    add-telegram-swarm

    Add Agent Swarm (Teams) support to Telegram. Each subagent gets its own bot identity in the group. Requires Telegram channel to be set up first (use /add-telegram). Triggers on "agent swarm", "agent teams telegram", "telegram swarm", "bot pool".

    Also in 7 projects that use this

  • +8 more from microsoft

The file

We split this skill into the rules it gives an agent

9 rules. 0 are common, 7 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 168 edited versions we read keep these.

  • 7

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If config exists, show current settings and ask if they want to reconfigure.

    line 20
  2. Distinctive:

    Check if Docker is running and the backend is accessible:

    line 34
  3. Distinctive:

    If not accessible, tell the user:

    line 38
  4. Distinctive:

    Use AskUserQuestion to get:

    line 46
  5. Distinctive:

    Create the config directory and file:

    line 52
  6. Very specific:

    Write ~/.claude/plugins/claude-rag/config.json with the chosen settings merged with defaults:

    line 58
  7. Very specific:

    Verify the response shows "status": "ok" and "db": true.

    line 96
  8. Distinctive:

    Wait 3 seconds for embedding, then search:

    line 107
  9. Distinctive:

    Verify a result comes back with score > 0.8.

    line 114

“Common” is measured: kept by at least 6 in 10 of the 168 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

RAG Plugin Setup

Guide the user through first-time setup of the Claude RAG plugin.

Steps

Step 1: Check current config

cat ~/.claude/plugins/claude-rag/config.json 2>/dev/null || echo "NO_CONFIG"

If config exists, show current settings and ask if they want to reconfigure.

Step 2: Choose connection mode

Use AskUserQuestion:

  • header: "Claude RAG Setup"
  • question: "How do you want to connect to the RAG backend?"
  • options:
    • "Local (Docker — for development only)"
    • "Cloud (remote server)"

Step 3: Configure endpoint

If Local:

  • Check if Docker is running and the backend is accessible:
    curl -s --max-time 3 https://api.clauderag.io/health
  • If not accessible, tell the user:
    Start the backend with:
    cd <project-root> && docker compose -f docker/docker-compose.yml up -d
    Then: bun run backend/src/index.ts

If Cloud:

  • Use AskUserQuestion to get:
    • Endpoint URL
    • API key

Step 4: Write config

Create the config directory and file:

mkdir -p ~/.claude/plugins/claude-rag

Write ~/.claude/plugins/claude-rag/config.json with the chosen settings merged with defaults:

{
  "connection": {
    "endpoint": "<chosen_endpoint>",
    "apiKey": "<if_cloud>"
  },
  "capture": {
    "enabled": true,
    "userPrompts": true,
    "aiOutputs": true,
    "toolCalls": true,
    "toolResults": true,
    "subAgents": true,
    "multimodal": { "copyFiles": true, "maxFileSize": "50MB" },
    "exclude": { "tools": ["AskUserQuestion"], "pathPatterns": ["*.env", "*.secret", "*credentials*"] }
  },
  "rag": {
    "mode": "auto",
    "threshold": 0.6,
    "maxContextTokens": 5000,
    "perPrompt": { "enabled": true, "maxItems": 5, "maxLatencyMs": 500 },
    "sessionStart": { "enabled": true, "maxItems": 3 }
  },
  "privacy": {
    "redactSecrets": true,
    "excludePatterns": ["password", "token", "secret", "api_key", "private_key"]
  }
}

Step 5: Test the connection

curl -s <endpoint>/health

Verify the response shows "status": "ok" and "db": true.

Step 6: Run a test cycle

Ingest a test event:

curl -s -X POST <endpoint>/api/v1/ingest \
  -H "Content-Type: application/json" \
  -d '{"events":[{"session_id":"setup-test","agent_id":"main","content_type":"user_prompt","content":"RAG plugin setup test","agent_type":"main","is_sub_agent":false,"hook_event_name":"UserPromptSubmit","timestamp":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}],"project":"setup-test"}'

Wait 3 seconds for embedding, then search:

sleep 3 && curl -s -X POST <endpoint>/api/v1/search \
  -H "Content-Type: application/json" \
  -d '{"query":"RAG plugin setup test","limit":1}'

Verify a result comes back with score > 0.8.

Step 7: Show success

Display:

Setup complete! The RAG plugin is now active.

Your conversations are being captured automatically.
Context from past sessions will be injected into your prompts.

Quick reference:
  /claude-rag:search [query]  — Search past conversations
  /claude-rag:ask [question]  — Ask about past work
  /claude-rag:browse          — Browse sessions & projects
  /claude-rag:stats           — View statistics
  /claude-rag:config          — Change settings
  /claude-rag:forget          — Soft-delete data

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.