peaqOS AI

Use the peaqOS agent skill to onboard machines, query MCR, and run fleet workflows from any AI coding agent.

peaqOS ships one agent skill, peaqos, that walks your AI agent through machine onboarding. It follows the skill.md spec and has adapters for Claude Code, Cursor, and Windsurf, plus a manual upload path for any other runtime that reads the standard. It drives the peaqos Python CLI, so anything you can do at the terminal, the skill can do for you.

What the skill does

Trigger it in your agent (/peaqos in Claude Code, or just describe what you want elsewhere) and it picks the right mode based on what you ask:

Mode	When it kicks in
Demo	First-time tour on agung testnet. Full onboarding in about 15 minutes, with explanations at every step.
Real onboarding	Asks five questions about your machine and deployment, recommends a self-managed or operator-managed setup, then runs the CLI to activate the machine and submit the first event.
Fleet management	Pulls MCR scores for an operator’s fleet, surfaces machines with low or no rating, submits heartbeat events.
Machine Markets (Scale)	Onboards a machine to the orchestrator, pairs an agent with a delegation policy, runs market search, places an order, and confirms or disputes delivery with peaqos scale .... Scale is paused right now: onboarding a machine to the orchestrator fails for every machine (see Scale).
Stream / Verify	Publishes or buys machine data with peaqos stream ...; reads a machine’s KYB and chip status and prepares chip preflight evidence with peaqos verify ....
Troubleshooting	Diagnoses common failures (funding, activation, MCR lag, key mismatches) and walks you through the fix.

The skill adapts its tone to your background: concise for developers, plain English with narrated steps for non-technical operators.

Install

Two pieces. The CLI does the actual work; the skill is the orchestration layer your agent loads.

1. Install the CLI

python3 -m venv .peaqos-env
source .peaqos-env/bin/activate
pip install -U 'peaq-os-cli[ows,solana]'
peaqos --version

The skill tracks the current CLI release. It covers Economics 2.0 activation, machine management, monetization, Scale (paused), Stream, Verify status reads and chip preflight, and the Solana onboarding path.

2. Add the skill to your agent

# Auto-detect (Claude Code, Cursor, or Windsurf)
npx skills add peaqnetwork/peaq-os-skills

# Or target a runtime: claude-code, cursor, windsurf
npx skills add peaqnetwork/peaq-os-skills --agent claude-code

The installer detects the agent on disk and prompts you if it finds several. Invoke /peaqos in Claude Code, or describe what you want (for example “onboard my machine to peaqOS”) in Cursor or Windsurf.

For ChatGPT, Claude Projects, custom GPTs, or anywhere you can’t run a local CLI, clone the repo and upload skills/peaqos/AGENT-PROMPT.md as the system prompt, with GUIDE.md and knowledge/ from the same folder as knowledge sources:

git clone https://github.com/peaqnetwork/peaq-os-skills

LLM context files

Separate from the skill, Mintlify auto-generates machine-readable bundles of these docs. Point any agent at one of:

File	URL	Use when
llms.txt	https://docs.peaq.xyz/llms.txt	Model has a modest context window or you want a compact index with links
llms-full.txt	https://docs.peaq.xyz/llms-full.txt	Model has a large context window and you want the full docs inline
skill.md	https://docs.peaq.xyz/skill.md	Agent needs a doc-derived capabilities spec rather than prose docs

These are doc context, not a substitute for the peaqos skill. The skill knows the onboarding flow, the decision tree, and the recovery paths. The generated bundles only know what is on the page.

Editor setup (docs context)

Wire the peaq docs into your editor. This is independent of the peaqos skill and useful any time you want the agent to ground answers in the current docs.

Cursor

Open Cursor Settings → Features → Docs, click Add new doc, and paste:

https://docs.peaq.xyz/llms-full.txt

Reference peaq in chat with @docs → peaq.

Windsurf

Windsurf has no persistent docs store. Paste into Cascade (Cmd+L) per chat:

@docs:https://docs.peaq.xyz/llms-full.txt

Claude Code

Add the Mintlify-hosted MCP server to .mcp.json:

{
  "mcpServers": {
    "peaq-docs": { "type": "http", "url": "https://docs.peaq.xyz/mcp" }
  }
}

Or add it from the terminal:

claude mcp add --transport http peaq-docs https://docs.peaq.xyz/mcp

Claude Desktop / ChatGPT / any MCP client

Same MCP URL: https://docs.peaq.xyz/mcp. For custom GPTs or Claude Projects, upload llms-full.txt as a knowledge source.

See also

peaqChain AI integrations

Chain-level prompting tips, Cursor Projects, peaq SDK prompt patterns.

SDK reference

The ground truth the skill calls into via the CLI.