# Onboarding

> Use when HA NOVA Relay requests fail due to onboarding, connectivity, or auth issues.

- **Type:** Skill
- **Install:** `agentstack add skill-markusleben-ha-nova-onboarding`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [markusleben](https://agentstack.voostack.com/s/markusleben)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [markusleben](https://github.com/markusleben)
- **Source:** https://github.com/markusleben/ha-nova/tree/main/skills/onboarding
- **Website:** https://github.com/markusleben/ha-nova

## Install

```sh
agentstack add skill-markusleben-ha-nova-onboarding
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# HA NOVA Onboarding

## Scope

Use when HA NOVA requests fail due to onboarding, connectivity, or auth issues.
Diagnostics only. Do not use this skill for config writes or routine HA operations after readiness is restored.

## Bootstrap

Relay CLI command: `ha-nova relay`
If missing: `ha-nova setup`

## Flow

1. Run diagnostics only after a real failure.
2. Classify failure quickly:
   - `401/403`: relay auth token mismatch
   - `404`: endpoint/path mismatch
   - connect error / status `000`: relay unreachable
   - `ha_ws_connected=false`: relay is reachable but not proven ready yet; confirm with `/ws` or `ha-nova doctor` before blaming LLAT
   - `/ws` proves `LLAT is required`: Home Assistant access token (`ha_llat`) is missing or wrong
3. Return one concrete remediation step.

## Standard Remediation Commands

- onboarding setup:
  - `ha-nova setup`
- health quick check:
  - `ha-nova relay health`
- doctor detail:
  - `ha-nova doctor`

## Output Format

Return a short diagnostic report:
1. **Status** — one-line result (e.g., "Relay reachable", "Auth token mismatch")
2. **Details** — error code or relevant diagnostic output (only on failure)
3. **Next step** — one concrete remediation command (only on failure)

On success, keep the response to the status line only. Do not dump raw relay output.

## Safety

- Diagnostics only — this skill never modifies Home Assistant state, config, or relay settings.
- Never ask the user to paste tokens or secrets in chat.
- All communication with Home Assistant goes through `ha-nova relay` exclusively.

## Guardrails

- no proactive doctor/ready in normal success path
- keep response short and action-oriented
- never ask user to paste secrets in chat

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [markusleben](https://github.com/markusleben)
- **Source:** [markusleben/ha-nova](https://github.com/markusleben/ha-nova)
- **License:** MIT
- **Homepage:** https://github.com/markusleben/ha-nova

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-markusleben-ha-nova-onboarding
- Seller: https://agentstack.voostack.com/s/markusleben
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.