Skip to content
Skills Library
DevOps & cloud · Tool integration

using-navaris-cli

/using-navaris-cli

Use when the user asks Claude to do anything with navaris sandboxes via the CLI — create/start/stop sandboxes, exec commands, snapshot, attach, manage projects. Establishes environment, picks the right task skill, and points autonomous-agent use cases at the MCP server.

Author
erans ↗
Repository
navaris ↗
Licence
Apache-2.0
Last repository change
07.08.2026

Assessment and security

90/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content25 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
1
Deprecation

No signals detected. Repository changed on 07.08.2026, without references to retired models or APIs.

Licence

Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.

What it does and when to use it

Use when the user asks Claude to do anything with navaris sandboxes via the CLI — create/start/stop sandboxes, exec commands, snapshot, attach, manage projects. Establishes environment, picks the right task skill, and points autonomous-agent use cases at the MCP server.

Original author description

Use when the user asks Claude to do anything with navaris sandboxes via the CLI — create/start/stop sandboxes, exec commands, snapshot, attach, manage projects. Establishes environment, picks the right task skill, and points autonomous-agent use cases at the MCP server.

How it works

  1. MCP fork
  2. Environment check (always run before any CLI command)
  3. Routing table
  4. Quiet mode for scripting
  5. Red flags
  6. When to escalate
Original SKILL.md headings · 50 lines, 490 words
SKILL.md preview
---
name: using-navaris-cli
description: Use when the user asks Claude to do anything with navaris sandboxes via the CLI — create/start/stop sandboxes, exec commands, snapshot, attach, manage projects. Establishes environment, picks the right task skill, and points autonomous-agent use cases at the MCP server.
---

# Using Navaris CLI

Navaris is a sandbox control plane with two backends (Incus containers, Firecracker microVMs) and one CLI (`navaris`). This skill pack teaches Claude Code how to drive that CLI on a user's behalf.

**Announce at start:** "I'm using the using-navaris-cli skill to drive navaris."

## MCP fork

If the user is driving navaris from an autonomous agent loop with no human in the chair, **prefer the MCP server** instead. See `docs/mcp.md` in the navaris repo. This pack is for human-in-the-loop CLI work in Claude Code — it goes through Bash, one command at a time, with user approval on destructive steps.

## Environment check (always run before any CLI command)

1. **`NAVARIS_API_URL`** — required. If unset, ask the user. Common default: `http://localhost:8080`.
2. **`NAVARIS_TOKEN`** — required when the daemon was started with `--auth-token`.
3. **`NAVARIS_PROJECT`** — optional, but highly recommended to set once so sandbox commands don't need `--project` on every call.
4. **One-shot health check:** `navaris project list --quiet --output json >/dev/null`. Classify failure:
   - `command not found` → CLI not installed → route to `navaris-getting-started`.
   - HTTP 401 → token missing or wrong → route to `navaris-getting-started`.
   - `connection refused` / `dial tcp` → daemon down → surface to user before proceeding.

## Routing table

Match the user's intent to one of the task skills and invoke it via the Skill tool:

| User intent | Skill |
|---|---|
| Install CLI, set up env, "where do I start" | `navaris-getting-started` |
| Create/list/start/stop/destroy a sandbox; manage projects/ports; pick a backend | `navaris-managing-sandboxes` |
| Run a command in a sandbox; attach a terminal; manage sessions | `navaris-running-commands` |
| Snapshot, restore, promote to image, wait on async operations | `navaris-snapshots-images-async` |

If the user's question spans two skills, start with the one that matches the verb they used (e.g. "snapshot the sandbox and then destroy it" → `navaris-snapshots-images-async` first).

## Quiet mode for scripting

Pass `--quiet` (`-q`) on operation commands so they print only the resulting ID — useful for `xargs`, shell variables, and scripted pipelines. For list commands, use `--output json | jq -r '.[].SandboxID'` (or the corresponding Pascal-case ID field: `SessionID`, `SnapshotID`, `ProjectID`, `ImageID`) since `--quiet` does not strip the table on lists.

## Red flags

- **Never** pass `--auth-token` directly to `navarisd` in a shared shell history. Use an env file or a secret manager.
- **Never** run `sandbox destroy` without confirming the sandbox ID with the user first.
- **Never** assume the daemon is up — always run the health check above.
- **Never** edit daemon config (KVM, jailer, OTLP flags) from this skill pack — that's an operator concern, out of scope here.
- **Never** fabricate command flags. Run `navaris <cmd> --help` if unsure.

## When to escalate

If the user asks for something not covered by the four task skills (e.g. web UI config, daemon operator tasks, SDK usage) say so and point them at `README.md` and `docs/mcp.md`.

Versions

The database has no other skills named using-navaris-cli.

Database snapshot: 13.11.2026 · package version 09c408456267 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 95navaris-managing-sandboxes
    Use when the user wants to create, list, start, stop, or destroy navaris sandboxes, manage projects, publish ports, or decide between the Incus and Firecracker backends. Covers the full sandbox lifecycle plus project/port CRUD.
  • 95navaris-running-commands
    Use when the user wants to run commands inside a navaris sandbox — one-shot exec, persistent interactive sessions, or attaching a terminal. Covers env/workdir/timeout on exec, session lifecycle, attach over WebSocket, and picking between exec and session.
  • 95b2c-sandbox
    Create and manage on-demand sandboxes (ODS) for B2C Commerce using the b2c CLI. Use this skill whenever the user needs to spin up a new development sandbox, list running sandboxes, start/stop/restart an instance, or manage sandbox lifecycle — even if they just say "I need a…
  • 100fleet
    Create sandboxes on the owner's intentic account from inside this one, via the `sandboxes` CLI, read what the account already runs, and remove one a task is done with. Use when a task needs a SEPARATE sandbox — a second project, a specialized agent with its own tools and access,…
  • 100boat
    Manage Boat (boat.dev, formerly Box by Ascii) cloud sandboxes via API, CLI, and SSH. Use for provisioning, environments, secrets, templates, snapshots, stop/resume/fork, or running BB and coding agents on Boat.
  • 95vz
    Run commands in a vz Developer Environment through the five-verb CLI (up, exec, status, stop, delete). Use when the user requests vz Linux or native macOS Machine execution or the task needs the project's vz.json Environment; the presence of vz.json alone does not require moving…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.