dlazy-chat

English · 中文

Chat with the dlazy sandbox agent — a project-scoped assistant that runs skills end-to-end over multiple turns. Discover skills and projects with dlazy skills list / dlazy projects list.

Trigger Keywords

• chat, talk to the agent
• sandbox agent, project conversation
• continue a project, multi-turn task

Authentication

All requests require a dLazy API key. The recommended way to authenticate is:

This runs a device-code flow (also works in remote shells) and **automatically saves your API key** to the local CLI config — no manual copy/paste required.

### Alternative: Set the Key Manually

If you already have an API key, you can save it directly:

```bash
dlazy auth set YOUR_API_KEY

The CLI saves the key in your user config directory (~/.dlazy/config.json on macOS/Linux, %USERPROFILE%\.dlazy\config.json on Windows), with file permissions restricted to your OS user account. You can also supply the key per-invocation via the DLAZY_API_KEY environment variable.

Getting Your API Key Manually

1. Sign in or create an account at dlazy.com
2. Go to dlazy.com/dashboard/organization/api-key
3. Copy the key shown in the API Key section

Each key is scoped to your dLazy organization and can be rotated or revoked at any time from the same dashboard.

About & Provenance

• CLI source code: github.com/dlazyai/cli
• Maintainer: dlazyai
• npm package: @dlazy/cli (pinned to 1.0.9 in this skill's install spec)
• Homepage: dlazy.com

You can install on demand without persisting a global binary by running:

npx @dlazy/[email protected] \x3Ccommand>

Or, if you prefer a global install, the skill's metadata.clawdbot.install field declares the exact pinned version (npm install -g @dlazy/[email protected]). Review the GitHub source before installing.

How It Works

This skill is a thin client over the dLazy hosted sandbox agent. When you invoke it:

• Your messages and options are sent to the dLazy API (api.dlazy.com), which streams the agent's reply back to your terminal.
• Any local files you attach via --files are uploaded to dLazy's media storage (files.dlazy.com) first, then referenced by url.
• Chat sessions are tracked per project so follow-up turns keep context; project and skill ids come from dlazy projects list / dlazy skills list.

This is the standard SaaS pattern; the skill itself does not access network or filesystem resources beyond what the dLazy CLI already handles. See dlazy.com for the full service terms.

Usage

This skill talks to the dlazy sandbox agent — a project-scoped assistant that can run skills (templates) end-to-end. Use it for conversational, multi-turn work rather than one-shot generation.

Discover Skills and Projects

# List the skills/templates you can start a chat with
dlazy skills list

# List existing projects in your organization
dlazy projects list

Start or Continue a Chat

# Auto-select a template from your prompt (creates a new project)
dlazy chat --prompt "Make a 3-scene storyboard about a city at night"

# Start a new project with a specific skill/template
dlazy chat --skill storyboard --prompt "..."

# Continue an existing project (skips --skill)
dlazy chat --project \x3Cproject_id> --prompt "..."

# Attach local files (uploaded to storage first)
dlazy chat --project \x3Cproject_id> --prompt "Use this reference" --files ref.png

# Session control
dlazy chat --project \x3Cproject_id> --clear      # drop the saved session, start fresh
dlazy chat --project \x3Cproject_id> --compact    # compact the current session's context

On a TTY, dlazy chat stays interactive after the first turn — type follow-up messages, or exit to leave.

CRITICAL INSTRUCTION FOR AGENT:

1. Run dlazy skills list (and dlazy projects list when continuing work) to discover valid ids.
2. Pick --skill for a new project, or --project to continue an existing one — never both.
3. Always pass --prompt for non-interactive (no-TTY) runs.
4. Run dlazy chat -h to see every option.

Error Handling

AGENT CRITICAL INSTRUCTION:

1. If the execution result returns code: "insufficient_balance", you MUST explicitly inform the user that their credits are insufficient and guide them to recharge: https://dlazy.com/dashboard/organization/settings?tab=credits
2. If the execution result returns code: "unauthorized" or indicates missing API key, you MUST inform the user to get their API key from https://dlazy.com/dashboard/organization/api-key and save it using dlazy auth set \x3Ckey> and resume the task.

Tips

Visit https://dlazy.com for more information.