blackbox

Delegate coding tasks to a multi-model AI agent via the Blackbox CLI.

1.2k|116|Updated Mar 19, 2026
One-click install
npx skills add https://github.com/math-inc/OpenGauss --skill blackbox-math-inc
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: blackbox
Source: https://github.com/math-inc/OpenGauss/tree/main/optional-skills/autonomous-ai-agents/blackbox
Command: npx skills add https://github.com/math-inc/OpenGauss --skill blackbox-math-inc

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Delegation of coding tasks to a Blackbox AI CLI agent, enabling a competitive multi-model evaluation and automatic selection of best results.

Core Features & Use Cases

  • Multi-model evaluation and built-in judge to compare outputs from different models
  • Interactive sessions, checkpointing, and easy task resumption
  • Simple integration with Blackbox CLI and API key for scalable coding tasks

Quick Start

Install the Blackbox CLI, configure your API key, and run your first task with a simple prompt.

Frequently Asked Questions about blackbox

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I delegate coding tasks to a multi-model AI agent?▼

Delegate coding tasks to a multi-model AI agent using the Blackbox CLI. The tool automates interactive coding, reviews, and checkpointed workflows by sending prompts directly through the command line interface.

Can I compare outputs from different AI models for code generation?▼

Compare outputs from different AI models for code generation using the built-in multi-model evaluation. A built-in judge automatically evaluates and selects the best results from the generated code outputs.

How do I resume long-running coding tasks if my session is interrupted?▼

Resume long-running coding tasks interrupted by session failures using checkpointing. The CLI supports saving task progress, allowing you to easily resume interactive coding sessions from the last saved checkpoint.

Do I need an API key to run the Blackbox CLI for automated code reviews?▼

You need an API key configured to run the Blackbox CLI for automated code reviews. The CLI requires both the Blackbox CLI installation and a valid API key setup to execute scalable coding tasks.

What is the best way to handle complex debugging workflows with multiple AI models?▼

Handle complex debugging workflows with multiple AI models by switching models during a checkpointed session. This approach enables competitive multi-model evaluation to automatically select the best debugging results.

Can I use the Blackbox CLI for one-shot coding tasks instead of long sessions?▼

Use the Blackbox CLI for one-shot coding tasks instead of long sessions. The agent supports both one-shot prompts and long-running interactive tasks, accommodating quick fixes and complex development workflows.