blackbox

Orchestrate multi-model coding tasks via the Blackbox CLI.

2|Updated Mar 26, 2026
One-click install
npx skills add https://github.com/CUexter/hermes-agent --skill blackbox-cuexter
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: blackbox
Source: https://github.com/CUexter/hermes-agent/tree/main/optional-skills/autonomous-ai-agents/blackbox
Command: npx skills add https://github.com/CUexter/hermes-agent --skill blackbox-cuexter

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Blackbox automates coding workflows by orchestrating multiple AI models through the Blackbox CLI, ensuring consistent results and faster delivery.

Core Features & Use Cases

  • Multi-model coding: Delegate coding tasks to multiple models and use an internal judge to select the best implementation.
  • Interactive and non-interactive modes: Supports interactive sessions, one-shot prompts, checkpointing, and resume capabilities for long-running tasks.
  • Parallel work & session management: Spawn multiple concurrent tasks and manage them from a single interface.
  • Vision and multimodal prompts: Handles multimodal inputs and model switching for diverse task types.
  • CLI-driven workflows: Scriptable, repeatable tasks including PR reviews, code quality checks, and automation.

Quick Start

Run a sample task with Blackbox by prompting the CLI to implement a small feature, such as adding JWT authentication to an Express API.

Frequently Asked Questions about blackbox

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

FAQPage Schema
How do I automate code generation across multiple AI models?

Multi-model code generation is automated by delegating coding tasks to multiple models and using an internal judge to select the highest-quality implementation. This ensures consistent results and faster delivery for software development workflows.

Can I run parallel coding tasks and manage multiple AI sessions concurrently?

Yes, you can spawn multiple concurrent tasks and manage them from a single interface. The system supports parallel work and session management, allowing interactive sessions, one-shot prompts, checkpointing, and resume capabilities for long-running tasks.

How do I automate PR reviews and code quality checks via CLI?

PR reviews and code quality checks are automated through scriptable, repeatable CLI-driven workflows. You can prompt the CLI with specific review tasks to execute automated checks and generate consistent code quality reports.

Does the coding assistant support vision prompts and multimodal inputs?

Yes, the coding assistant handles vision and multimodal prompts. It supports multimodal inputs and model switching, allowing you to process diverse task types that require visual context alongside standard text-based code generation.

What is the best way to implement a small feature using an AI CLI?

To implement a small feature, run a sample task by prompting the AI CLI with a specific instruction, such as adding JWT authentication to an Express API. The CLI orchestrates the models to deliver the complete implementation automatically.

When should I use checkpointing for long-running coding tasks?

Checkpointing should be used for long-running coding tasks to ensure progress is saved. It provides resume capabilities, allowing you to pause and continue interactive or non-interactive sessions without losing previous work.