skills.rest
blueskies1818
blueskies1818COMMUNITY
Explore all skills by this author →
WebsiteGitHub

blackbox

Dispatch coding tasks to multiple LLMs and select the best result.

1|Updated May 21, 2026
Search Tags:#AI agent#multi-model#code refactoring#coding#API development
One-click install
npx skills add https://github.com/blueskies1818/hermesALIone --skill blackbox-blueskies1818
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: blackbox
Source: https://github.com/blueskies1818/hermesALIone/tree/main/Agent/optional-skills/autonomous-ai-agents/blackbox
Command: npx skills add https://github.com/blueskies1818/hermesALIone --skill blackbox-blueskies1818

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @blackboxai/cli, and includes scripts (resource) components.

What problem does it solve?

This Skill streamlines coding tasks by delegating them to Blackbox AI, a multi-model agent that runs tasks through multiple LLMs and selects the best result, saving time and improving code quality.

Core Features & Use Cases

  • Multi-Model Coding Agent: Dispatches tasks to multiple LLMs (Claude, Codex, Gemini, Blackbox Pro) for comprehensive results.
  • Built-in Judge: Evaluates outputs from different models and selects the best implementation.
  • Prerequisites: Requires the blackbox CLI and a Blackbox AI API key.
  • Use Case: Ideal for developers needing to refactor code or build REST APIs and want to leverage multiple models to ensure the best implementation.

Quick Start

Use the blackbox skill to refactor the auth module of your Express API to use OAuth 2.0.

Frequently Asked Questions about blackbox

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

FAQPage Schema
How do I use multiple LLMs to refactor code and pick the best result?▼

Multi-model code refactoring uses an AI agent to dispatch tasks to multiple LLMs, evaluates the outputs, and selects the best implementation to improve code quality and save development time.

What is the best way to build a REST API using multiple AI models?▼

Building a REST API with multiple AI models involves dispatching your coding requirements to different LLMs concurrently, using a built-in judge to evaluate the generated code, and selecting the optimal implementation.

Do I need an API key to use a multi-model coding agent for API development?▼

Yes, multi-model coding agents require the blackbox CLI installed and a valid Blackbox AI API key configured to authenticate requests and dispatch tasks to models like Claude, Codex, or Gemini.

Can I run interactive coding sessions and switch vision models during code generation?▼

Yes, multi-model coding agents support interactive sessions, non-interactive one-shots, checkpointing, MCP, and vision model switching to handle diverse coding and refactoring workflows dynamically.

How does a built-in judge evaluate generated code from different AI models?▼

A built-in judge evaluates generated code by comparing outputs from multiple LLMs dispatched for the same coding task, selecting the highest quality implementation to ensure optimal refactoring or API development results.

What are the limitations of using a multi-model agent for code refactoring?▼

Multi-model code refactoring requires external dependencies like the blackbox CLI and a Blackbox AI API key, meaning tasks cannot execute without proper environment setup and valid authentication credentials.

Related Skills

Explore More Software Engineering Skills→
zengbaochengzengbaocheng

blackbox

Delegate coding tasks to Blackbox AI CLI with multi-model evaluation.

Community
Advanced
1thirteeng31thirteeng3

blackbox

Delegate coding tasks to multiple AI models with built-in judging.

Community
Advanced
MuhammadUsmanGMMuhammadUsmanGM
1

mcp-code-execution

Execute MCP calls in external scripts to minimize agent context tokens.

Community
Advanced
wibus-weewibus-wee

pi-coding-agent

Guide development of reproducible LLM coding agents using a deterministic REPL loop.

Community
Intermediate