skills.rest
zeronx798
zeronx798COMMUNITY
Explore all skills by this author →
GitHub

blackbox

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

Updated Jul 13, 2026
Search Tags:#automation#development#refactoring#llm#multi-agent#coding
One-click install
npx skills add https://github.com/zeronx798/demo-hermes-agent --skill blackbox-zeronx798
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: blackbox
Source: https://github.com/zeronx798/demo-hermes-agent/tree/main/optional-skills/autonomous-ai-agents/blackbox
Command: npx skills add https://github.com/zeronx798/demo-hermes-agent --skill blackbox-zeronx798

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @blackboxai/cli.

What problem does it solve?

This skill solves the challenge of choosing the right AI model for coding tasks by automating the dispatch of requests to multiple LLMs and using a judge to select the highest-quality implementation.

Core Features & Use Cases

  • Multi-Model Judging: Dispatches coding prompts to multiple models like Claude, Codex, and Gemini, then evaluates the outputs to provide the best result.
  • Checkpointing & Resume: Allows for long-running coding tasks to be paused and resumed using specific checkpoints.
  • Use Case: Use this to refactor a complex legacy module where you need to compare different architectural approaches generated by various models before committing to a final implementation.

Quick Start

Use the blackbox skill to add JWT authentication to the current project directory by running the terminal command with the appropriate prompt.

Frequently Asked Questions about blackbox

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

FAQPage Schema
How does multi-model AI coding work for complex refactoring tasks?▼

Multi-model AI coding dispatches prompts to multiple LLMs like Claude, Codex, and Gemini, then evaluates the outputs to select the optimal code implementation for complex refactoring tasks.

Do I need Node.js and an API key to use multi-agent LLM coding automation?▼

Yes, multi-agent LLM coding automation requires a Node.js environment, a valid API key, and the Blackbox CLI tool to be configured before delegating development tasks.

Can I pause and resume long-running coding tasks with multi-agent LLM automation?▼

Yes, long-running coding tasks can be paused and resumed using checkpoint-based workflow management, allowing you to stop background task execution and continue later.

What is the best way to compare architectural approaches for a legacy module refactor?▼

The best way to compare architectural approaches is using a multi-model judging agent that generates implementations from various LLMs and evaluates them before you commit to a final refactor.

How do I add JWT authentication to a project using an AI coding agent?▼

To add JWT authentication, run the terminal command with your specific prompt to delegate the interactive coding session to the multi-model AI agent for implementation.

Related Skills

Explore More Software Engineering Skills→
afel6afel6

blackbox

Delegate coding tasks to the Blackbox CLI agent with multi-model adjudication.

Community
Intermediate
Kirankumar2604Kirankumar2604

diagnostics

Identify static code errors via language server diagnostics and suggest checkpoint rollbacks.

Community
Intermediate
moshehbenavrahammoshehbenavraham
2

coding-agent

Orchestrate coding agents across Claude Code, Codex CLI, OpenCode, and Pi as background sessions.

Community
Advanced
nextplus896nextplus896

laravel-routing

Configure Laravel routes with model binding and route-level authorization.

Community
Advanced