skills.rest
ar0cket1
ar0cket1COMMUNITY
Explore all skills by this author →
GitHub

blackbox

Automate multi-model coding tasks with Blackbox AI CLI and an internal judge.

Updated Aug 27, 2026
Search Tags:#cli#multi-model#code-generation#judge#coding-task#blackbox
One-click install
npx skills add https://github.com/ar0cket1/Hermes-Agent-Online-RL --skill blackbox-ar0cket1
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: blackbox
Source: https://github.com/ar0cket1/Hermes-Agent-Online-RL/tree/main/optional-skills/autonomous-ai-agents/blackbox
Command: npx skills add https://github.com/ar0cket1/Hermes-Agent-Online-RL --skill blackbox-ar0cket1

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Delegates coding tasks to Blackbox AI CLI, combining multiple models and an internal judge to produce higher-quality results with automated evaluation.

Core Features & Use Cases

  • Multi-model execution: dispatches tasks to Claude, Codex, Gemini, and Blackbox Pro and uses a judge to select the best implementation.
  • Flexible workflows: supports interactive sessions, one-shot prompts, checkpointing, and multi-provider configuration (MCP).
  • Quick prototyping and reviews: ideal for rapid code generation, refactors, and comparing model outputs in API and JS/TS projects.

Quick Start

Ask Blackbox CLI to generate a simple Express API endpoint and review the best output.

Frequently Asked Questions about blackbox

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

FAQPage Schema
How do I compare multiple AI models for code generation?▼

Multi-model code generation compares outputs by dispatching tasks to Claude, Codex, Gemini, and Blackbox Pro. An internal judge evaluates the responses to automatically select the best implementation, ensuring higher-quality code for your JavaScript or TypeScript projects.

What is the best way to automate rapid prototyping for an Express API?▼

Automating rapid prototyping for an Express API is best handled by delegating coding tasks to a multi-model AI judge. It dispatches your prompt to multiple models and uses an internal judge to select the highest-quality generated endpoint code.

Do I need an API key to run multi-model coding tasks?▼

Yes, you need an API key and the Blackbox AI CLI installed to run multi-model coding tasks. These prerequisites allow the internal judge to dispatch prompts across multiple providers and evaluate the best code implementation.

Can I use interactive sessions and checkpointing for code refactoring?▼

Yes, you can use interactive sessions and checkpointing for code refactoring. This multi-model workflow supports flexible development by allowing you to pause, review intermediate outputs, and compare model implementations during your coding task.

Does multi-provider configuration work with JavaScript and TypeScript scripts?▼

Multi-provider configuration works across JavaScript, TypeScript, and API scripts. It dispatches coding tasks to various models using MCP configuration, allowing the internal judge to evaluate and select the optimal implementation for your specific script environment.

Related Skills

Explore More Software Engineering Skills→
zengbaochengzengbaocheng

blackbox

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

Community
Advanced
trotsky1997trotsky1997
6

cursor-agent-development

Orchestrate interactive development sessions with the cursor-agent CLI.

Community
Intermediate
rongarederongarede
4

collaborating-with-codex

Delegate coding tasks to Codex CLI via a Python bridge with JSON outputs.

Community
Intermediate
ollieb89ollieb89

llm-evaluation

Evaluate LLM outputs with automated metrics and LLM-as-Judge workflows.

Community
Advanced