blackbox

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

Updated May 14, 2026
One-click install
npx skills add https://github.com/SethyPagna/Secretary-Jarvis --skill blackbox-sethypagna
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: blackbox
Source: https://github.com/SethyPagna/Secretary-Jarvis/tree/main/src/capabilities/optional-skills/autonomous-ai-agents/blackbox
Command: npx skills add https://github.com/SethyPagna/Secretary-Jarvis --skill blackbox-sethypagna

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill reduces the effort of handing off coding tasks by routing them to a multi-model Blackbox AI agent and returning the strongest result, so you can offload implementation work, refactors, and reviews faster.

Core Features & Use Cases

  • Multi-Model Delegation: Sends programming tasks to Blackbox AI through the terminal and benefits from model comparison plus a built-in judge.
  • Long-Running Workflows: Supports background execution, live monitoring, input submission, and kill controls for extended tasks.
  • Checkpointed Resumption: Lets you pause and continue work from saved checkpoints for iterative development.
  • PR Review and Parallel Tasks: Useful for reviewing pull requests in isolated clones and running multiple independent coding jobs at once.

Quick Start

Use the blackbox skill to delegate a coding task through the terminal and ask it to deliver the best implementation with a short summary of changes.

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?▼

You can delegate coding tasks to a multi-model AI agent by routing them through a CLI tool like Blackbox, which compares outputs across models, judges the strongest result, and returns the completed implementation.

Can I run long-running refactors and monitor them in the background?▼

Yes, long-running refactors execute in the background with live session monitoring, input submission, and kill controls, enabling you to manage extended coding workflows without blocking your terminal.

Do I need a configured API key and PTY-based terminal to use a coding agent?▼

Yes, delegating work to this multi-model coding agent requires an installed Blackbox CLI, a configured API key, and PTY-based terminal execution to handle background sessions and model-switching.

What is the best way to review pull requests using an AI coding agent?▼

Reviewing pull requests with an AI coding agent is best handled by isolating repository clones, allowing the multi-model agent to analyze the code, compare implementations, and return judged review feedback.

How do I resume an iterative development workflow from a saved checkpoint?▼

You resume iterative development workflows from saved checkpoints by using the checkpointed resumption feature, which lets you pause and continue long-running coding tasks without losing prior progress.