Delegate complex coding tasks to a multi-model agent CLI.
npx skills add https://github.com/Rheasilvia/hermes-desktop --skill blackbox-rheasilvia
Please help me install this Agent Skill. Skill: blackbox Source: https://github.com/Rheasilvia/hermes-desktop/tree/main/optional-skills/autonomous-ai-agents/blackbox Command: npx skills add https://github.com/Rheasilvia/hermes-desktop --skill blackbox-rheasilvia
This skill solves the challenge of managing complex coding tasks by delegating them to a multi-model AI agent that evaluates and selects the best implementation from various LLMs.
Use the blackbox skill to add JWT authentication to the current project directory by running the terminal command with the appropriate prompt.
High-intent search queries and answers about installing and using this skill.
To automate refactoring, this skill dispatches coding tasks to a multi-model agent that evaluates outputs from models like Claude, Codex, and Gemini to select the optimal implementation. It requires Node.js 20+ and the @blackbox_ai/blackbox-cli package to interface with the Blackbox AI API.
Multi-model evaluation for code generation dispatches a single coding task to various LLMs such as Claude, Codex, and Gemini. A built-in judge mechanism then evaluates the generated outputs to automatically select the best implementation for your software project.
Yes, you can run long-running background coding tasks with process monitoring directly in the terminal. The skill supports both real-time interactive coding sessions and background execution for complex software development operations.
Yes, you need Node.js 20 or higher to use this multi-model coding agent. The skill relies on the @blackbox_ai/blackbox-cli package to interface with the Blackbox AI API and facilitate interactive coding sessions and background task execution.
You can save progress and resume complex feature implementation tasks using the checkpointing feature. This allows developers to pause long-running refactoring or coding operations and resume them at any time without losing prior context.
The best way to select the optimal code implementation is to use a multi-model judge that dispatches tasks to various LLMs like Claude, Codex, and Gemini. It evaluates the different outputs and automatically selects the best result for your project.
InverterNetworkDelegate complex coding tasks to a multi-model CLI agent for automated generation and review.
Open330Coordinate parallel planning across Claude, Codex, and Gemini with auto-save.
jonnytacos8Orchestrate interactive coding agents in PTY-enabled background terminal sessions.
jacardlDelegate coding tasks to a multi-model AI CLI agent.
