harbor-task-creator

Automate creation and management of AI agent evaluation tasks in Harbor.

Updated Mar 27, 2026
One-click install
npx skills add https://github.com/qiushiyan/harbor-eval-experiments --skill harbor-task-creator
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: harbor-task-creator
Source: https://github.com/qiushiyan/harbor-eval-experiments/tree/main/.claude/skills/harbor-task-creator
Command: npx skills add https://github.com/qiushiyan/harbor-eval-experiments --skill harbor-task-creator

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill addresses the challenge of creating and managing complex evaluation tasks for AI agents in the Harbor platform, streamlining the setup and maintenance of benchmark challenges.

Core Features & Use Cases

  • Task Creation: Automates the generation of essential files for new Harbor tasks, including configuration, instructions, and Docker setup.
  • Task Management: Provides tools for debugging, validating, and refining existing tasks.
  • Use Case: When you need to create a new benchmark task for AI agents, this Skill can save time by automating the creation of necessary files and configurations.

Quick Start

Run the following command to initialize a new task: harbor tasks init my-task

Frequently Asked Questions about harbor-task-creator

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

FAQPage Schema
How do I create a benchmark task for AI agents in Harbor?

You create a Harbor benchmark task by running `harbor tasks init my-task`, which automates the generation of necessary configuration files, instructions, and Docker setup for new benchmark challenges.

What is needed to set up evaluation tasks for AI agents in Harbor?

Setting up Harbor evaluation tasks requires Docker and knowledge of the Harbor task structure. The Skill automates configuration generation, but you need these prerequisites to properly initialize and manage the benchmark environment.

Can I debug existing Harbor benchmark tasks?

Yes, you can debug existing Harbor benchmark tasks. The Skill provides tools for task management, allowing you to validate, debug, and refine existing evaluation tasks alongside creating new ones.

What files are generated when initializing a new Harbor task?

Initializing a new Harbor task generates essential files including configuration files, instructions, and Docker setup. It also creates verification scripts to ensure the benchmark task is properly structured and functional.

Why are my Harbor task configuration files not validating correctly?

If your Harbor task configuration files are not validating, use the Skill's task management tools to debug and refine existing tasks. Ensure your Docker setup and Harbor task structure match the expected benchmark requirements.