Back to skills
SkillHub ClubAnalyze Data & AIFull StackData / AI

harbor

Harbor framework for agent evaluation. Use when: (1) Running harbor commands (harbor run, harbor tasks check), (2) Creating/validating SkillsBench tasks, (3) Understanding task format or debugging failures.

Packaged view

This page reorganizes the original catalog entry around fit, installability, and workflow context first. The original raw source lives below.

Stars
785
Hot score
99
Updated
March 20, 2026
Overall rating
C5.1
Composite score
5.1
Best-practice grade
A92.0

Install command

npx @skill-hub/cli install benchflow-ai-skillsbench-harbor

Repository

benchflow-ai/SkillsBench

Skill path: .claude/skills/harbor

Harbor framework for agent evaluation. Use when: (1) Running harbor commands (harbor run, harbor tasks check), (2) Creating/validating SkillsBench tasks, (3) Understanding task format or debugging failures.

Open repository

Best for

Primary workflow: Analyze Data & AI.

Technical facets: Full Stack, Data / AI.

Target audience: Development teams looking for install-ready agent workflows..

License: Unknown.

Original source

Catalog source: SkillHub Club.

Repository owner: benchflow-ai.

This is still a mirrored public skill entry. Review the repository before installing into production workflows.

What it helps with

  • Install harbor into Claude Code, Codex CLI, Gemini CLI, or OpenCode workflows
  • Review https://github.com/benchflow-ai/SkillsBench before adding harbor to shared team environments
  • Use harbor for development workflows

Works across

Claude CodeCodex CLIGemini CLIOpenCode

Favorites: 0.

Sub-skills: 0.

Aggregator: No.