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.
Key Features
- Comprehensive skill evaluation and performance tracking
- Community-driven ratings and reviews
- Easy integration with Claude Code
- Regular updates and maintenance
Quick Start
TopRank Skills install NeverSight/harborchat Comments (0)
Sign in to join the discussion and leave a comment.
Skill Details
GitHub Stars
66
GitHub Forks
19
Created
Mar 2026
Last Updated
3个月前
tools
tools debugging
Related Skills
Build your own?
Join 12,000+ developers contributing to the Claude ecosystem.
No comments yet. Be the first to share your thoughts!