agent-evaluation
π―Skillfrom davila7/claude-code-templates
|Evaluates AI agent performance by systematically testing and scoring their capabilities across multiple predefined metrics and scenarios.
Same repository
davila7/claude-code-templates(666 items)
Installation
npx skills add https://github.com/davila7/claude-code-templates --skill agent-evaluation~/.claude/skills/agent-evaluation/SKILL.mdNeed more details? View full documentation on GitHub β
SKILL.md
More from this repository10
Ready-to-use Claude Code templates organized by workflow
Automated documentation generation with API docs, technical writing, and content management
DevOps automation suite with CI/CD, infrastructure management, and deployment orchestration
A Claude Code template for building production-grade Next.js applications with Vercel deployment, providing best-practice project structure, configuration, and workflow patterns.
Project management toolkit with sprint planning, task automation, and team collaboration tools
Enterprise security toolkit with auditing, penetration testing, and compliance automation
A Claude Code template for building applications with Supabase, providing pre-configured patterns for authentication, database operations, and real-time features.
A Claude Code template for comprehensive testing workflows, providing pre-configured patterns for unit testing, integration testing, and end-to-end testing.
Performance optimization suite with profiling, bundle analysis, and speed improvement tools
Git workflow automation: feature, release, and hotfix commands with git specialists