agentic-eval
Iterative LLM self-improvement patterns using reflection, evaluation, and code-specific refinement loops.
Install
npx skills add https://github.com/github/awesome-copilot --skill agentic-evalStats
| Total installs | 7,961 |
| Weekly installs | 7.9K |
| GitHub stars | 27.4K |
| First seen | Jan 23, 2026 |
| Source | @github/awesome-copilot |
Summary
- Provides three core patterns: basic reflection (self-critique loops), evaluator-optimizer (separated generation and evaluation), and code-specific test-driven refinement
- Supports multiple evaluation strategies including outcome-based assessment, LLM-as-judge comparison, and rubric-based scoring with weighted dimensions
- Includes practical Python implementations with structured JSON output parsing, iteration limits, and convergence detection to prevent infinite loops
- Best suited for quality-critical tasks like code generation, reports, and analysis where clear evaluation criteria and success metrics exist
Tags
Related skills
| Skill | Installs | vs agentic-eval |
|---|---|---|
| ai-social-media-content | 8,316 | +355 |
| logo-design-guide | 7,613 | -348 |
| prompt-engineering-patterns | 8,725 | +764 |
| prompt-builder | 7,817 | -144 |
| firecrawl-scrape | 8,534 | +573 |
FAQ
- How many installs does agentic-eval have?
- agentic-eval has 7,961 total installs and 7.9K installs this week.
- Where is agentic-eval hosted?
- agentic-eval is published by @github/awesome-copilot at https://github.com/github/awesome-copilot.
- How many GitHub stars does agentic-eval have?
- agentic-eval has 27.4K GitHub stars.
- When was agentic-eval first indexed?
- OrangeBot.AI first indexed agentic-eval on Jan 23, 2026.
- How do I install agentic-eval?
- Run: npx skills add https://github.com/github/awesome-copilot --skill agentic-eval