agentic-eval
agentic-eval (github/awesome-copilot): Patterns and techniques for evaluating and improving AI agent outputs. Use this skill when: - Implementing self-critique and reflection loops - Building evaluator-optimizer pipelines for quality-critical generation - Creating test-driven code refinement workflows - Designing rubric-based or LLM-as-judge evaluation systems - Adding iterative improvement to agent outputs (code, reports, analysis) - Measuring and improving agent response quality
Stars
40k
Votes
—
Score
46.0634
Source: github/awesome-copilot · skills/agentic-eval/SKILL.md
npx skills add github/awesome-copilot --skill agentic-eval
Related skills
| 01 | nature-figureYuan1z0825/nature-skills | Science | 51k | 4706.2 |
↗ | Yuan1z0825/nature-skills · Science · 4706.2 |
| 02 | axolotlOrchestra-Research/AI-Research-SKILLs | Science | 13k | 4128.6 |
↗ | Orchestra-Research/AI-Research-SKILLs · Science · 4128.6 |
| 03 | neuroskill-bciNousResearch/hermes-agent | Science | 263k | 5420.7 |
↗ | NousResearch/hermes-agent · Science · 5420.7 |
| 04 | aeonK-Dense-AI/scientific-agent-skills | Science | 57k | 4757.8 |
↗ | K-Dense-AI/scientific-agent-skills · Science · 4757.8 |
| 05 | anndataK-Dense-AI/scientific-agent-skills | Science | 57k | 4757.8 |
↗ | K-Dense-AI/scientific-agent-skills · Science · 4757.8 |