agentic-eval
by github
· Github
· 9056 installs
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
Add agentic-eval to your agent in AIniverse
Discover more reusable skills, save them to your stack, get notified when new ones land.
Open in App · skills.shMore agent skills
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is...
gstack-autoplan
Fully reviewed plan running CEO → design → eng review automatically.
android-agp-9-upgrade
Upgrades, or migrates, an Android project to use Android Gradle Plugin (AGP) version 9. Do not use this skill for mig...
gstack-benchmark
Baseline page load times, Core Web Vitals, and resource sizes.