agentic-eval
NewPatterns 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
Install & Usage
~/.claude.jsonAdd the configuration to "mcpServers": { "agentic-eval": { "command": "...", "args": [] } }
/mcpSecurity Audits
Frequently Asked Questions
What is agentic-eval?
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
How to install agentic-eval?
To install agentic-eval: open your mcp config (~/.claude.json), then add the config to "mcpServers": { "agentic-eval": { "command": "...", "args": [] } }. Finally, /mcp in Claude Code.
What is agentic-eval best for?
agentic-eval is a mcp categorized under General. It is designed for: testing, design, agent, ai-&-ml, data-&-analytics. Created by github.